- R1: flipping 1 answer keeps truth in range 98-100% but cuts head hit by a third or more; 2 flips squeeze truth out in 7-10% of ±30/±60 replays (two flips = 8 points = SEPARATION_LEAD). - R2: weights do apply (research scorer == production at V0); V1/V2 are identity at ±30/±60 by construction and leave six-question metrics unchanged at ±10 -> no_benefit (measured). Supplementary V1n does not pass the gate. - R3: boundary shift is ~3.8 days/minute (1.3-5.9), not 1.1; the 45-day gate is ~8-34 minutes. The _representative_pairs hypothesis is refuted (all-pairs adds no dated probes); the bottleneck is monthly evaluation. New finding recorded as BUG-1048 (investigating): _boundary_windows year-straddle exemption and positional zip misalignment bypass the gate. - Dated errata appended (no deletions) to the 09-14/09-16 briefs and research docs; README board row -> 待验收. No production code, scoring, thresholds, gates or Skill changed. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8
5682 lines
121 KiB
JSON
5682 lines
121 KiB
JSON
{
|
|
"generated_at": "2026-09-26",
|
|
"nature": "offline replay on the public AA open set (v4); not a blind test, not accuracy",
|
|
"ayanamsa": "raman",
|
|
"node_mode": "mean",
|
|
"holdout": "references/real_case_calibration/minute_rectification_holdout_v4.json",
|
|
"case_count": 20,
|
|
"radii": [
|
|
10,
|
|
30,
|
|
60
|
|
],
|
|
"minute_step": 2,
|
|
"gate": "G0 production (45 / refresh 30)",
|
|
"factor_table_V1": {
|
|
"10": {
|
|
"D2": 0.3333,
|
|
"D3": 0.5,
|
|
"D4": 1.0,
|
|
"D5": 0.8333,
|
|
"D7": 1.0,
|
|
"D9": 1.0,
|
|
"D10": 1.0,
|
|
"D11": 1.0,
|
|
"D12": 1.0,
|
|
"D24": 1.0,
|
|
"D30": 1.0
|
|
},
|
|
"30": {
|
|
"D2": 1.0,
|
|
"D3": 1.0,
|
|
"D4": 1.0,
|
|
"D5": 1.0,
|
|
"D7": 1.0,
|
|
"D9": 1.0,
|
|
"D10": 1.0,
|
|
"D11": 1.0,
|
|
"D12": 1.0,
|
|
"D24": 1.0,
|
|
"D30": 1.0
|
|
},
|
|
"60": {
|
|
"D2": 1.0,
|
|
"D3": 1.0,
|
|
"D4": 1.0,
|
|
"D5": 1.0,
|
|
"D7": 1.0,
|
|
"D9": 1.0,
|
|
"D10": 1.0,
|
|
"D11": 1.0,
|
|
"D12": 1.0,
|
|
"D24": 1.0,
|
|
"D30": 1.0
|
|
}
|
|
},
|
|
"factor_table_V1n": {
|
|
"D2": 0.170513,
|
|
"D3": 0.255769,
|
|
"D4": 1.364103,
|
|
"D5": 0.426282,
|
|
"D7": 0.596795,
|
|
"D9": 0.769231,
|
|
"D10": 0.852564,
|
|
"D11": 0.937821,
|
|
"D12": 1.023077,
|
|
"D24": 2.046154,
|
|
"D30": 2.557692
|
|
},
|
|
"varga_minutes": {
|
|
"D2": 60.0,
|
|
"D3": 40.0,
|
|
"D4": 7.5,
|
|
"D5": 24.0,
|
|
"D7": 17.143,
|
|
"D9": 13.3,
|
|
"D10": 12.0,
|
|
"D11": 10.909,
|
|
"D12": 10.0,
|
|
"D24": 5.0,
|
|
"D30": 4.0
|
|
},
|
|
"domain_prefixes": {
|
|
"education": [
|
|
"D24",
|
|
"D5"
|
|
],
|
|
"relocation": [
|
|
"D4"
|
|
],
|
|
"relationship": [
|
|
"D9"
|
|
],
|
|
"career": [
|
|
"D10"
|
|
],
|
|
"finance": [
|
|
"D2",
|
|
"D11"
|
|
],
|
|
"health_pressure": [
|
|
"D30"
|
|
],
|
|
"family": [
|
|
"D12",
|
|
"D7",
|
|
"D3"
|
|
],
|
|
"appearance": [],
|
|
"occupation": [
|
|
"D10"
|
|
]
|
|
},
|
|
"proof": {
|
|
"10": {
|
|
"production_vs_V0_policy": {
|
|
"cases_with_any_change": 0,
|
|
"cases": 20,
|
|
"candidates_changed": 0,
|
|
"candidates_total": 220,
|
|
"max_abs_delta": 0.0,
|
|
"cases_top_changed": 0
|
|
},
|
|
"V1_vs_V0": {
|
|
"cases_with_any_change": 17,
|
|
"cases": 20,
|
|
"candidates_changed": 168,
|
|
"candidates_total": 220,
|
|
"max_abs_delta": 0.4284,
|
|
"cases_top_changed": 0
|
|
},
|
|
"V2_vs_V0": {
|
|
"cases_with_any_change": 17,
|
|
"cases": 20,
|
|
"candidates_changed": 159,
|
|
"candidates_total": 220,
|
|
"max_abs_delta": 0.625,
|
|
"cases_top_changed": 1
|
|
},
|
|
"V1n_vs_V0": {
|
|
"cases_with_any_change": 20,
|
|
"cases": 20,
|
|
"candidates_changed": 220,
|
|
"candidates_total": 220,
|
|
"max_abs_delta": 1.8142,
|
|
"cases_top_changed": 4
|
|
},
|
|
"V2_cases_dropping_any_domain_prefix": 12,
|
|
"V0_varga_hits_total": {
|
|
"D10": 1035,
|
|
"D12": 744,
|
|
"D24": 2325,
|
|
"D3": 886,
|
|
"D30": 470,
|
|
"D4": 568,
|
|
"D5": 2782,
|
|
"D7": 854,
|
|
"D9": 530
|
|
}
|
|
},
|
|
"30": {
|
|
"production_vs_V0_policy": {
|
|
"cases_with_any_change": 0,
|
|
"cases": 20,
|
|
"candidates_changed": 0,
|
|
"candidates_total": 620,
|
|
"max_abs_delta": 0.0,
|
|
"cases_top_changed": 0
|
|
},
|
|
"V1_vs_V0": {
|
|
"cases_with_any_change": 0,
|
|
"cases": 20,
|
|
"candidates_changed": 0,
|
|
"candidates_total": 620,
|
|
"max_abs_delta": 0.0,
|
|
"cases_top_changed": 0
|
|
},
|
|
"V2_vs_V0": {
|
|
"cases_with_any_change": 0,
|
|
"cases": 20,
|
|
"candidates_changed": 0,
|
|
"candidates_total": 620,
|
|
"max_abs_delta": 0.0,
|
|
"cases_top_changed": 0
|
|
},
|
|
"V1n_vs_V0": {
|
|
"cases_with_any_change": 20,
|
|
"cases": 20,
|
|
"candidates_changed": 619,
|
|
"candidates_total": 620,
|
|
"max_abs_delta": 2.0199,
|
|
"cases_top_changed": 3
|
|
},
|
|
"V2_cases_dropping_any_domain_prefix": 0,
|
|
"V0_varga_hits_total": {
|
|
"D10": 2380,
|
|
"D12": 2195,
|
|
"D24": 6362,
|
|
"D3": 2425,
|
|
"D30": 1405,
|
|
"D4": 1915,
|
|
"D5": 6726,
|
|
"D7": 2226,
|
|
"D9": 1301
|
|
}
|
|
},
|
|
"60": {
|
|
"production_vs_V0_policy": {
|
|
"cases_with_any_change": 0,
|
|
"cases": 20,
|
|
"candidates_changed": 0,
|
|
"candidates_total": 1220,
|
|
"max_abs_delta": 0.0,
|
|
"cases_top_changed": 0
|
|
},
|
|
"V1_vs_V0": {
|
|
"cases_with_any_change": 0,
|
|
"cases": 20,
|
|
"candidates_changed": 0,
|
|
"candidates_total": 1220,
|
|
"max_abs_delta": 0.0,
|
|
"cases_top_changed": 0
|
|
},
|
|
"V2_vs_V0": {
|
|
"cases_with_any_change": 0,
|
|
"cases": 20,
|
|
"candidates_changed": 0,
|
|
"candidates_total": 1220,
|
|
"max_abs_delta": 0.0,
|
|
"cases_top_changed": 0
|
|
},
|
|
"V1n_vs_V0": {
|
|
"cases_with_any_change": 20,
|
|
"cases": 20,
|
|
"candidates_changed": 1210,
|
|
"candidates_total": 1220,
|
|
"max_abs_delta": 3.8397,
|
|
"cases_top_changed": 3
|
|
},
|
|
"V2_cases_dropping_any_domain_prefix": 0,
|
|
"V0_varga_hits_total": {
|
|
"D10": 5318,
|
|
"D12": 4556,
|
|
"D24": 11853,
|
|
"D3": 5344,
|
|
"D30": 3610,
|
|
"D4": 5099,
|
|
"D5": 12539,
|
|
"D7": 4315,
|
|
"D9": 1920
|
|
}
|
|
}
|
|
},
|
|
"metrics": {
|
|
"10": {
|
|
"V0": {
|
|
"n": 20,
|
|
"top1": 0.8,
|
|
"coverage": 1.0,
|
|
"width_median": 15.0,
|
|
"tie": 0.0,
|
|
"squeezed": 0,
|
|
"entropy0": 2.5595,
|
|
"entropy6": 2.0346,
|
|
"probes_mean": 5.1,
|
|
"refresh_mean": 3.25,
|
|
"discriminative_mean": 3.25,
|
|
"unique_mean": 2.5,
|
|
"alive": 20,
|
|
"engine_top1": 0.3
|
|
},
|
|
"V1": {
|
|
"n": 20,
|
|
"top1": 0.8,
|
|
"coverage": 1.0,
|
|
"width_median": 15.0,
|
|
"tie": 0.0,
|
|
"squeezed": 0,
|
|
"entropy0": 2.5595,
|
|
"entropy6": 2.0346,
|
|
"probes_mean": 5.1,
|
|
"refresh_mean": 3.25,
|
|
"discriminative_mean": 3.25,
|
|
"unique_mean": 2.5,
|
|
"alive": 20,
|
|
"engine_top1": 0.3,
|
|
"verdict_vs_V0": "no_benefit"
|
|
},
|
|
"V2": {
|
|
"n": 20,
|
|
"top1": 0.8,
|
|
"coverage": 1.0,
|
|
"width_median": 15.0,
|
|
"tie": 0.0,
|
|
"squeezed": 0,
|
|
"entropy0": 2.5595,
|
|
"entropy6": 2.0346,
|
|
"probes_mean": 5.1,
|
|
"refresh_mean": 3.25,
|
|
"discriminative_mean": 3.25,
|
|
"unique_mean": 2.5,
|
|
"alive": 20,
|
|
"engine_top1": 0.35,
|
|
"verdict_vs_V0": "no_benefit"
|
|
},
|
|
"V1n": {
|
|
"n": 20,
|
|
"top1": 0.85,
|
|
"coverage": 1.0,
|
|
"width_median": 15.0,
|
|
"tie": 0.0,
|
|
"squeezed": 0,
|
|
"entropy0": 2.5601,
|
|
"entropy6": 2.0353,
|
|
"probes_mean": 5.1,
|
|
"refresh_mean": 3.25,
|
|
"discriminative_mean": 3.25,
|
|
"unique_mean": 2.6,
|
|
"alive": 20,
|
|
"engine_top1": 0.45,
|
|
"verdict_vs_V0": "no_benefit"
|
|
}
|
|
},
|
|
"30": {
|
|
"V0": {
|
|
"n": 20,
|
|
"top1": 0.55,
|
|
"coverage": 1.0,
|
|
"width_median": 33.0,
|
|
"tie": 0.0,
|
|
"squeezed": 0,
|
|
"entropy0": 4.0386,
|
|
"entropy6": 3.1646,
|
|
"probes_mean": 7.1,
|
|
"refresh_mean": 5.45,
|
|
"discriminative_mean": 5.45,
|
|
"unique_mean": 3.9,
|
|
"alive": 20,
|
|
"engine_top1": 0.2
|
|
},
|
|
"V1": {
|
|
"n": 20,
|
|
"top1": 0.55,
|
|
"coverage": 1.0,
|
|
"width_median": 33.0,
|
|
"tie": 0.0,
|
|
"squeezed": 0,
|
|
"entropy0": 4.0386,
|
|
"entropy6": 3.1646,
|
|
"probes_mean": 7.1,
|
|
"refresh_mean": 5.45,
|
|
"discriminative_mean": 5.45,
|
|
"unique_mean": 3.9,
|
|
"alive": 20,
|
|
"engine_top1": 0.2,
|
|
"verdict_vs_V0": "no_benefit"
|
|
},
|
|
"V2": {
|
|
"n": 20,
|
|
"top1": 0.55,
|
|
"coverage": 1.0,
|
|
"width_median": 33.0,
|
|
"tie": 0.0,
|
|
"squeezed": 0,
|
|
"entropy0": 4.0386,
|
|
"entropy6": 3.1646,
|
|
"probes_mean": 7.1,
|
|
"refresh_mean": 5.45,
|
|
"discriminative_mean": 5.45,
|
|
"unique_mean": 3.9,
|
|
"alive": 20,
|
|
"engine_top1": 0.2,
|
|
"verdict_vs_V0": "no_benefit"
|
|
},
|
|
"V1n": {
|
|
"n": 20,
|
|
"top1": 0.6,
|
|
"coverage": 1.0,
|
|
"width_median": 33.0,
|
|
"tie": 0.0,
|
|
"squeezed": 0,
|
|
"entropy0": 4.0384,
|
|
"entropy6": 3.1647,
|
|
"probes_mean": 7.1,
|
|
"refresh_mean": 5.45,
|
|
"discriminative_mean": 5.45,
|
|
"unique_mean": 4.0,
|
|
"alive": 20,
|
|
"engine_top1": 0.15,
|
|
"verdict_vs_V0": "no_benefit"
|
|
}
|
|
},
|
|
"60": {
|
|
"V0": {
|
|
"n": 20,
|
|
"top1": 0.4,
|
|
"coverage": 1.0,
|
|
"width_median": 56.0,
|
|
"tie": 0.0,
|
|
"squeezed": 0,
|
|
"entropy0": 4.9942,
|
|
"entropy6": 3.9537,
|
|
"probes_mean": 7.2,
|
|
"refresh_mean": 5.75,
|
|
"discriminative_mean": 5.4,
|
|
"unique_mean": 4.0,
|
|
"alive": 20,
|
|
"engine_top1": 0.05
|
|
},
|
|
"V1": {
|
|
"n": 20,
|
|
"top1": 0.4,
|
|
"coverage": 1.0,
|
|
"width_median": 56.0,
|
|
"tie": 0.0,
|
|
"squeezed": 0,
|
|
"entropy0": 4.9942,
|
|
"entropy6": 3.9537,
|
|
"probes_mean": 7.2,
|
|
"refresh_mean": 5.75,
|
|
"discriminative_mean": 5.4,
|
|
"unique_mean": 4.0,
|
|
"alive": 20,
|
|
"engine_top1": 0.05,
|
|
"verdict_vs_V0": "no_benefit"
|
|
},
|
|
"V2": {
|
|
"n": 20,
|
|
"top1": 0.4,
|
|
"coverage": 1.0,
|
|
"width_median": 56.0,
|
|
"tie": 0.0,
|
|
"squeezed": 0,
|
|
"entropy0": 4.9942,
|
|
"entropy6": 3.9537,
|
|
"probes_mean": 7.2,
|
|
"refresh_mean": 5.75,
|
|
"discriminative_mean": 5.4,
|
|
"unique_mean": 4.0,
|
|
"alive": 20,
|
|
"engine_top1": 0.05,
|
|
"verdict_vs_V0": "no_benefit"
|
|
},
|
|
"V1n": {
|
|
"n": 20,
|
|
"top1": 0.5,
|
|
"coverage": 1.0,
|
|
"width_median": 73.0,
|
|
"tie": 0.0,
|
|
"squeezed": 0,
|
|
"entropy0": 4.9926,
|
|
"entropy6": 3.9539,
|
|
"probes_mean": 7.2,
|
|
"refresh_mean": 5.9,
|
|
"discriminative_mean": 5.55,
|
|
"unique_mean": 4.2,
|
|
"alive": 20,
|
|
"engine_top1": 0.1,
|
|
"verdict_vs_V0": "no_benefit"
|
|
}
|
|
}
|
|
},
|
|
"per_case": [
|
|
{
|
|
"case_id": "barack_obama_1961_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.4284,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.5326,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 1.0749,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D12": 14,
|
|
"D24": 125,
|
|
"D3": 22,
|
|
"D4": 66,
|
|
"D5": 487,
|
|
"D7": 13,
|
|
"D9": 1
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D30",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {
|
|
"family": [
|
|
"D3"
|
|
],
|
|
"relocation": [
|
|
"D4"
|
|
]
|
|
}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 15,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 15,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 15,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 15,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "barack_obama_1961_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 1.0749,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 29,
|
|
"D12": 31,
|
|
"D24": 533,
|
|
"D3": 53,
|
|
"D4": 195,
|
|
"D5": 687,
|
|
"D7": 33,
|
|
"D9": 9
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 39,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 39,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 39,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 39,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "barack_obama_1961_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 61,
|
|
"max_abs": 1.0749,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 62,
|
|
"D12": 56,
|
|
"D24": 1027,
|
|
"D3": 86,
|
|
"D4": 394,
|
|
"D5": 1100,
|
|
"D7": 61,
|
|
"D9": 11
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 25,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 25,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 25,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 25,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "angelina_jolie_1975_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.3125,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.3125,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.9221,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 14,
|
|
"D12": 20,
|
|
"D3": 32,
|
|
"D30": 24,
|
|
"D7": 22,
|
|
"D9": 7
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {
|
|
"family": [
|
|
"D3"
|
|
]
|
|
}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 19,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 19,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 19,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 19,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "angelina_jolie_1975_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 0.9221,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 14,
|
|
"D12": 74,
|
|
"D3": 83,
|
|
"D30": 71,
|
|
"D7": 52,
|
|
"D9": 22
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "angelina_jolie_1975_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 61,
|
|
"max_abs": 1.4349,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 177,
|
|
"D12": 151,
|
|
"D3": 147,
|
|
"D30": 420,
|
|
"D7": 137,
|
|
"D9": 40
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 53,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 53,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 53,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 53,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "tiger_woods_1975_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.1875,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.625,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.4115,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D12": 13,
|
|
"D24": 176,
|
|
"D3": 14,
|
|
"D30": 11,
|
|
"D5": 232,
|
|
"D7": 1
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {
|
|
"education": [
|
|
"D5"
|
|
],
|
|
"family": [
|
|
"D3"
|
|
],
|
|
"health_pressure": [
|
|
"D30"
|
|
]
|
|
}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 5
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 5
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 5
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 5
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "tiger_woods_1975_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 1.3121,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 6,
|
|
"D12": 39,
|
|
"D24": 287,
|
|
"D3": 38,
|
|
"D30": 28,
|
|
"D5": 582,
|
|
"D7": 8,
|
|
"D9": 30
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 27,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 27,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 27,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 27,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "tiger_woods_1975_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 61,
|
|
"max_abs": 1.5801,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 111,
|
|
"D12": 70,
|
|
"D24": 449,
|
|
"D3": 64,
|
|
"D30": 46,
|
|
"D5": 885,
|
|
"D7": 44,
|
|
"D9": 37
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "elizabeth_taylor_1932_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 5,
|
|
"max_abs": 0.1875,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 5,
|
|
"max_abs": 0.1875,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.5526,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 203,
|
|
"D12": 8,
|
|
"D3": 9,
|
|
"D30": 5,
|
|
"D4": 155
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 13,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 13,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 13,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 13,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "elizabeth_taylor_1932_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 0.5526,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 212,
|
|
"D12": 26,
|
|
"D3": 35,
|
|
"D30": 52,
|
|
"D4": 400,
|
|
"D7": 4
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 7,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 7,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 7,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 7,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "elizabeth_taylor_1932_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 58,
|
|
"max_abs": 1.3255,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 257,
|
|
"D12": 59,
|
|
"D3": 64,
|
|
"D30": 396,
|
|
"D4": 487,
|
|
"D7": 15
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 33,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 33,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 33,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 33,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "elizabeth_montgomery_1933_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.1875,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.25,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.4832,
|
|
"top_changed": true
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 29,
|
|
"D12": 16,
|
|
"D24": 73,
|
|
"D3": 19,
|
|
"D30": 150,
|
|
"D5": 162,
|
|
"D7": 12,
|
|
"D9": 86
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D30",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {
|
|
"family": [
|
|
"D3"
|
|
]
|
|
}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 7,
|
|
"engine_top1": false,
|
|
"probes": 7,
|
|
"refresh": 1
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 7,
|
|
"engine_top1": false,
|
|
"probes": 7,
|
|
"refresh": 1
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 7,
|
|
"engine_top1": false,
|
|
"probes": 7,
|
|
"refresh": 1
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 7,
|
|
"engine_top1": true,
|
|
"probes": 7,
|
|
"refresh": 1
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "elizabeth_montgomery_1933_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 0.4832,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 146,
|
|
"D12": 36,
|
|
"D24": 252,
|
|
"D3": 39,
|
|
"D30": 418,
|
|
"D5": 366,
|
|
"D7": 33,
|
|
"D9": 265
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 33,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 33,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 33,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 33,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "elizabeth_montgomery_1933_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 61,
|
|
"max_abs": 1.0541,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 164,
|
|
"D12": 53,
|
|
"D24": 508,
|
|
"D3": 60,
|
|
"D30": 1006,
|
|
"D5": 587,
|
|
"D7": 79,
|
|
"D9": 366
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 55,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 55,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 55,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 55,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "pablo_picasso_1881_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.2292,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.5,
|
|
"top_changed": true
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.7811,
|
|
"top_changed": true
|
|
},
|
|
"V0_varga_hits": {
|
|
"D12": 6,
|
|
"D24": 217,
|
|
"D3": 12,
|
|
"D4": 61,
|
|
"D5": 16,
|
|
"D7": 13,
|
|
"D9": 16
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D4",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {
|
|
"education": [
|
|
"D5"
|
|
],
|
|
"family": [
|
|
"D3"
|
|
]
|
|
}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": true,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": true,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "pablo_picasso_1881_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 0.7811,
|
|
"top_changed": true
|
|
},
|
|
"V0_varga_hits": {
|
|
"D12": 20,
|
|
"D24": 283,
|
|
"D3": 35,
|
|
"D4": 232,
|
|
"D5": 232,
|
|
"D7": 39,
|
|
"D9": 16
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": true,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "pablo_picasso_1881_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 61,
|
|
"max_abs": 0.7811,
|
|
"top_changed": true
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 244,
|
|
"D12": 45,
|
|
"D24": 504,
|
|
"D3": 50,
|
|
"D4": 356,
|
|
"D5": 547,
|
|
"D7": 50,
|
|
"D9": 26
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 1439,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 1439,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 1439,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 1439,
|
|
"engine_top1": true,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "sigmund_freud_1856_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.1888,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.1888,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.4396,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 13,
|
|
"D24": 168,
|
|
"D3": 17,
|
|
"D30": 149,
|
|
"D5": 12,
|
|
"D7": 21,
|
|
"D9": 6
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {
|
|
"relocation": [
|
|
"D4"
|
|
]
|
|
}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "sigmund_freud_1856_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 0.9387,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 93,
|
|
"D12": 20,
|
|
"D24": 254,
|
|
"D3": 39,
|
|
"D30": 408,
|
|
"D4": 199,
|
|
"D5": 28,
|
|
"D7": 50,
|
|
"D9": 16
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 61,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "sigmund_freud_1856_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 61,
|
|
"max_abs": 1.577,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 150,
|
|
"D12": 59,
|
|
"D24": 500,
|
|
"D3": 65,
|
|
"D30": 814,
|
|
"D4": 592,
|
|
"D5": 135,
|
|
"D7": 67,
|
|
"D9": 18
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 121,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 121,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 121,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 121,
|
|
"engine_top1": false,
|
|
"probes": 0,
|
|
"refresh": 0
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "salma_hayek_1966_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.2292,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.3177,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.5121,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 109,
|
|
"D12": 21,
|
|
"D24": 137,
|
|
"D3": 22,
|
|
"D4": 25,
|
|
"D5": 181,
|
|
"D7": 5,
|
|
"D9": 1
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D30",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {
|
|
"family": [
|
|
"D3"
|
|
],
|
|
"relocation": [
|
|
"D4"
|
|
]
|
|
}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 9,
|
|
"engine_top1": false,
|
|
"probes": 7,
|
|
"refresh": 4
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 9,
|
|
"engine_top1": false,
|
|
"probes": 7,
|
|
"refresh": 4
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 9,
|
|
"engine_top1": false,
|
|
"probes": 7,
|
|
"refresh": 4
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 9,
|
|
"engine_top1": false,
|
|
"probes": 7,
|
|
"refresh": 4
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "salma_hayek_1966_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 0.7074,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 152,
|
|
"D12": 41,
|
|
"D24": 282,
|
|
"D3": 57,
|
|
"D4": 76,
|
|
"D5": 469,
|
|
"D7": 23,
|
|
"D9": 13
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 37,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 37,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 37,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 37,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "salma_hayek_1966_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 61,
|
|
"max_abs": 0.9232,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 323,
|
|
"D12": 75,
|
|
"D24": 506,
|
|
"D3": 117,
|
|
"D4": 187,
|
|
"D5": 862,
|
|
"D7": 39,
|
|
"D9": 14
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 95,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 95,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 95,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 95,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "steve_reich_1936_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.1302,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.1302,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.8218,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 13,
|
|
"D24": 158,
|
|
"D4": 31,
|
|
"D5": 342,
|
|
"D9": 17
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 17,
|
|
"engine_top1": false,
|
|
"probes": 4,
|
|
"refresh": 6
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 17,
|
|
"engine_top1": false,
|
|
"probes": 4,
|
|
"refresh": 6
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 17,
|
|
"engine_top1": false,
|
|
"probes": 4,
|
|
"refresh": 6
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 17,
|
|
"engine_top1": false,
|
|
"probes": 4,
|
|
"refresh": 6
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "steve_reich_1936_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 0.8546,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 16,
|
|
"D24": 663,
|
|
"D4": 190,
|
|
"D5": 543,
|
|
"D9": 149
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 35,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 10
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 35,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 10
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 35,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 10
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 35,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 10
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "steve_reich_1936_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 61,
|
|
"max_abs": 1.1912,
|
|
"top_changed": true
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 43,
|
|
"D24": 1067,
|
|
"D4": 1051,
|
|
"D5": 833,
|
|
"D9": 195
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 29,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 29,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 29,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 29,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "albert_brooks_1947_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.0989,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.0989,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.6286,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 207,
|
|
"D12": 37,
|
|
"D24": 64,
|
|
"D3": 140,
|
|
"D5": 29,
|
|
"D7": 323,
|
|
"D9": 70
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": true,
|
|
"probes": 0,
|
|
"refresh": 7
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": true,
|
|
"probes": 0,
|
|
"refresh": 7
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": true,
|
|
"probes": 0,
|
|
"refresh": 7
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": true,
|
|
"probes": 0,
|
|
"refresh": 7
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "albert_brooks_1947_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 0.6286,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 230,
|
|
"D12": 270,
|
|
"D24": 236,
|
|
"D3": 324,
|
|
"D5": 167,
|
|
"D7": 516,
|
|
"D9": 175
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 33,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 33,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 33,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 33,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "albert_brooks_1947_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 60,
|
|
"max_abs": 0.6286,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 494,
|
|
"D12": 671,
|
|
"D24": 546,
|
|
"D3": 816,
|
|
"D5": 396,
|
|
"D7": 640,
|
|
"D9": 208
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 107,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 107,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 107,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 107,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "paul_ryan_1970_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 9,
|
|
"max_abs": 0.099,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 9,
|
|
"max_abs": 0.099,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.689,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 25,
|
|
"D12": 147,
|
|
"D24": 164,
|
|
"D3": 146,
|
|
"D5": 222,
|
|
"D7": 4
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D4",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {
|
|
"education": [
|
|
"D5"
|
|
]
|
|
}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": false,
|
|
"probes": 2,
|
|
"refresh": 2
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": false,
|
|
"probes": 2,
|
|
"refresh": 2
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": false,
|
|
"probes": 2,
|
|
"refresh": 2
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": false,
|
|
"probes": 2,
|
|
"refresh": 2
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "paul_ryan_1970_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 30,
|
|
"max_abs": 0.689,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 40,
|
|
"D12": 345,
|
|
"D24": 294,
|
|
"D3": 319,
|
|
"D5": 564,
|
|
"D7": 131,
|
|
"D9": 2
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 53,
|
|
"engine_top1": false,
|
|
"probes": 6,
|
|
"refresh": 3
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 53,
|
|
"engine_top1": false,
|
|
"probes": 6,
|
|
"refresh": 3
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 53,
|
|
"engine_top1": false,
|
|
"probes": 6,
|
|
"refresh": 3
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 53,
|
|
"engine_top1": false,
|
|
"probes": 6,
|
|
"refresh": 3
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "paul_ryan_1970_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 60,
|
|
"max_abs": 0.7028,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 56,
|
|
"D12": 723,
|
|
"D24": 479,
|
|
"D3": 716,
|
|
"D5": 941,
|
|
"D7": 608,
|
|
"D9": 17
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 53,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 3
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 53,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 3
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 53,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 3
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 53,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 3
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "tom_kennedy_1927_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.2049,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 93,
|
|
"D24": 57,
|
|
"D4": 8,
|
|
"D5": 139,
|
|
"D9": 118
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D4",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {
|
|
"education": [
|
|
"D5"
|
|
],
|
|
"health_pressure": [
|
|
"D30"
|
|
]
|
|
}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 15,
|
|
"engine_top1": true,
|
|
"probes": 7,
|
|
"refresh": 5
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 15,
|
|
"engine_top1": true,
|
|
"probes": 7,
|
|
"refresh": 5
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 15,
|
|
"engine_top1": true,
|
|
"probes": 7,
|
|
"refresh": 5
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 15,
|
|
"engine_top1": true,
|
|
"probes": 7,
|
|
"refresh": 5
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "tom_kennedy_1927_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 1.8763,
|
|
"top_changed": true
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 164,
|
|
"D24": 277,
|
|
"D30": 11,
|
|
"D4": 24,
|
|
"D5": 414,
|
|
"D9": 154
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "tom_kennedy_1927_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 60,
|
|
"max_abs": 2.1821,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 562,
|
|
"D24": 589,
|
|
"D30": 36,
|
|
"D4": 351,
|
|
"D5": 801,
|
|
"D9": 194
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 57,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 57,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 57,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 85,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "andrew_windsor_1960_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 6,
|
|
"max_abs": 0.0625,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 6,
|
|
"max_abs": 0.0625,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.451,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D12": 21,
|
|
"D24": 49,
|
|
"D3": 6,
|
|
"D5": 56,
|
|
"D7": 32
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 5,
|
|
"engine_top1": true,
|
|
"probes": 7,
|
|
"refresh": 4
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 5,
|
|
"engine_top1": true,
|
|
"probes": 7,
|
|
"refresh": 4
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 5,
|
|
"engine_top1": true,
|
|
"probes": 7,
|
|
"refresh": 4
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 5,
|
|
"engine_top1": true,
|
|
"probes": 7,
|
|
"refresh": 4
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "andrew_windsor_1960_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 0.8708,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 16,
|
|
"D12": 56,
|
|
"D24": 334,
|
|
"D3": 25,
|
|
"D5": 112,
|
|
"D7": 64,
|
|
"D9": 25
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 27,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 9
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 27,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 9
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 27,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 9
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 27,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 9
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "andrew_windsor_1960_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 61,
|
|
"max_abs": 1.3271,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 51,
|
|
"D12": 125,
|
|
"D24": 443,
|
|
"D3": 71,
|
|
"D5": 147,
|
|
"D7": 124,
|
|
"D9": 38
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "sean_lennon_1975_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.0352,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.0352,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.357,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 57,
|
|
"D12": 28,
|
|
"D24": 189,
|
|
"D3": 16,
|
|
"D5": 117,
|
|
"D7": 30,
|
|
"D9": 94
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {
|
|
"family": [
|
|
"D3"
|
|
]
|
|
}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 5,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 2
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 5,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 2
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 5,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 2
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 5,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 2
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "sean_lennon_1975_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 0.6766,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 162,
|
|
"D12": 65,
|
|
"D24": 632,
|
|
"D3": 56,
|
|
"D5": 390,
|
|
"D7": 57,
|
|
"D9": 160
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 19,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 19,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 19,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 19,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "sean_lennon_1975_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 61,
|
|
"max_abs": 0.6766,
|
|
"top_changed": true
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 174,
|
|
"D12": 78,
|
|
"D24": 1236,
|
|
"D3": 87,
|
|
"D5": 1159,
|
|
"D7": 74,
|
|
"D9": 162
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 8
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "joseph_kennedy_iii_1980_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.2252,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.2252,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.6214,
|
|
"top_changed": true
|
|
},
|
|
"V0_varga_hits": {
|
|
"D12": 140,
|
|
"D24": 168,
|
|
"D3": 277,
|
|
"D4": 25,
|
|
"D5": 338,
|
|
"D7": 184,
|
|
"D9": 6
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 0
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 0
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 0
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 0
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "joseph_kennedy_iii_1980_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 0.6237,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 3,
|
|
"D12": 525,
|
|
"D24": 546,
|
|
"D3": 812,
|
|
"D4": 78,
|
|
"D5": 857,
|
|
"D7": 427,
|
|
"D9": 20
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "joseph_kennedy_iii_1980_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 61,
|
|
"max_abs": 0.6237,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 13,
|
|
"D12": 790,
|
|
"D24": 1181,
|
|
"D3": 1136,
|
|
"D4": 326,
|
|
"D5": 1240,
|
|
"D7": 749,
|
|
"D9": 22
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 75,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 75,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 75,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 85,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "kurt_cobain_1967_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 1.5666,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D12": 15,
|
|
"D24": 163,
|
|
"D30": 2,
|
|
"D4": 31,
|
|
"D5": 28,
|
|
"D7": 10
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 15,
|
|
"engine_top1": false,
|
|
"probes": 6,
|
|
"refresh": 2
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 15,
|
|
"engine_top1": false,
|
|
"probes": 6,
|
|
"refresh": 2
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 15,
|
|
"engine_top1": false,
|
|
"probes": 6,
|
|
"refresh": 2
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 15,
|
|
"engine_top1": false,
|
|
"probes": 6,
|
|
"refresh": 2
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "kurt_cobain_1967_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 2.0199,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 14,
|
|
"D12": 29,
|
|
"D24": 287,
|
|
"D30": 19,
|
|
"D4": 129,
|
|
"D5": 70,
|
|
"D7": 40,
|
|
"D9": 4
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 39,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 39,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 39,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 41,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "kurt_cobain_1967_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 61,
|
|
"max_abs": 2.1933,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 56,
|
|
"D12": 53,
|
|
"D24": 600,
|
|
"D3": 11,
|
|
"D30": 45,
|
|
"D4": 511,
|
|
"D5": 129,
|
|
"D7": 60,
|
|
"D9": 21
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 121,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 121,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 121,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 115,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "john_robbins_1947_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.043,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.043,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 1.8142,
|
|
"top_changed": true
|
|
},
|
|
"V0_varga_hits": {
|
|
"D24": 141,
|
|
"D30": 13,
|
|
"D5": 213
|
|
},
|
|
"V2_changing": [
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {
|
|
"career": [
|
|
"D10"
|
|
]
|
|
}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": true,
|
|
"probes": 7,
|
|
"refresh": 1
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": true,
|
|
"probes": 7,
|
|
"refresh": 1
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": true,
|
|
"probes": 7,
|
|
"refresh": 1
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": true,
|
|
"probes": 7,
|
|
"refresh": 1
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "john_robbins_1947_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 1.8798,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 125,
|
|
"D24": 576,
|
|
"D30": 26,
|
|
"D5": 624
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "john_robbins_1947_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 61,
|
|
"max_abs": 1.8798,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 317,
|
|
"D24": 1172,
|
|
"D30": 29,
|
|
"D5": 1768,
|
|
"D9": 8
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 121,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 121,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 121,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 121,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 5
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "chad_everett_1937_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 5,
|
|
"max_abs": 0.013,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 5,
|
|
"max_abs": 0.013,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.5586,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D12": 126,
|
|
"D24": 120,
|
|
"D3": 22,
|
|
"D30": 105,
|
|
"D4": 12,
|
|
"D5": 61,
|
|
"D7": 50,
|
|
"D9": 1
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 3
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 3
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 3
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 3
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "chad_everett_1937_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 1.2007,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 210,
|
|
"D12": 182,
|
|
"D24": 314,
|
|
"D3": 78,
|
|
"D30": 352,
|
|
"D4": 47,
|
|
"D5": 211,
|
|
"D7": 402,
|
|
"D9": 11
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 11,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "chad_everett_1937_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 61,
|
|
"max_abs": 1.2007,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 350,
|
|
"D12": 858,
|
|
"D24": 573,
|
|
"D3": 839,
|
|
"D30": 741,
|
|
"D4": 191,
|
|
"D5": 455,
|
|
"D7": 947,
|
|
"D9": 11
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 103,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 12
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 103,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 12
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 103,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 12
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 103,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 12
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "bernd_eichinger_1949_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.0834,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 2,
|
|
"max_abs": 0.0026,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.404,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 154,
|
|
"D12": 132,
|
|
"D24": 156,
|
|
"D3": 132,
|
|
"D5": 147,
|
|
"D7": 134,
|
|
"D9": 80
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {
|
|
"family": [
|
|
"D3"
|
|
],
|
|
"health_pressure": [
|
|
"D30"
|
|
]
|
|
}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": true,
|
|
"probes": 1,
|
|
"refresh": 3
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": true,
|
|
"probes": 1,
|
|
"refresh": 3
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": true,
|
|
"probes": 1,
|
|
"refresh": 3
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 21,
|
|
"engine_top1": true,
|
|
"probes": 1,
|
|
"refresh": 3
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "bernd_eichinger_1949_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 1.2914,
|
|
"top_changed": true
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 189,
|
|
"D12": 436,
|
|
"D24": 312,
|
|
"D3": 432,
|
|
"D30": 2,
|
|
"D5": 410,
|
|
"D7": 347,
|
|
"D9": 120
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": true,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 31,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "bernd_eichinger_1949_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 61,
|
|
"max_abs": 2.3907,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 457,
|
|
"D12": 690,
|
|
"D24": 473,
|
|
"D3": 1015,
|
|
"D30": 35,
|
|
"D5": 554,
|
|
"D7": 621,
|
|
"D9": 281
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 51,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V1": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 51,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V2": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 51,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
},
|
|
"V1n": {
|
|
"top1": true,
|
|
"coverage": true,
|
|
"width": 111,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 4
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "iwao_takamoto_1925_aa_v4_holdout",
|
|
"radius": 10,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 11,
|
|
"changed": 11,
|
|
"max_abs": 0.6546,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 118,
|
|
"D30": 11,
|
|
"D4": 154,
|
|
"D9": 27
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 5,
|
|
"engine_top1": false,
|
|
"probes": 6,
|
|
"refresh": 5
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 5,
|
|
"engine_top1": false,
|
|
"probes": 6,
|
|
"refresh": 5
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 5,
|
|
"engine_top1": false,
|
|
"probes": 6,
|
|
"refresh": 5
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 5,
|
|
"engine_top1": false,
|
|
"probes": 6,
|
|
"refresh": 5
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "iwao_takamoto_1925_aa_v4_holdout",
|
|
"radius": 30,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 31,
|
|
"changed": 31,
|
|
"max_abs": 0.6546,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 559,
|
|
"D30": 18,
|
|
"D4": 345,
|
|
"D9": 110
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 59,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 59,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 59,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 59,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 7
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"case_id": "iwao_takamoto_1925_aa_v4_holdout",
|
|
"radius": 60,
|
|
"proof": {
|
|
"production_vs_V0_policy": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V2_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 0,
|
|
"max_abs": 0.0,
|
|
"top_changed": false
|
|
},
|
|
"V1n_vs_V0": {
|
|
"candidates": 61,
|
|
"changed": 57,
|
|
"max_abs": 3.8397,
|
|
"top_changed": false
|
|
},
|
|
"V0_varga_hits": {
|
|
"D10": 1257,
|
|
"D30": 42,
|
|
"D4": 653,
|
|
"D9": 251
|
|
},
|
|
"V2_changing": [
|
|
"D10",
|
|
"D11",
|
|
"D12",
|
|
"D2",
|
|
"D24",
|
|
"D3",
|
|
"D30",
|
|
"D4",
|
|
"D5",
|
|
"D7",
|
|
"D9"
|
|
],
|
|
"V2_dropped_domain_prefixes": {}
|
|
},
|
|
"measured": {
|
|
"V0": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 17,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 17,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V2": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 17,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
},
|
|
"V1n": {
|
|
"top1": false,
|
|
"coverage": true,
|
|
"width": 17,
|
|
"engine_top1": false,
|
|
"probes": 8,
|
|
"refresh": 6
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"errors": [],
|
|
"command": "python3 scripts/research/varga_sensitivity_rerun.py"
|
|
}
|