Files
Jyotisha/docs/research/answer_flip_tolerance_2026_09_26.json
T
Jesse_ChenandClaude Opus 5.5 0f5442cea2 research(rectification): offline R1/R2/R3 — answer-flip tolerance, V1/V2 rerun, dasha shift arithmetic
- 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
2026-09-26 14:47:48 +08:00

1578 lines
33 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,
"ask_count": 6,
"flip_seed": 20260926,
"repeats": 30,
"gate": "G0 production (45 / refresh 30)",
"delivery": "lead-8 union of non-eliminated clusters",
"sampled": {
"10": {
"0": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.8,
"width_median": 15.0
},
"cases": 20,
"runs": 20,
"truth_in_range": 1.0,
"head_hit": 0.8,
"width_median": 15.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 0
},
"1": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.9375,
"width_median": 12.0
},
"cases": 16,
"runs": 480,
"truth_in_range": 1.0,
"head_hit": 0.5771,
"width_median": 13.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 0
},
"2": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.9333,
"width_median": 11
},
"cases": 15,
"runs": 450,
"truth_in_range": 0.9956,
"head_hit": 0.3956,
"width_median": 11.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 1
}
},
"30": {
"0": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.55,
"width_median": 33.0
},
"cases": 20,
"runs": 20,
"truth_in_range": 1.0,
"head_hit": 0.55,
"width_median": 33.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 0
},
"1": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.6111,
"width_median": 32.0
},
"cases": 18,
"runs": 540,
"truth_in_range": 0.9889,
"head_hit": 0.3315,
"width_median": 35.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 1
},
"2": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.6111,
"width_median": 32.0
},
"cases": 18,
"runs": 540,
"truth_in_range": 0.9259,
"head_hit": 0.0778,
"width_median": 33.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 9
}
},
"60": {
"0": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.4,
"width_median": 56.0
},
"cases": 20,
"runs": 20,
"truth_in_range": 1.0,
"head_hit": 0.4,
"width_median": 56.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 0
},
"1": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.4444,
"width_median": 54.0
},
"cases": 18,
"runs": 540,
"truth_in_range": 0.9815,
"head_hit": 0.2444,
"width_median": 73.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 2
},
"2": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.4444,
"width_median": 54.0
},
"cases": 18,
"runs": 540,
"truth_in_range": 0.8981,
"head_hit": 0.063,
"width_median": 71.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 12
}
}
},
"exhaustive": {
"10": {
"0": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.8,
"width_median": 15.0
},
"cases": 20,
"runs": 20,
"truth_in_range": 1.0,
"head_hit": 0.8,
"width_median": 15.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 0
},
"1": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.9375,
"width_median": 12.0
},
"cases": 16,
"runs": 85,
"truth_in_range": 1.0,
"head_hit": 0.6588,
"width_median": 13,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 0
},
"2": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.9333,
"width_median": 11
},
"cases": 15,
"runs": 202,
"truth_in_range": 0.9901,
"head_hit": 0.4257,
"width_median": 11.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 2
}
},
"30": {
"0": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.55,
"width_median": 33.0
},
"cases": 20,
"runs": 20,
"truth_in_range": 1.0,
"head_hit": 0.55,
"width_median": 33.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 0
},
"1": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.6111,
"width_median": 32.0
},
"cases": 18,
"runs": 108,
"truth_in_range": 0.9907,
"head_hit": 0.3333,
"width_median": 35.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 1
},
"2": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.6111,
"width_median": 32.0
},
"cases": 18,
"runs": 270,
"truth_in_range": 0.9185,
"head_hit": 0.0926,
"width_median": 33.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 9
}
},
"60": {
"0": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.4,
"width_median": 56.0
},
"cases": 20,
"runs": 20,
"truth_in_range": 1.0,
"head_hit": 0.4,
"width_median": 56.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 0
},
"1": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.4444,
"width_median": 54.0
},
"cases": 18,
"runs": 108,
"truth_in_range": 0.9815,
"head_hit": 0.2315,
"width_median": 73.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 2
},
"2": {
"baseline_same_cases": {
"truth_in_range": 1.0,
"head_hit": 0.4444,
"width_median": 54.0
},
"cases": 18,
"runs": 270,
"truth_in_range": 0.9074,
"head_hit": 0.0556,
"width_median": 73.0,
"tie": 0.0,
"truth_eliminated": 0.0,
"cases_ever_squeezed": 12
}
}
},
"answerable_per_case": {
"10": [
6,
6,
0,
6,
6,
0,
0,
6,
4,
0,
2,
6,
6,
6,
6,
6,
6,
6,
1,
6
],
"30": [
6,
6,
6,
6,
6,
0,
0,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6
],
"60": [
6,
6,
6,
6,
6,
0,
0,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6,
6
]
},
"per_case": [
{
"case_id": "barack_obama_1961_aa_v4_holdout",
"radius": 10,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 15
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.5,
"width_median": 13.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.1333,
"width_median": 13
}
},
{
"case_id": "barack_obama_1961_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 39
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 33.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 39
}
},
{
"case_id": "barack_obama_1961_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 25
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 39.0
},
"k2": {
"truth_in_range": 0.9333,
"head_hit": 0.0,
"width_median": 45
}
},
{
"case_id": "angelina_jolie_1975_aa_v4_holdout",
"radius": 10,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 19
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.3333,
"width_median": 20.0
},
"k2": {
"truth_in_range": 0.9333,
"head_hit": 0.0,
"width_median": 13
}
},
{
"case_id": "angelina_jolie_1975_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 61
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.1667,
"width_median": 45.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 51
}
},
{
"case_id": "angelina_jolie_1975_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 53
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 56.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 67
}
},
{
"case_id": "tiger_woods_1975_aa_v4_holdout",
"radius": 10,
"answerable": 0,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 21
},
"k1": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
},
"k2": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
}
},
{
"case_id": "tiger_woods_1975_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 27
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.5,
"width_median": 34.0
},
"k2": {
"truth_in_range": 0.8,
"head_hit": 0.0,
"width_median": 35
}
},
{
"case_id": "tiger_woods_1975_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 61
},
"k1": {
"truth_in_range": 0.8333,
"head_hit": 0.0,
"width_median": 55.0
},
"k2": {
"truth_in_range": 0.6667,
"head_hit": 0.0,
"width_median": 51
}
},
{
"case_id": "elizabeth_taylor_1932_aa_v4_holdout",
"radius": 10,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 13
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.8333,
"width_median": 13.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.6667,
"width_median": 13
}
},
{
"case_id": "elizabeth_taylor_1932_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 7
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.8333,
"width_median": 35.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.2667,
"width_median": 33
}
},
{
"case_id": "elizabeth_taylor_1932_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 33
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.5,
"width_median": 62.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.1333,
"width_median": 63
}
},
{
"case_id": "elizabeth_montgomery_1933_aa_v4_holdout",
"radius": 10,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 7
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 14.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.6,
"width_median": 7
}
},
{
"case_id": "elizabeth_montgomery_1933_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 33
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.3333,
"width_median": 37.0
},
"k2": {
"truth_in_range": 0.9333,
"head_hit": 0.0667,
"width_median": 31
}
},
{
"case_id": "elizabeth_montgomery_1933_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 55
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 73.0
},
"k2": {
"truth_in_range": 0.8667,
"head_hit": 0.0,
"width_median": 105
}
},
{
"case_id": "pablo_picasso_1881_aa_v4_holdout",
"radius": 10,
"answerable": 0,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 21
},
"k1": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
},
"k2": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
}
},
{
"case_id": "pablo_picasso_1881_aa_v4_holdout",
"radius": 30,
"answerable": 0,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 61
},
"k1": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
},
"k2": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
}
},
{
"case_id": "pablo_picasso_1881_aa_v4_holdout",
"radius": 60,
"answerable": 0,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 1439
},
"k1": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
},
"k2": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
}
},
{
"case_id": "sigmund_freud_1856_aa_v4_holdout",
"radius": 10,
"answerable": 0,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 21
},
"k1": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
},
"k2": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
}
},
{
"case_id": "sigmund_freud_1856_aa_v4_holdout",
"radius": 30,
"answerable": 0,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 61
},
"k1": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
},
"k2": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
}
},
{
"case_id": "sigmund_freud_1856_aa_v4_holdout",
"radius": 60,
"answerable": 0,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 121
},
"k1": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
},
"k2": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
}
},
{
"case_id": "salma_hayek_1966_aa_v4_holdout",
"radius": 10,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 9
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.6667,
"width_median": 11.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.4,
"width_median": 11
}
},
{
"case_id": "salma_hayek_1966_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 37
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 38.0
},
"k2": {
"truth_in_range": 0.8667,
"head_hit": 0.0,
"width_median": 37
}
},
{
"case_id": "salma_hayek_1966_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 95
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.1667,
"width_median": 71.0
},
"k2": {
"truth_in_range": 0.7333,
"head_hit": 0.0,
"width_median": 73
}
},
{
"case_id": "steve_reich_1936_aa_v4_holdout",
"radius": 10,
"answerable": 4,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 17
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.25,
"width_median": 19.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 20.0
}
},
{
"case_id": "steve_reich_1936_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 35
},
"k1": {
"truth_in_range": 0.8333,
"head_hit": 0.0,
"width_median": 37.0
},
"k2": {
"truth_in_range": 0.6667,
"head_hit": 0.0,
"width_median": 17
}
},
{
"case_id": "steve_reich_1936_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 29
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 39.0
},
"k2": {
"truth_in_range": 0.8,
"head_hit": 0.0,
"width_median": 61
}
},
{
"case_id": "albert_brooks_1947_aa_v4_holdout",
"radius": 10,
"answerable": 0,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 21
},
"k1": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
},
"k2": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
}
},
{
"case_id": "albert_brooks_1947_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 33
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.5,
"width_median": 33.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.2,
"width_median": 31
}
},
{
"case_id": "albert_brooks_1947_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 107
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.6667,
"width_median": 107.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.3333,
"width_median": 77
}
},
{
"case_id": "paul_ryan_1970_aa_v4_holdout",
"radius": 10,
"answerable": 2,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 21
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 16.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 21
}
},
{
"case_id": "paul_ryan_1970_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 53
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.1667,
"width_median": 51.0
},
"k2": {
"truth_in_range": 0.8,
"head_hit": 0.0,
"width_median": 45
}
},
{
"case_id": "paul_ryan_1970_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 53
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 57.0
},
"k2": {
"truth_in_range": 0.9333,
"head_hit": 0.0,
"width_median": 91
}
},
{
"case_id": "tom_kennedy_1927_aa_v4_holdout",
"radius": 10,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 15
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.8333,
"width_median": 15.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.6,
"width_median": 7
}
},
{
"case_id": "tom_kennedy_1927_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 11
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.8333,
"width_median": 32.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.2667,
"width_median": 31
}
},
{
"case_id": "tom_kennedy_1927_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 57
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.3333,
"width_median": 73.0
},
"k2": {
"truth_in_range": 0.9333,
"head_hit": 0.0,
"width_median": 73
}
},
{
"case_id": "andrew_windsor_1960_aa_v4_holdout",
"radius": 10,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 5
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 13.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.6,
"width_median": 11
}
},
{
"case_id": "andrew_windsor_1960_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 27
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.6667,
"width_median": 35.0
},
"k2": {
"truth_in_range": 0.9333,
"head_hit": 0.0667,
"width_median": 35
}
},
{
"case_id": "andrew_windsor_1960_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 11
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 82.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.3333,
"width_median": 83
}
},
{
"case_id": "sean_lennon_1975_aa_v4_holdout",
"radius": 10,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 5
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.8333,
"width_median": 9.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.4667,
"width_median": 5
}
},
{
"case_id": "sean_lennon_1975_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 19
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.5,
"width_median": 40.0
},
"k2": {
"truth_in_range": 0.9333,
"head_hit": 0.0667,
"width_median": 31
}
},
{
"case_id": "sean_lennon_1975_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 31
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.6667,
"width_median": 81.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.2,
"width_median": 75
}
},
{
"case_id": "joseph_kennedy_iii_1980_aa_v4_holdout",
"radius": 10,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 11
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 11.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 11
}
},
{
"case_id": "joseph_kennedy_iii_1980_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 31
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.6667,
"width_median": 31.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.4,
"width_median": 31
}
},
{
"case_id": "joseph_kennedy_iii_1980_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 75
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.3333,
"width_median": 102.0
},
"k2": {
"truth_in_range": 0.9333,
"head_hit": 0.0,
"width_median": 93
}
},
{
"case_id": "kurt_cobain_1967_aa_v4_holdout",
"radius": 10,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 15
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.5,
"width_median": 16.0
},
"k2": {
"truth_in_range": 0.9333,
"head_hit": 0.1333,
"width_median": 11
}
},
{
"case_id": "kurt_cobain_1967_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 39
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 44.0
},
"k2": {
"truth_in_range": 0.8,
"head_hit": 0.0,
"width_median": 31
}
},
{
"case_id": "kurt_cobain_1967_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 121
},
"k1": {
"truth_in_range": 0.8333,
"head_hit": 0.0,
"width_median": 115.0
},
"k2": {
"truth_in_range": 0.8667,
"head_hit": 0.0,
"width_median": 85
}
},
{
"case_id": "john_robbins_1947_aa_v4_holdout",
"radius": 10,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 11
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.8333,
"width_median": 11.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.6667,
"width_median": 5
}
},
{
"case_id": "john_robbins_1947_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 31
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 31.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 15
}
},
{
"case_id": "john_robbins_1947_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 121
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 121.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 109
}
},
{
"case_id": "chad_everett_1937_aa_v4_holdout",
"radius": 10,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 11
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.8333,
"width_median": 11.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.4667,
"width_median": 11
}
},
{
"case_id": "chad_everett_1937_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 11
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 27.0
},
"k2": {
"truth_in_range": 0.8,
"head_hit": 0.0,
"width_median": 41
}
},
{
"case_id": "chad_everett_1937_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 103
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 108.0
},
"k2": {
"truth_in_range": 0.8667,
"head_hit": 0.0,
"width_median": 67
}
},
{
"case_id": "bernd_eichinger_1949_aa_v4_holdout",
"radius": 10,
"answerable": 1,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 21
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 21
},
"k2": {
"truth_in_range": null,
"head_hit": null,
"width_median": null
}
},
{
"case_id": "bernd_eichinger_1949_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 31
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.8333,
"width_median": 48.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.3333,
"width_median": 35
}
},
{
"case_id": "bernd_eichinger_1949_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 1.0,
"width_median": 51
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.5,
"width_median": 77.0
},
"k2": {
"truth_in_range": 0.9333,
"head_hit": 0.0,
"width_median": 77
}
},
{
"case_id": "iwao_takamoto_1925_aa_v4_holdout",
"radius": 10,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 5
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 11.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 15
}
},
{
"case_id": "iwao_takamoto_1925_aa_v4_holdout",
"radius": 30,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 59
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 54.0
},
"k2": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 47
}
},
{
"case_id": "iwao_takamoto_1925_aa_v4_holdout",
"radius": 60,
"answerable": 6,
"k0": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 17
},
"k1": {
"truth_in_range": 1.0,
"head_hit": 0.0,
"width_median": 85.0
},
"k2": {
"truth_in_range": 0.8667,
"head_hit": 0.0,
"width_median": 79
}
}
],
"errors": [],
"command": "python3 scripts/research/answer_flip_tolerance.py"
}