Jesse_ChenandClaude Opus 5.5 bcf0c86feb research(rectification): typed events scored as answered probes — no benefit (BUG-1089) ...

v4 open holdout, ±10/±30/±60, raw and percent priors: only 4/9/14 of 57
day-precision training events split candidates; widths unchanged, top-1
drops. Narrowed year blocking (R3) mixed. All arms no_benefit; no
implementation brief recommended. Two runs byte-identical.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017eEAG8HD3mm8gsKXgk8uU8

2026-09-29 10:06:13 +08:00

..

jev_intent_samples

research: compare Jev intent state with the previous turn

2026-09-27 11:41:53 +08:00

answer_flip_tolerance.py

research(rectification): offline R1/R2/R3 — answer-flip tolerance, V1/V2 rerun, dasha shift arithmetic

2026-09-26 14:47:48 +08:00

capture_consult_evidence_card_golden.py

fix(engine): D9 double-transit targets check the D9 signs they name (BUG-1060)

2026-09-27 17:30:05 +08:00

cluster_width_lib.py

docs(research): measure why delivered range width equals the search window

2026-09-14 22:11:47 +08:00

cluster_width_probe.py

docs(research): measure why delivered range width equals the search window

2026-09-14 22:11:47 +08:00

consult_evidence_card_lib.py

research: consultation evidence-card inventory and draft

2026-09-27 01:27:57 +08:00

consult_evidence_card_run.py

feat(engine): expose native technique layers in the consultation output

2026-09-27 16:27:24 +08:00

consult_evidence_card_time.py

research: consultation evidence-card inventory and draft

2026-09-27 01:27:57 +08:00

dasha_shift_per_minute.py

research(rectification): offline R1/R2/R3 — answer-flip tolerance, V1/V2 rerun, dasha shift arithmetic

2026-09-26 14:47:48 +08:00

fewer_probes_card_replay.py

feat(rectification): 少问几道就出卡，交付卡以范围为主（D1–D4）

2026-09-26 14:27:12 +08:00

guided_collect_holdout_replay.py

fix(rectification): 有题就接着问，题问完才出卡；引导窗口不再硬贴领域

2026-09-16 12:16:55 +00:00

holdout_v4_build.py

docs(research): measure minute-resolution scoring; no variant clears all radii

2026-09-14 20:43:27 +08:00

house_lord_gochara_supply.py

docs(research): measure house-lord gochara rules with no benefit

2026-09-14 01:07:11 +08:00

jev_intent_corpus_build.py

research(jev-intent): 修复轮重造语料并全量对照

2026-09-19 11:30:31 +08:00

jev_intent_current.py

research: compare Jev intent state with the previous turn

2026-09-27 11:41:53 +08:00

jev_intent_probe_v2.py

research: compare Jev intent state with the previous turn

2026-09-27 11:41:53 +08:00

jev_intent_probe.py

research: compare Jev intent state with the previous turn

2026-09-27 11:41:53 +08:00

jev_intent_questions.py

research: compare Jev intent state with the previous turn

2026-09-27 11:41:53 +08:00

jev_intent_source_b_v2.py

research: compare Jev intent state with the previous turn

2026-09-27 11:41:53 +08:00

measure_consult_evidence_card.ts

feat(consult): evidence card v2 per the astrologer's review

2026-09-27 16:44:19 +08:00

midnight_date_anchor_regression.py

fix(rectification): anchor candidate windows to civil dates across midnight

2026-09-21 02:55:00 +08:00

minute_resolution_lib.py

docs(research): measure minute-resolution scoring; no variant clears all radii

2026-09-14 20:43:27 +08:00

minute_resolution_sweep.py

docs(research): measure minute-resolution scoring; no variant clears all radii

2026-09-14 20:43:27 +08:00

offline_research_20260926_lib.py

research(rectification): offline R1/R2/R3 — answer-flip tolerance, V1/V2 rerun, dasha shift arithmetic

2026-09-26 14:47:48 +08:00

precision_gate_lib.py

docs(research): measure precision-adaptive probe gates; no variant clears the bar

2026-09-15 09:04:03 +08:00

precision_gate_sweep.py

docs(research): measure precision-adaptive probe gates; no variant clears the bar

2026-09-15 09:04:03 +08:00

probe_supply_after_six.py

docs(research): measure dated probe supply after six answers

2026-09-13 12:59:46 +08:00

project_consult_model_context.ts

research: consultation evidence-card inventory and draft

2026-09-27 01:27:57 +08:00

quality_wording_ab.py

fix(rectification): name education quality events by kind, no month for year precision (BUG-1088)

2026-09-29 10:06:13 +08:00

reported_offset_sweep.py

fix(rectification): name education quality events by kind, no month for year precision (BUG-1088)

2026-09-29 10:06:13 +08:00

representative_pairs_probe.py

research(rectification): offline R1/R2/R3 — answer-flip tolerance, V1/V2 rerun, dasha shift arithmetic

2026-09-26 14:47:48 +08:00

sealed_holdout_rerun.py

fix(rectification): name education quality events by kind, no month for year precision (BUG-1088)

2026-09-29 10:06:13 +08:00

typed_event_as_probe.py

research(rectification): typed events scored as answered probes — no benefit (BUG-1089)

2026-09-29 10:06:13 +08:00

varga_sensitivity_rerun.py

research(rectification): offline R1/R2/R3 — answer-flip tolerance, V1/V2 rerun, dasha shift arithmetic

2026-09-26 14:47:48 +08:00