Files
Jyotisha/docs/research
ClaudeandClaude Opus 5.5 c032823f9e
Independent Staging Quality Gate / validate-frontend (push) Successful in 5m18s
Independent Staging Quality Gate / validate-python (push) Successful in 6m37s
Independent Staging Quality Gate / publish (push) Successful in 2m27s
research(rectification): reseal round7_integration_2026_11_09 on staging b453505d (BUG-1809)
Product owner approved 2026-11-09 ("agree new result"). Same protocol as
BUG-1720 / BUG-1759: c1a69445^ replay tree + float_split + round5 overlays +
b453505d scripts/references + a small replay overlay (new tag paths, retired
scorer zero-row adapter, RuntimeError guards). Product default strength scope
seed_only_v0, comparability policy common_evidence_coverage_v1.

- sealed 20: top-1 0.35 -> 0.30, top-3 0.45 -> 0.45, mean error 6.80 -> 6.75
- offset 900: top-1 0.0156 -> 0.0100, coverage 0.900 -> 0.883 (164/900 vs
  round5 tag; 57/900 over 4 cases vs pre-integration staging)
- live v5 231: best = truth 8 -> 8; 124 changes vs round5 tag, 115 vs
  pre-integration staging
- leaders: sealed 40/40 comparable; offset 863 comparable / 35 provisional /
  2 no single leader; live 226 / 5

Trial-for-trial identical to the integration agent's seed_only runs.
Sensitivity only, not accuracy (event scoring near chance, BUG-1644).
Older tags unchanged.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01DbBXoyn7Hj3LCW3BUs5bZ8
2026-11-09 07:28:04 +08:00
..

Research Workspace

This directory stores research notes, audits, benchmark packets, and active adjudicator iteration records for the Jyotish project.

Layout

  • active/
    • reserved for current working research fronts that directly support the next implementation cycle
  • archive/
    • historical round notes, sidecar work orders, and local draft research that should not clutter normal implementation work
  • top-level docs/research/*.md
    • current canonical research notes that are still referenced by active engineering work

What Stays Top-Level

Keep a research file at the top level only if at least one of the following is true:

  • it is referenced by an active implementation spec
  • it is referenced by tests, workflow docs, or benchmark dashboards
  • it captures a currently active adjudicator audit or closure board

What Moves To Archive

Move a research file into archive/ when:

  • it is a completed round log or sidecar work order
  • it is a local exploration draft with no active code dependency
  • it is superseded by a newer audit, dashboard, or implementation note

Current Working Rule

When adding new research notes:

  1. put active, decision-driving notes at the top level
  2. move noisy round-by-round drafts into archive/
  3. avoid storing transient terminal captures or scratch outputs here