docs: preregistration commit hash after history rewrite
4 changed files +4 −4
modified
docs/DELIVERY_REPORT.md
+1 −1
@@ -12,7 +12,7 @@ Executor: Claude Code 2.1.317 (claude-fable-5-1) operating autonomously on the a | ||
| 12 | 12 | | 4 Profiles | 8 YAML profiles (train split 221 docs) with medians/IQR/bootstrap CIs, move prevalence, contribution placement; 4 figures | `profiles/`, `figures/` | |
| 13 | 13 | | 5 Retrieval + engine | 9 642-unit hybrid index (BM25 + MiniLM, provenance); engine modes outline/write/upgrade, conditions A–E, deterministic audits, referee pass, proposal+report+diff contract; 5 review roles; evidence lookup | `src/jof250/{embeddings,retrieval,generation,auditing}.py` | |
| 14 | 14 | | 6 Claude Code | 10 slash commands, 7 agents, 1 skill (project + user scope); registration verified in a live session (skill + commands listed; `jof-*` agent types available); `/jof-audit` executed headlessly from a separate sample project | `.claude/`, `experiments/outputs/demo/separate_project_test.md` | |
| 15 | −| 7 Experiment | Preregistration frozen (commit 87c73cd) before runs; run 1 discarded after two defects (A-004, archived); **run 2**: 199/199 runs, 33 blind judge sets; preregistered analysis with cluster bootstrap + Holm | `experiments/preregistration.md`, `experiments/analysis/results_heldout_v1.json` | | |
| 15 | +| 7 Experiment | Preregistration frozen (commit 7ef3b9a) before runs; run 1 discarded after two defects (A-004, archived); **run 2**: 199/199 runs, 33 blind judge sets; preregistered analysis with cluster bootstrap + Holm | `experiments/preregistration.md`, `experiments/analysis/results_heldout_v1.json` | | |
| 16 | 16 | | 8 Paper | LaTeX WP45 (UQO template), 11 sections + appendices A–H, 64 verified references, all numbers from `numbers.tex` macros; compiled PDF | `paper/main.pdf` | |
| 17 | 17 | | 9 Tests | 29 pytest tests (inventory, hashes, duplicates, parsing, schema, segmentation cap, auditing, overlap, CLI, Claude Code files, provenance, budget cap, retrieval, Markdown loader regression) — all pass | `make test` | |
| 18 | 18 | |
modified
docs/PROGRESS.md
+1 −1
@@ -50,7 +50,7 @@ Verified milestones only. Times are America/Toronto unless marked UTC. Code vers | ||
| 50 | 50 | - Project scope: 10 commands, 7 agents, 1 skill (`.claude/`). User scope installed on explicit request (A-003); registration verified: the `jof250` skill and `/jof-*` commands appear in the running Claude Code session. |
| 51 | 51 | - Separate-project test: `/jof-audit` run headlessly in `/tmp/sample-paper` → `experiments/outputs/demo/separate_project_test.md`. |
| 52 | 52 | |
| 53 | −## Phase 7 — Preregistration frozen (commit 87c73cd) and benchmark launched (2026-11-03 18:40) | |
| 53 | +## Phase 7 — Preregistration frozen (commit 7ef3b9a) and benchmark launched (2026-11-03 18:40) | |
| 54 | 54 | - `experiments/preregistration.md`; fixtures from held-out docs jof_12439 (corporate/intermediation) and jof_12777 (credit spreads / asset pricing) + WP29 (out-of-domain); plan: 199 runs (A–E ×27, 4 ablations ×16), 27 judge sets (+25% second pass); estimated 46 USD. |
| 55 | 55 | |
| 56 | 56 | ## Phase 7 — Benchmark heldout_v1 run (2026-11-03 18:40 → 19:54 ET) ✅ |
modified
experiments/fixtures/heldout_v1/manifest.json
+1 −1
@@ -2,7 +2,7 @@ | ||
| 2 | 2 | "protocol": "heldout_v1", |
| 3 | 3 | "built": { |
| 4 | 4 | "timestamp": "2026-11-03T23:27:49+00:00", |
| 5 | − "code_version": "87c73cd-dirty", | |
| 5 | + "code_version": "7ef3b9a-dirty", | |
| 6 | 6 | "host": { |
| 7 | 7 | "platform": "macOS-27.0-arm64-arm-64bit", |
| 8 | 8 | "python": "3.12.13", |
modified
experiments/outputs/demo/wp29_referee.md
+1 −1
@@ -91,7 +91,7 @@ Resolution: | ||
| 91 | 91 | |
| 92 | 92 | # Manuscript audit — Protocol-Guided Autonomous Research with Claude Code |
| 93 | 93 | |
| 94 | −Generated 2026-11-03T23:13:09+00:00 (jof250 87c73cd-dirty). Body words: 15946. | |
| 94 | +Generated 2026-11-03T23:13:09+00:00 (jof250 7ef3b9a-dirty). Body words: 15946. | |
| 95 | 95 | |
| 96 | 96 | ## Sections |
| 97 | 97 | |
| 98 | 98 | |