From b891b0bbf4f1fe5e32b343bb6d7a2bd487b34b27 Mon Sep 17 00:00:00 2001 From: u52f85420 Date: Sun, 1 Nov 2026 10:15:35 +0000 Subject: [PATCH] docs: move research dossier into docs/ and update cross-references --- MANIFEST.sha256 | 16 ++++++++-------- README.md | 8 ++++---- experiment_plan.md => docs/experiment_plan.md | 0 .../literature_review.md | 0 .../manuscript_outline.md | 0 .../mathematical_analysis.md | 0 novelty_matrix.md => docs/novelty_matrix.md | 2 +- .../research_decision.md | 0 research_log.md => docs/research_log.md | 2 +- 9 files changed, 14 insertions(+), 14 deletions(-) rename experiment_plan.md => docs/experiment_plan.md (100%) rename literature_review.md => docs/literature_review.md (100%) rename manuscript_outline.md => docs/manuscript_outline.md (100%) rename mathematical_analysis.md => docs/mathematical_analysis.md (100%) rename novelty_matrix.md => docs/novelty_matrix.md (95%) rename research_decision.md => docs/research_decision.md (100%) rename research_log.md => docs/research_log.md (97%) diff --git a/MANIFEST.sha256 b/MANIFEST.sha256 index 7e64fa1..2f43956 100644 --- a/MANIFEST.sha256 +++ b/MANIFEST.sha256 @@ -1,23 +1,23 @@ 7d1e0ddfdb4426ffb927d1dd39ad1cbeda1f01d6de737eb72432676d022f4f08 .gitignore -c285194eb7af8b7e344e536aba5db06d802ab0e33370dc11ee3b5117a25f6335 README.md +eeafe296521594d62361a6fb168d23cee7bf0ad357fb5ec231d0b0264d888b97 README.md c3ae05270d76ec205da3bb7bece26663a612f2e608836af25eee96c66270eeaf configs/ablations.csv 8346e5ca6fae19e5dfb441e5a35fb3da3a99a034f03c465dc5f0714ef9a0cce2 data/README.md +19ec2160d5dc910147671c3ce678cd89fa60d8382b16cb1c5cb830fbc58ddc0b docs/experiment_plan.md +51897c6ba5a98e2790eec4b9d440aa64644064c42501bd14d01efbc32e3fc550 docs/literature_review.md +f071ca15394dea34339784af23cece8acdc4320a2773d5b9969632bf997c93b7 docs/manuscript_outline.md +6cece4721ad443ddb35e2c9ab24ff2cd3a5607e3bc06101e299c0aef3cc15f5b docs/mathematical_analysis.md +a0eb226ec5aedc768f3e827a112d4a09b9491af0c9a73ed431e9257414f1709e docs/novelty_matrix.md +c5c803a06c5f0e8b9e220cf5e4dd79e018d881c006420ab6d03806d5b8c9901e docs/research_decision.md +fdef315212cacc1b77cc940ff3fadd137c3648d84bb76795472eeb7f4218d587 docs/research_log.md 7641c6789c27309cf8ef00eacd417e01bf7a1683a5c7bdbaeb6b290896088aa2 evidence/papers.json bf1ce5f0924d4c5e93455cc4a5bb7c39b6730aa629cf339182f960011f58a80d evidence/upstream_audit.md -19ec2160d5dc910147671c3ce678cd89fa60d8382b16cb1c5cb830fbc58ddc0b experiment_plan.md d909687f70245e3fc3c9811271359f9ab827057ae3a7a6245f6d26ead7ef4d56 irstd/__init__.py 4775281f0e897fa22dd6b1697f8d6673e63aa6e3746ff5e058ae93d2860ca140 irstd/core.py 6c6fd77673d18f97271e9b2d6b3548ba1c477ba67ddbc53d80d507e7ae4e0879 irstd/data.py ea405b291820d076b09285d3940eb20bc3348ca64eeff5b89dfa76f81cb5f1a8 irstd/models.py -51897c6ba5a98e2790eec4b9d440aa64644064c42501bd14d01efbc32e3fc550 literature_review.md -f071ca15394dea34339784af23cece8acdc4320a2773d5b9969632bf997c93b7 manuscript_outline.md -6cece4721ad443ddb35e2c9ab24ff2cd3a5607e3bc06101e299c0aef3cc15f5b mathematical_analysis.md -e2441716df54e3725f208e6514e7dd06a7a70d617003cb1eefec4a3660fea3c9 novelty_matrix.md 48c8ebe01079642883c2b64ff1bc05771192b419ea3caec73db91aede4776322 pyproject.toml f793676a40e71a12c2d9066d4f2e342bf5d920a971a725519c00ed500c4231ed requirements-core.txt aea3df914eb73b204f3461b373e0b33cab0e2d58d31200b7f40c29a6614e1e02 requirements-training.txt -c5c803a06c5f0e8b9e220cf5e4dd79e018d881c006420ab6d03806d5b8c9901e research_decision.md -4d3c59eab8eda8d0c4836b66a01693ad0a456e157afb3f33fdb2faa7734dd2da research_log.md 3522b07838f6b3327e5f2253f251113139fd2608cb741554a98361a386f7ea9a results/README.md 9728844a980ca8598b75c3f347a08d51a1c8996ba855876f6b53a879e57cbf2a results/environment.json 7d6f7bd3315bb0498c2801551bd64272deea801a49c88444431de13c713b4837 results/math_checks.json diff --git a/README.md b/README.md index d96d02d..7f44434 100644 --- a/README.md +++ b/README.md @@ -2,7 +2,7 @@ **Status: research dossier and partially executed prototype, 2026-10-31.** Revised Project B is the provisional priority. None of A/B/C has been established as a novel publishable result. No real dataset has been trained on or evaluated in this environment. -Read in order: `research_decision.md`, `novelty_matrix.md`, `mathematical_analysis.md`, `literature_review.md`, `experiment_plan.md`. Full bibliographic verification, dataset rights/downloads and several upstream implementations remain open, individually marked in the review. There are 10 A, 15 B and 12 C relevant reference placements with overlap, plus a pending NP-loss reference. General loss/calibration papers are explicitly distinguished from IRSTD papers. +Read in order: `docs/research_decision.md`, `docs/novelty_matrix.md`, `docs/mathematical_analysis.md`, `docs/literature_review.md`, `docs/experiment_plan.md`. Full bibliographic verification, dataset rights/downloads and several upstream implementations remain open, individually marked in the review. There are 10 A, 15 B and 12 C relevant reference placements with overlap, plus a pending NP-loss reference. General loss/calibration papers are explicitly distinguished from IRSTD papers. ## Contents @@ -13,7 +13,7 @@ Read in order: `research_decision.md`, `novelty_matrix.md`, `mathematical_analys - `configs/ablations.csv`: prepared versus unimplemented comparisons. - `evidence/papers.json`: bibliographic/status records; no copied paper text. - `results/`: actual test logs and analytic calculations only. -- `manuscript_outline.md`, `research_log.md`: writing and milestone records. +- `docs/manuscript_outline.md`, `docs/research_log.md`: writing and milestone records. ## Actual execution status @@ -37,7 +37,7 @@ For CPU-only evaluation, omit PyTorch; `evaluate.py` imports it only when a lear ## Data preparation -No data, checkpoints or third-party code are bundled. Follow `data/README.md` and `experiment_plan.md`. Create `data/manifest.csv` with native uint8 image/mask paths, exact split membership and independent scene groups. Original test sets stay untouched; dev and cal come from training groups or separately authorized data. Binary masks cannot resolve overlapping target identities. License and annotation audits are required before claiming a valid benchmark. +No data, checkpoints or third-party code are bundled. Follow `data/README.md` and `docs/experiment_plan.md`. Create `data/manifest.csv` with native uint8 image/mask paths, exact split membership and independent scene groups. Original test sets stay untouched; dev and cal come from training groups or separately authorized data. Binary masks cannot resolve overlapping target identities. License and annotation audits are required before claiming a valid benchmark. ```bash python scripts/audit_data.py --manifest data/manifest.csv --out data/audit.json @@ -84,4 +84,4 @@ The benchmark uses random images solely for timing. It excludes disk IO and lear Add `--calibration-method fixed_sequence` to the calibration command to test the predeclared thresholds from highest to lowest and stop at the first failure. The default remains `bonferroni` for reference. Count risk uses the Hoeffding KL bound on FP/cap; any-alarm risk uses an exact binomial lower-tail test. The output reports a certified risk budget, not a simultaneous table of confidence bounds. Choose the procedure before calibration; selecting whichever procedure works on the same labels requires its own error allocation. -At alpha=.01 and delta=.05, zero observed errors need 299 independent images for the fixed-sequence any-alarm test, or 19,172 for count risk with cap=64. These are procedure-specific calculations, not universal lower bounds. See mathematical_analysis.md. +At alpha=.01 and delta=.05, zero observed errors need 299 independent images for the fixed-sequence any-alarm test, or 19,172 for count risk with cap=64. These are procedure-specific calculations, not universal lower bounds. See docs/mathematical_analysis.md. diff --git a/experiment_plan.md b/docs/experiment_plan.md similarity index 100% rename from experiment_plan.md rename to docs/experiment_plan.md diff --git a/literature_review.md b/docs/literature_review.md similarity index 100% rename from literature_review.md rename to docs/literature_review.md diff --git a/manuscript_outline.md b/docs/manuscript_outline.md similarity index 100% rename from manuscript_outline.md rename to docs/manuscript_outline.md diff --git a/mathematical_analysis.md b/docs/mathematical_analysis.md similarity index 100% rename from mathematical_analysis.md rename to docs/mathematical_analysis.md diff --git a/novelty_matrix.md b/docs/novelty_matrix.md similarity index 95% rename from novelty_matrix.md rename to docs/novelty_matrix.md index 54909f8..3e7831d 100644 --- a/novelty_matrix.md +++ b/docs/novelty_matrix.md @@ -1,6 +1,6 @@ # Novelty matrix -Reference IDs resolve to `literature_review.md` and `evidence/papers.json`. “No certificate established” means none was established in this audit; it does not assert absence from an unread full text. +Reference IDs resolve to `docs/literature_review.md` and `evidence/papers.json`. “No certificate established” means none was established in this audit; it does not assert absence from an unread full text. ## Closest three per original proposal diff --git a/research_decision.md b/docs/research_decision.md similarity index 100% rename from research_decision.md rename to docs/research_decision.md diff --git a/research_log.md b/docs/research_log.md similarity index 97% rename from research_log.md rename to docs/research_log.md index b0d604f..131b11b 100644 --- a/research_log.md +++ b/docs/research_log.md @@ -8,7 +8,7 @@ **Decision.** Revised B is the first falsification target; C second; original A third. No novel theorem or publication-ready performance claim. Full-text novelty gates remain open. -**Analytical milestone.** Derived matching-deficiency monotonicity for frozen candidates; canonical assignment gives a conservative smooth FP upper bound; iid finite-grid tail-sum CP intervals give a population expected-count certificate. Derived explicit sample-size limitations. All use known combinatorial/statistical tools. Proved assumptions and counterexamples are in `mathematical_analysis.md`. +**Analytical milestone.** Derived matching-deficiency monotonicity for frozen candidates; canonical assignment gives a conservative smooth FP upper bound; iid finite-grid tail-sum CP intervals give a population expected-count certificate. Derived explicit sample-size limitations. All use known combinatorial/statistical tools. Proved assumptions and counterexamples are in `docs/mathematical_analysis.md`. **Implementation milestone.** Created original compact U-Net/loss/gate training code, fixed-pool metrics/calibration, data audit, scripts and ablation matrix. Pure CPU mathematical and integration checks pass. 24 tests discovered: 22 pass; 2 PyTorch gradient tests skipped. Syntax compilation passes. No dataset/GPU experiment ran; PyTorch and an exposed NVIDIA device are unavailable. The fixture pipeline exercises reject-all handling and certificate invalidation, not real IRSTD accuracy.