docs: move research dossier into docs/ and update cross-references

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

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.

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
 

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.