docs: final GPU readout in README + model card; add POM relation section

fix: paper_data exporter prefers GPU readout; stamp val_total into GPU evals; stats bundle

feat: GPU readout figures + stats scripts + val-total macros

feat: GPU A/B readout — per-genre prospective figure + refreshed paper_data macros

feat: paper_data.yaml exporter for autopaper (49 data_macros)

chore: READY gate state, material_profiles v11_5 refresh, source-population AI review, repair-pairs benchmark

chore: v11.6 + v11.5 + candidate-20260716a artifact reports and manifests

chore: two-arm A/B checkpoints + frozen-benchmark readout -> HF

feat: gate flips READY_FOR_TRAINING (all 5 checks pass)

feat: prospective formula benchmark (40 in-silico formulas, blinded labels)

feat: complete representation ablation + discordant substitution triplets

feat: freeze representation validation gate

chore: record genre challenge v2 archive manifest

release: freeze blinded genre challenge v2

v11.5 verdict + paper fold: substitution = bounded

v11.5 powered re-run: effective n=14→28, retriever=0/28 [0.000,0.121], physchem=0/28 [0.000,0.121], random=0/28 [0.000,0.121], verdict=underpowered

Complete catalog recovery and enrichment

v11.5 paper fold: substitution = bounded

v11.5 training decision: not-warranted, data is the lever

v11.5 powered re-run: effective n=28, full=1/28 [0.006,0.177], physchem=0/28 [0.000,0.121], verdict=underpowered

v11.5 enrichment: VP/BP 67→340, structure 1731→1741, eval-pairs newly representable=3, leak-rejected=0, formula/MW-rejected=15

v11.3 paper fold: substitution section = inconclusive, profile-coverage limited

v11.3 training scope: not-warranted, independent data coverage is the lever

v11.3 verdict: advantage ambiguous at effective n=14, CIs full=[0.076,0.476] physchem=[0.000,0.215]

v11.3 powered retriever: full=3/14 [0.076,0.476], physchem=0/14 [0.000,0.215], random=1/14 [0.013,0.315], n_excluded=27

results(v11): report preregistered retrieval assessment

fix(v11): preregister mode-aware retrieval evaluation

v11 assessment: retriever top5=0.133, descriptor kept, formula scoped

v11 retriever descriptors: top5=0.133, descriptor delta=0.033 kept

train v10: substantivity rho=0.535, character macro F1=0.134

pimt v9 require registry db for gbm reproduction

pimt v9 substantivity gbm train publish path

pimt v8 diagnostics and qa artifacts

pimt v8 run statistical validation

substantivity writeup: result consolidated, noise-floor framed, prior-art positioned

character verdict: discriminative-weak under distributional metric

character distributional metric: cosine/JS over prevalence vectors, mean=0.080

character diagnostic: artifact-fixes — prevalence-by-genre, threshold-sensitivity, retract fake best-grouping

character 1.000 diagnosis: artifact — superclass sets identical

character grouping diagnostic: 26-class J=0.793, 5-superclass J=1.000, recommend pause labels

phase1 recompute: drop-10 ρ=0.708, prefer-measured ρ=0.663, baseline survived Y, noise floor=0.479

Add Fraterworks ingestion and upload data split support

feat: add WiseMoor v9 provenance dataset

docs: record Task A anchor audit

feat: add Poucher substantivity targets

feat: expand descriptor target coverage

v6: ConcentrationAwarePyramidHead + OAV fix + curated descriptors + integration