chore: untrack large generated artifacts from source repo; ignore them

feat: low-evidence gating in substitution_v11 + wisemoor description provenance

release: freeze blinded genre challenge v2

pimt v8 diagnostics and qa artifacts

feat: add WiseMoor v9 provenance dataset

feat: use AI (OpenRouter) to classify GoodScents prose into perfume tiers

chore: ignore large PDFs, temp scripts, and intermediate extraction artifacts

v6: ConcentrationAwarePyramidHead + OAV fix + curated descriptors + integration

v4: three-tier descriptor targets (v3), collate padding sentinel, HF job v3 dataset

v4: time-aware objective head, physics-derived v2 targets, Pyrfume vocab

feat(naturals,shalimar): hierarchical natural oil tokenization

chore(hf): download warm registry.db cache from HF dataset repo before training

chore(gitignore): ignore generated artifacts, datasets, checkpoints, and logs

feat(pino): literature seed integration, stratified dataset split, registry enrichment, and Space sync

feat(literature): ingest and seed human-designed fragrance skeletons

feat(scraper): TGSC enrichment with mmHg->Pa conversion and priority registry updates

perf(optimizer): cache PIMT model locally instead of hitting Space every candidate

feat: add Milestone 5 generative inverse-design composer (CMA-ES)

chore: remove binary registry.db from repo

feat: Milestone 4 clean code snapshot