round-10: physics-factorial + direct-2048 chain (src/pino/train.py)

round-7 follow-through: disjoint_256 arm (src/pino/train.py)

round-7: morgan_2048_rp parity arm (src/pino/train.py)

Factorial channel ablation: --physics-mode (gamma_only/headspace_only) in train.py + evaluator matching + factorial job script

Upload src/pino/train.py with huggingface_hub

Upload src/pino/train.py with huggingface_hub

Upload src/pino/train.py with huggingface_hub

review-response: upload src/pino/train.py

Upload src/pino/train.py with huggingface_hub

feat: pom_alltags structural source — 269-dim OpenPOM input, 575-dim tag objective head

feat: wire genuine 256-dim OpenPOM into training (--structural-source)

pimt v9 substantivity gbm train publish path

Add Fraterworks ingestion and upload data split support

fix: normalize objective targets for pyramid training

feat: prepare v7 HF training and evaluation

v6: ConcentrationAwarePyramidHead + OAV fix + curated descriptors + integration

feat: 3-tier scent pyramid objective head + v4 dataset + v5 training job

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

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

fix(loss): prevent objective-starvation with fixed task weights; target pimt_v3.pt

feat: replace sigmoid gating with stabilized FiLM affine modulation; train pimt_v2.pt

feat(embeddings): expand input token from 145-D to 151-D with physical-functional payload

perf(train): avoid Hugging Face Dataset round-trip during formula-disjoint split

fix(train): keep AdaptiveLossBalancer forward signature intact, expose last_weights attribute

feat(train): log AdaptiveLossBalancer weights per batch for telemetry verification

chore(train): point default data path to empirical dataset and confirm balancer/loss setup

feat(train): pin 597 single-molecule controls exclusively to training

refactor(loss): rename DeepSeekLossBalancer to AdaptiveLossBalancer

feat(train,heads,loss): DeepSeekLossBalancer + continuous cosine alignment

feat(structure,thermo): 3D shape + natural oil reconstruction, 145-D input

fix(upload,train): use load_dataset select and fingerprint-based leakage check

feat(upload,train): formula-disjoint split with full corpus recovery

fix(upload,train): enforce strict molecule-disjoint isolation

refactor(train): directive-style molecule-disjoint data ingestion

feat(upload,train): directive-compliant molecule-disjoint split

chore(train): default DataLoader workers to 0 for local check cycles

feat(train,upload): multi-task training with InfoNCE and molecule-disjoint upload

feat: Milestone 4 clean code snapshot