Commit History

25 days ago

  1. feat: TabPFN-3.5 options for the PFN, a cosine schedule and faster meta-training⁠

    ho22joshua +1: Claude Opus 5.5
    71aefe8

  1. docs: correct the label-efficiency study and add a script that reruns it⁠

    ho22joshua +1: Claude Opus 5.5
    9b7b80d
  2. docs: first label-efficiency study on GamGam⁠

    ho22joshua +1: Claude Opus 5.5
    4e2096a

  1. feat: linear CKA between object encoders⁠

    ho22joshua +1: Claude Opus 5.5
    0821800
  2. feat: evaluation subsample, Slurm wrappers for the study and label-efficiency plots⁠

    ho22joshua +1: Claude Opus 5.5
    e71731f
  3. feat: tabular in-context models, LoRA meta-training, pretraining objectives and probes⁠

    ho22joshua +1: Claude Opus 5.5
    8dff74c
  4. feat: TabPFN and a collider PFN as in-context models⁠

    ho22joshua +1: Claude Opus 5.5
    9402518
  5. feat: JEPA pretraining of the edge network⁠

    ho22joshua +1: Claude Opus 5.5
    722850b
  6. feat: JEPA pretraining of the object transformer⁠

    ho22joshua +1: Claude Opus 5.5
    9b40da9
  7. feat: transformer pair attention bias and a Deep Sets model⁠

    ho22joshua +1: Claude Opus 5.5
    df3eb75
  8. feat(transformer): type embedding instead of positions, pre-norm, ONNX export⁠

    ho22joshua +1: Claude Opus 5.5
    f43b1e5

  1. chore: move test fixtures into tests/, flatten scripts/, drop paper source⁠

    ho22joshua +1: Claude Opus 5.5
    2f04f23
  2. chore: keep only the final epoch of each pretrained model⁠

    ho22joshua +1: Claude Opus 5.5
    973bea8
  3. refactor: flat modules, one YAML per experiment, no Hydra⁠

    ho22joshua +1: Claude Opus 5.5
    0cef53c
  4. chore: remove legacy parity, validation harness, benchmarks and release tooling⁠

    ho22joshua +1: Claude Opus 5.5
    59a41d9
  5. feat: upgrade to Python 3.14 and PyTorch 2.14; add torch.compile and bfloat16⁠

    ho22joshua +1: Claude Opus 5.5
    3f1977c
  6. docs: make the ATLAS Open Data GamGam task the main benchmark⁠

    ho22joshua +1: Claude Opus 5.5
    6285343

  1. feat: replace DGL with shared packed events and native PyTorch graphs

    fa0afd8
  2. chore: reorganize repository and move graph preparation into graphs⁠

    ho22joshua +1: Claude Opus 5.5
    21ff625

  1. feat: add restartable sharded graph preparation

    2c479af
  2. feat: add restartable sharded graph preparation

    c5cf2cc
  3. feat: add ttH CP parity benchmark configuration

    d2d4ccf
  4. feat: add initial root transformer model

    8344837
  5. perf: parallelize deterministic graph preparation

    e74a91a
  6. docs: add package and agent workflow guides

    70ee5cc
  7. Remove historical implementation from active tree

    de46a3c
  8. Document frozen ROOT-GNN parity baseline

    d93a2db

  1. docs: add Codex and Claude workflow skill

    9f7b9b2
  2. PR 2 — Portable Public End-to-End Validation Fixture (#11)⁠

    c20af2a
  3. ci: support macOS core development (#8)⁠

    5ae003d
  4. rewriting codebase (#7)⁠

    916755e