Commit History

  1. feat: evaluation subsample, Slurm wrappers for the study and label-efficiency plots⁠

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

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

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

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

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

    ho22joshua +1: Claude Opus 5.5
    df3eb75
  7. 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
  7. feat: add the ATLAS Open Data GamGam 5-class task and faster training⁠

    ho22joshua +1: Claude Opus 5.5
    5b73bcb
  8. docs: drop dgl tag from model card metadata⁠

    ho22joshua +1: Claude Opus 5.5
    b08aa60

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

    fa0afd8
  2. test: freeze DGL ROOT-GNN outputs on the 64-event fixture⁠

    ho22joshua +1: Claude Opus 5.5
    125ce6d
  3. 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. chore: remove obsolete legacy workspace plumbing

    7cb97a8
  7. docs: protect paper README

    bccdb43
  8. docs: add package and agent workflow guides

    70ee5cc
  9. Remove historical implementation from active tree

    de46a3c
  10. Document frozen ROOT-GNN parity baseline

    d93a2db
  11. Add binary CP parity validation runners

    c93e291

  1. Add legacy pretrained checkpoints

    05ddcfb

  1. docs: add Codex and Claude workflow skill

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

    c20af2a
  3. docs: normalize inline notation in model card

    a900118
  4. docs: normalize model card ending

    1eecff3
  5. docs: clean model card formatting artifacts

    bc5e5b8
  6. docs: fix Hugging Face model card rendering

    da5e5e2
  7. docs: add Hugging Face model card based on paper (#9)⁠

    0075ca0
  8. ci: support macOS core development (#8)⁠

    5ae003d
  9. rewriting codebase (#7)⁠

    916755e

  1. adding delphes configs, improved parallism in graph processing

    15a699e

  1. adding multiclass pretrained model

    ae01d3e

  1. fixing error when no selections applied

    966f93f
  2. making job submission and scripts more general, removing hard coded paths

    9e4bc69
  3. updating codex skills

    a3c512e

  1. fixing inference script corrupting vector branches in ntuples

    a78b1b8

  1. improved randomness in dataset shuffling

    815d3b2

  1. onnx export

    6fe006b

  1. adding onnx model export scripts

    ad71257

  1. implemented preselections inside config

    47591c0
  2. adding pretrained model to repo

    3f9504d