Correct TabSketchFM checkpoint provenance and re-host decision - #1
Correct TabSketchFM checkpoint provenance and re-host decision#1weipang142857 wants to merge 1 commit into
Conversation
The audit recorded the TabSketchFM checkpoint as an IBM/LakeBench Zenodo artifact and directed users there. That was wrong on two counts: upstream released no checkpoint at all, and the weights TRL-Bench uses were trained by us with the upstream pretrain.py. Following the old instructions made the paper's TabSketchFM results unreproducible. Confirmed from checkpoint metadata: the file records pytorch-lightning 2.5.6, a release postdating the upstream paper (July 2024), so it cannot be an upstream artifact. Weights (not code) are now mirrored to logo-lab/trl-bench-ckpts/tabsketchfm/ with per-model LICENSE and NOTICE. The ND clause governs redistribution of code and is not engaged by publishing our own training output; no upstream source is redistributed. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
There was a problem hiding this comment.
🟡 Not ready to approve
A few documentation updates are confusing/inconsistent (upstream-only list) and include overly definitive license interpretation language that should be made more cautious/precise.
Once you've addressed the issues Copilot identified, you can request another Copilot review.
This review doesn't count toward merge requirements. Sign up for the private preview to control whether Copilot approvals count.
Pull request overview
Updates checkpoint licensing/provenance documentation to correct TabSketchFM’s source attribution and to document the decision to mirror TRL-Bench-trained weights (since no upstream checkpoint exists), improving reproducibility guidance.
Changes:
- Corrects TabSketchFM provenance (no upstream checkpoint; TRL-Bench-trained weights) and updates the mirror decision accordingly.
- Removes TabSketchFM from the “upstream-only” checkpoint category and updates the fetch-path table to reference the HF mirror.
- Expands TabSketchFM section with provenance evidence and updated attribution guidance.
File summaries
| File | Description |
|---|---|
| docs/CHECKPOINT_LICENSES.md | Corrects TabSketchFM checkpoint provenance/mirroring policy and updates user-facing fetch instructions accordingly. |
Review details
- Files reviewed: 1/1 changed files
- Comments generated: 4
- Review effort level: Lite
We're testing this review assessment. Please use 👍 or 👎 to tell us if it's correct.
| | TaBERT | CC BY-NC 4.0 | NON-COMMERCIAL ONLY | Mirror under NC tag (TRL-Bench is academic) | | ||
| | TURL | Apache-2.0 | YES, attribution required | Mirror | | ||
| | TabSketchFM | CC BY-NC-ND 4.0 | NO (no derivatives) | Document upstream URL only | | ||
| | TabSketchFM | CC BY-NC-ND 4.0 (code) | WEIGHTS ARE OURS | Mirror our own trained weights (no upstream ckpt exists) | |
| - **Re-host permitted:** YES, for the weights. They are our own training output | ||
| rather than a copy of any IBM-distributed artefact, so the ND clause — which | ||
| governs redistribution of *code* — is not engaged by publishing them. Hosting | ||
| is also required for reproducibility, since no upstream checkpoint exists. | ||
| Source code is NOT redistributed: the mirror carries weights only, and users | ||
| obtain the code from the upstream repository under the upstream license. |
| 3. **TabSketchFM is no longer in this category.** Upstream released no | ||
| checkpoint at all, and the weights TRL-Bench uses were trained by us; they | ||
| are now mirrored on logo-lab/trl-bench-ckpts (weights only — no upstream | ||
| code is redistributed). See its section above. TaBERT (CC BY-NC 4.0, was | ||
| previously also upstream-only) is likewise mirrored under the | ||
| non-commercial inheritance described in its section. |
| | TURL | `turl/pretrained/{pytorch_model.bin,config.json}` | HF: `logo-lab/trl-bench-ckpts` (auto-fetched) | | ||
| | TUTA | `tuta/tuta.bin` | HF: `logo-lab/trl-bench-ckpts` (auto-fetched) | | ||
| | TabSketchFM | `tabsketchfm/epoch=10-step=27786.ckpt` | MANUAL: https://doi.org/10.5281/zenodo.8014642 | | ||
| | TabSketchFM | `tabsketchfm/epoch=10-step=27786.ckpt` | HF: `logo-lab/trl-bench-ckpts` (TRL-Bench-trained weights; no upstream ckpt exists) | |
Problem
docs/CHECKPOINT_LICENSES.mdrecorded the TabSketchFM checkpoint as an IBM/LakeBench artifact and directed users to Zenodo (10.5281/zenodo.8014642) to obtain it. That was wrong on two counts:pretrain.py, initialized frombert-base-uncased, over tables fetched from the source URLs upstream publishes inpretraining_tables.txt.Consequence: anyone following the documentation to reproduce the paper's TabSketchFM results hit a dead end.
Evidence
The checkpoint's own metadata records
pytorch-lightning 2.5.6— a release postdating the upstream paper (arXiv:2407.01619, July 2024) — so it cannot be an upstream artifact.The filename
epoch=10-step=27786.ckptis PyTorch Lightning's defaultModelCheckpointauto-naming and carries no provenance; the original entry appears to have inferred IBM origin from it. The file is also a weights-only save (state_dictonly, nohyper_parametersorcallbacks), which is why it embeds no training paths that would have settled the question directly.Change
Four corrections in
docs/CHECKPOINT_LICENSES.md:NO (no derivatives)→ weights are ours, mirroredRe-host rationale, in short: the ND clause governs redistribution of code, and these weights are our own training output rather than a copy of an IBM-distributed artifact. Publishing is additionally necessary for reproducibility, since no upstream checkpoint exists.
Companion change (already live, outside this repo)
epoch=10-step=27786.ckptis now mirrored atlogo-lab/trl-bench-ckpts/tabsketchfm/with per-modelLICENSEandNOTICE. Remote SHA256 verified identical to local (26f2107d…f9f211d).Weights only — no upstream source code is redistributed. The
NOTICEstates prominently that this is not an official IBM release and directs users toIBM/tabsketchfmfor the code under the upstream license. The repo README was updated to match, including scoping its previous blanket "byte-identical to the upstream releases" claim to the checkpoints where it actually holds.scripts/checksums.sha256already carried the correct hash for this file, so post-download verification works unchanged.Not included (deliberate — follow-up needed)
Two files still direct users to Zenodo and should be fixed separately:
scripts/download_checkpoints.sh:85-89— prints the placeholder and skips; TabSketchFM will not auto-fetch from the new mirrorsrc/trl_bench/registry.py:964-968— comment still reads "Cannot be mirrored (ND clause); users fetch from the IBM/LakeBench Zenodo record"scripts/checksums.sha256— hash correct; only its(CC BY-NC-ND 4.0, upstream-only)comment label is stale🤖 Generated with Claude Code