catt-bench/vtok101-distr-attribution-baselines

9,869 downloads in 30 days4 likesLast modified 29 Oct 2026View on Hugging Face

The declared licence (mit) is classified as permissive.

Declared licencemit, from the tag
Licence filesNo licence file at the top level of the repository
Declared sourcesNone listed in the card metadata
Access gated on Hugging FaceNo

Citation text from the card

The attribution scores of "Elucidating the Design Space of LM Data Attribution"
on **Function Bindings with distractors**, for the LoRA adapters in
[catt-bench/Qwen3.5-4B-d0-vtok101-distr-lora-seeds](https://huggingface.co/catt-bench/Qwen3.5-4B-d0-vtok101-distr-lora-seeds). The CATT code release reads them
with `catt fetch results --task fb-distr` and rebuilds the paper's figures and tables
from them with `catt report results`.

Every real document has a decoy beside it: a shadow function `<Axx>` taught the
same constant in the same template as `<Bxx>`. The pool is twice as large and
queries only ask about real functions, so AUC keeps its meaning while Recall@N's
chance line halves. `metrics.json` adds `decoy_auc` (a real document against the
query's own decoys) and `decoy_top1`.

All datasets marked Permissive or share-alike | JSON

The same facts for your agent

A free MCP server at mcp.datalicense.uk/mcp. Connect it from an MCP client such as Claude or Cursor.

dataset_licence({ "id": "catt-bench/vtok101-distr-attribution-baselines" })
signal: "permissive"
stated_licence: "mit"
sources: 0

Licence facts reported by the dataset and its declared sources. Not legal advice, and not a grant of permission to use the dataset.