{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3TNI45ZJJBU63RBYTI2FLPWUYY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e2bc41ae09223cc236ed3abf9a05adc8c2877ebcf112e6bd6c266a159415d2ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T05:50:19Z","title_canon_sha256":"513d15ead7be70b3bce1621b3976558806babde39c75c9d165a1cc6a0a91e262"},"schema_version":"1.0","source":{"id":"2505.16260","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16260","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16260v1","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16260","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"pith_short_12","alias_value":"3TNI45ZJJBU6","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"pith_short_16","alias_value":"3TNI45ZJJBU63RBY","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"pith_short_8","alias_value":"3TNI45ZJ","created_at":"2026-07-05T11:07:32Z"}],"graph_snapshots":[{"event_id":"sha256:902a81695f3a51bfc59b57b6cc9fd5b2d0c4e7bed6d56bd2ace7e6419e8bf6c3","target":"graph","created_at":"2026-07-05T11:07:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.16260/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Choice of training data distribution greatly influences model behavior. Yet, in large-scale settings, precisely characterizing how changes in training data affects predictions is often difficult due to model training costs. Current practice is to instead extrapolate from scaled down, inexpensive-to-train proxy models. However, changes in data do not influence smaller and larger models identically. Therefore, understanding how choice of data affects large-scale models raises the question: how does training data distribution influence model behavior across compute scale? We find that small- and ","authors_text":"Alaa Khaddaj, Aleksander Madry, Logan Engstrom","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T05:50:19Z","title":"Small-to-Large Generalization: Data Influences Models Consistently Across Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16260","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e079cbb18a4f34e0d63e83031d9724fbf87479132c29f27527d8c05afdb78fb2","target":"record","created_at":"2026-07-05T11:07:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e2bc41ae09223cc236ed3abf9a05adc8c2877ebcf112e6bd6c266a159415d2ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T05:50:19Z","title_canon_sha256":"513d15ead7be70b3bce1621b3976558806babde39c75c9d165a1cc6a0a91e262"},"schema_version":"1.0","source":{"id":"2505.16260","kind":"arxiv","version":1}},"canonical_sha256":"dcda8e77294869edc4389a3455bed4c6183caafa484e216b9046509fe9629e51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcda8e77294869edc4389a3455bed4c6183caafa484e216b9046509fe9629e51","first_computed_at":"2026-07-05T11:07:32.323786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:32.323786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xK7rH1zFbNIFo804Aioga+s/BsoILCh/ST0DBuZQeqoV2txwIQzKmPlWOZuuwzm+cXglWyR5dzXjD4C9Dz2GBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:32.324167Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16260","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e079cbb18a4f34e0d63e83031d9724fbf87479132c29f27527d8c05afdb78fb2","sha256:902a81695f3a51bfc59b57b6cc9fd5b2d0c4e7bed6d56bd2ace7e6419e8bf6c3"],"state_sha256":"954833cc9dc2cf6a5e2e7e355e0a2f6d6d357b48e4bf06b2fd2d4b91225a372b"}