{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GPJSTAHIITKQH5F4J6UYH5RZFY","short_pith_number":"pith:GPJSTAHI","canonical_record":{"source":{"id":"2410.03249","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T09:14:11Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"cdc9bb92f406c159a2b41c138081a5fa1a8ec632cda8519b2befe15db0285926","abstract_canon_sha256":"c5cc7f4af2600a69ef0837b45e30af48bca5d9981ee14739039dc17d3eb7fc66"},"schema_version":"1.0"},"canonical_sha256":"33d32980e844d503f4bc4fa983f6392e3f633b22c52b1d72a6400bbfe3dbf56d","source":{"kind":"arxiv","id":"2410.03249","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03249","created_at":"2026-07-05T11:21:36Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03249v4","created_at":"2026-07-05T11:21:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03249","created_at":"2026-07-05T11:21:36Z"},{"alias_kind":"pith_short_12","alias_value":"GPJSTAHIITKQ","created_at":"2026-07-05T11:21:36Z"},{"alias_kind":"pith_short_16","alias_value":"GPJSTAHIITKQH5F4","created_at":"2026-07-05T11:21:36Z"},{"alias_kind":"pith_short_8","alias_value":"GPJSTAHI","created_at":"2026-07-05T11:21:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GPJSTAHIITKQH5F4J6UYH5RZFY","target":"record","payload":{"canonical_record":{"source":{"id":"2410.03249","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T09:14:11Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"cdc9bb92f406c159a2b41c138081a5fa1a8ec632cda8519b2befe15db0285926","abstract_canon_sha256":"c5cc7f4af2600a69ef0837b45e30af48bca5d9981ee14739039dc17d3eb7fc66"},"schema_version":"1.0"},"canonical_sha256":"33d32980e844d503f4bc4fa983f6392e3f633b22c52b1d72a6400bbfe3dbf56d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:36.403556Z","signature_b64":"piu86o6j6AhUf7PVN9chPX/1gKyga3l9rR+ls84gebNfb+6kE3qmzoDaAv3+4qmwYBCxCZTMuSGtZo5hvkgOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33d32980e844d503f4bc4fa983f6392e3f633b22c52b1d72a6400bbfe3dbf56d","last_reissued_at":"2026-07-05T11:21:36.403012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:36.403012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.03249","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HSWO2aWZzddy4wxesvPSEhjiAefA5jhzy/MdAwlGbf3d0dFoAMUkKV8bzPZyoCtEzuBrAUcsfD5SN7QybFp9AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:58:31.817186Z"},"content_sha256":"1bfca08f1cbc997242b44fd2693a4286b98cb260ec96428b4a642d8e27ec1d80","schema_version":"1.0","event_id":"sha256:1bfca08f1cbc997242b44fd2693a4286b98cb260ec96428b4a642d8e27ec1d80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GPJSTAHIITKQH5F4J6UYH5RZFY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Much Can We Forget about Data Contamination?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Sebastian Bordt, Suraj Srinivas, Ulrike von Luxburg, Valentyn Boreiko","submitted_at":"2024-10-04T09:14:11Z","abstract_excerpt":"The leakage of benchmark data into the training data has emerged as a significant challenge for evaluating the capabilities of large language models (LLMs). In this work, we challenge the common assumption that small-scale contamination renders benchmark evaluations invalid. First, we experimentally quantify the magnitude of benchmark overfitting based on scaling along three dimensions: The number of model parameters (up to 1.6B), the number of times an example is seen (up to 144), and the number of training tokens (up to 40B). If model and data follow the Chinchilla scaling laws, minor contam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03249","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.03249/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:21:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X7zhtjg9ykX6idBjUrNK49VwgLwEEiZu4sZhMrPc3yUoIb2VMoXn7OjrGenmb878Iw/E+5g2sT/H8NGhNzQ2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T12:58:31.818627Z"},"content_sha256":"d4bfbc429ffc78a6d375af4a84f7316e53cfc3df6dc94e51199645bb6339c4d1","schema_version":"1.0","event_id":"sha256:d4bfbc429ffc78a6d375af4a84f7316e53cfc3df6dc94e51199645bb6339c4d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GPJSTAHIITKQH5F4J6UYH5RZFY/bundle.json","state_url":"https://pith.science/pith/GPJSTAHIITKQH5F4J6UYH5RZFY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GPJSTAHIITKQH5F4J6UYH5RZFY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T12:58:31Z","links":{"resolver":"https://pith.science/pith/GPJSTAHIITKQH5F4J6UYH5RZFY","bundle":"https://pith.science/pith/GPJSTAHIITKQH5F4J6UYH5RZFY/bundle.json","state":"https://pith.science/pith/GPJSTAHIITKQH5F4J6UYH5RZFY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GPJSTAHIITKQH5F4J6UYH5RZFY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GPJSTAHIITKQH5F4J6UYH5RZFY","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":"c5cc7f4af2600a69ef0837b45e30af48bca5d9981ee14739039dc17d3eb7fc66","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T09:14:11Z","title_canon_sha256":"cdc9bb92f406c159a2b41c138081a5fa1a8ec632cda8519b2befe15db0285926"},"schema_version":"1.0","source":{"id":"2410.03249","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03249","created_at":"2026-07-05T11:21:36Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03249v4","created_at":"2026-07-05T11:21:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03249","created_at":"2026-07-05T11:21:36Z"},{"alias_kind":"pith_short_12","alias_value":"GPJSTAHIITKQ","created_at":"2026-07-05T11:21:36Z"},{"alias_kind":"pith_short_16","alias_value":"GPJSTAHIITKQH5F4","created_at":"2026-07-05T11:21:36Z"},{"alias_kind":"pith_short_8","alias_value":"GPJSTAHI","created_at":"2026-07-05T11:21:36Z"}],"graph_snapshots":[{"event_id":"sha256:d4bfbc429ffc78a6d375af4a84f7316e53cfc3df6dc94e51199645bb6339c4d1","target":"graph","created_at":"2026-07-05T11:21:36Z","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/2410.03249/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The leakage of benchmark data into the training data has emerged as a significant challenge for evaluating the capabilities of large language models (LLMs). In this work, we challenge the common assumption that small-scale contamination renders benchmark evaluations invalid. First, we experimentally quantify the magnitude of benchmark overfitting based on scaling along three dimensions: The number of model parameters (up to 1.6B), the number of times an example is seen (up to 144), and the number of training tokens (up to 40B). If model and data follow the Chinchilla scaling laws, minor contam","authors_text":"Sebastian Bordt, Suraj Srinivas, Ulrike von Luxburg, Valentyn Boreiko","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T09:14:11Z","title":"How Much Can We Forget about Data Contamination?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03249","kind":"arxiv","version":4},"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":"sha256:1bfca08f1cbc997242b44fd2693a4286b98cb260ec96428b4a642d8e27ec1d80","target":"record","created_at":"2026-07-05T11:21:36Z","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":"c5cc7f4af2600a69ef0837b45e30af48bca5d9981ee14739039dc17d3eb7fc66","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T09:14:11Z","title_canon_sha256":"cdc9bb92f406c159a2b41c138081a5fa1a8ec632cda8519b2befe15db0285926"},"schema_version":"1.0","source":{"id":"2410.03249","kind":"arxiv","version":4}},"canonical_sha256":"33d32980e844d503f4bc4fa983f6392e3f633b22c52b1d72a6400bbfe3dbf56d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33d32980e844d503f4bc4fa983f6392e3f633b22c52b1d72a6400bbfe3dbf56d","first_computed_at":"2026-07-05T11:21:36.403012Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:36.403012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"piu86o6j6AhUf7PVN9chPX/1gKyga3l9rR+ls84gebNfb+6kE3qmzoDaAv3+4qmwYBCxCZTMuSGtZo5hvkgOBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:36.403556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03249","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bfca08f1cbc997242b44fd2693a4286b98cb260ec96428b4a642d8e27ec1d80","sha256:d4bfbc429ffc78a6d375af4a84f7316e53cfc3df6dc94e51199645bb6339c4d1"],"state_sha256":"85748108181b29d6cbf3e51d1a456d5701c31bb2ee74c75c65cb8fb294262f7f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"snscNw5aB5axzGMOPoh0bp0S7sBGR9e45Hbs+NJWuRqRRTHkJJ32Z9qb+JyOn8oLjm3M2vPFoIYGNcT/IgSaAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T12:58:31.826087Z","bundle_sha256":"b99a9e2d8c51e3dc8fab791770a29409988bf65a41cf3c46d94c41467bf19026"}}