{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WML3K5MZ5GDESO7MOVAIGXMUZ6","short_pith_number":"pith:WML3K5MZ","canonical_record":{"source":{"id":"2401.06059","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T17:24:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3f683ebc6f8c0d03bb377ab7be1f7556278e7cb68a3fddd14da323fada976858","abstract_canon_sha256":"dbdfdf732b900702c1009d57ed770ac938d07d83bc2a513991f080f75fcc95e9"},"schema_version":"1.0"},"canonical_sha256":"b317b57599e986493bec7540835d94cf9ce17a3078f0c0be1f57c9e3f4c8aa61","source":{"kind":"arxiv","id":"2401.06059","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06059","created_at":"2026-07-05T07:32:40Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06059v1","created_at":"2026-07-05T07:32:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06059","created_at":"2026-07-05T07:32:40Z"},{"alias_kind":"pith_short_12","alias_value":"WML3K5MZ5GDE","created_at":"2026-07-05T07:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"WML3K5MZ5GDESO7M","created_at":"2026-07-05T07:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"WML3K5MZ","created_at":"2026-07-05T07:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WML3K5MZ5GDESO7MOVAIGXMUZ6","target":"record","payload":{"canonical_record":{"source":{"id":"2401.06059","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T17:24:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3f683ebc6f8c0d03bb377ab7be1f7556278e7cb68a3fddd14da323fada976858","abstract_canon_sha256":"dbdfdf732b900702c1009d57ed770ac938d07d83bc2a513991f080f75fcc95e9"},"schema_version":"1.0"},"canonical_sha256":"b317b57599e986493bec7540835d94cf9ce17a3078f0c0be1f57c9e3f4c8aa61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:40.120830Z","signature_b64":"SdcvdGwU0Ne0t1NEoCZDqbQktHdSNpke7duLlxCpVc7/q7sJ40rUtI6ZX0zKF1qjBkuwOB6V2132f64rci6eAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b317b57599e986493bec7540835d94cf9ce17a3078f0c0be1f57c9e3f4c8aa61","last_reissued_at":"2026-07-05T07:32:40.120322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:40.120322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.06059","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:32:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Yv5WilPie19rXkUVHZiMp26jGncc0AuZDHheMknV61U/rez+IoWuaLhY/WtgQPGH+kI4HLiJNfoAsHjUvQbAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:28:09.683588Z"},"content_sha256":"e887fc23ba7010736a74f5fbce2bb1253a7bab29c0c0432cd3e26f9eb532f0f5","schema_version":"1.0","event_id":"sha256:e887fc23ba7010736a74f5fbce2bb1253a7bab29c0c0432cd3e26f9eb532f0f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WML3K5MZ5GDESO7MOVAIGXMUZ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Data Contamination for Pre-training Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiawei Han, Ken Ziyu Liu, Ming Zhong, Minhao Jiang, Rylan Schaeffer, Sanmi Koyejo, Siru Ouyang","submitted_at":"2024-01-11T17:24:49Z","abstract_excerpt":"Language models pre-trained on web-scale corpora demonstrate impressive capabilities on diverse downstream tasks. However, there is increasing concern whether such capabilities might arise from evaluation datasets being included in the pre-training corpus -- a phenomenon known as \\textit{data contamination} -- in a manner that artificially increases performance. There has been little understanding of how this potential contamination might influence LMs' performance on downstream tasks. In this paper, we explore the impact of data contamination at the pre-training stage by pre-training a series"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06059","kind":"arxiv","version":1},"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/2401.06059/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":"2026-07-05T07:32:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hBB1cdftpVeGbbTKuLPxuP9TNhzGnhZP7Gc6nppqCNp+XeQgeqy6YmASQzUhiYZiYhfKuhFHbpq4aSMwjFDHCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:28:09.684171Z"},"content_sha256":"3765c4fc582f83b3cf6ae4dc4c6f67edf7084c08e8509482de37074ad99a0f09","schema_version":"1.0","event_id":"sha256:3765c4fc582f83b3cf6ae4dc4c6f67edf7084c08e8509482de37074ad99a0f09"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WML3K5MZ5GDESO7MOVAIGXMUZ6/bundle.json","state_url":"https://pith.science/pith/WML3K5MZ5GDESO7MOVAIGXMUZ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WML3K5MZ5GDESO7MOVAIGXMUZ6/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":"2026-08-07T21:28:09Z","links":{"resolver":"https://pith.science/pith/WML3K5MZ5GDESO7MOVAIGXMUZ6","bundle":"https://pith.science/pith/WML3K5MZ5GDESO7MOVAIGXMUZ6/bundle.json","state":"https://pith.science/pith/WML3K5MZ5GDESO7MOVAIGXMUZ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WML3K5MZ5GDESO7MOVAIGXMUZ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WML3K5MZ5GDESO7MOVAIGXMUZ6","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":"dbdfdf732b900702c1009d57ed770ac938d07d83bc2a513991f080f75fcc95e9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T17:24:49Z","title_canon_sha256":"3f683ebc6f8c0d03bb377ab7be1f7556278e7cb68a3fddd14da323fada976858"},"schema_version":"1.0","source":{"id":"2401.06059","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06059","created_at":"2026-07-05T07:32:40Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06059v1","created_at":"2026-07-05T07:32:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06059","created_at":"2026-07-05T07:32:40Z"},{"alias_kind":"pith_short_12","alias_value":"WML3K5MZ5GDE","created_at":"2026-07-05T07:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"WML3K5MZ5GDESO7M","created_at":"2026-07-05T07:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"WML3K5MZ","created_at":"2026-07-05T07:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:3765c4fc582f83b3cf6ae4dc4c6f67edf7084c08e8509482de37074ad99a0f09","target":"graph","created_at":"2026-07-05T07:32:40Z","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/2401.06059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models pre-trained on web-scale corpora demonstrate impressive capabilities on diverse downstream tasks. However, there is increasing concern whether such capabilities might arise from evaluation datasets being included in the pre-training corpus -- a phenomenon known as \\textit{data contamination} -- in a manner that artificially increases performance. There has been little understanding of how this potential contamination might influence LMs' performance on downstream tasks. In this paper, we explore the impact of data contamination at the pre-training stage by pre-training a series","authors_text":"Jiawei Han, Ken Ziyu Liu, Ming Zhong, Minhao Jiang, Rylan Schaeffer, Sanmi Koyejo, Siru Ouyang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T17:24:49Z","title":"Investigating Data Contamination for Pre-training Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06059","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:e887fc23ba7010736a74f5fbce2bb1253a7bab29c0c0432cd3e26f9eb532f0f5","target":"record","created_at":"2026-07-05T07:32:40Z","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":"dbdfdf732b900702c1009d57ed770ac938d07d83bc2a513991f080f75fcc95e9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T17:24:49Z","title_canon_sha256":"3f683ebc6f8c0d03bb377ab7be1f7556278e7cb68a3fddd14da323fada976858"},"schema_version":"1.0","source":{"id":"2401.06059","kind":"arxiv","version":1}},"canonical_sha256":"b317b57599e986493bec7540835d94cf9ce17a3078f0c0be1f57c9e3f4c8aa61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b317b57599e986493bec7540835d94cf9ce17a3078f0c0be1f57c9e3f4c8aa61","first_computed_at":"2026-07-05T07:32:40.120322Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:32:40.120322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SdcvdGwU0Ne0t1NEoCZDqbQktHdSNpke7duLlxCpVc7/q7sJ40rUtI6ZX0zKF1qjBkuwOB6V2132f64rci6eAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:32:40.120830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06059","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e887fc23ba7010736a74f5fbce2bb1253a7bab29c0c0432cd3e26f9eb532f0f5","sha256:3765c4fc582f83b3cf6ae4dc4c6f67edf7084c08e8509482de37074ad99a0f09"],"state_sha256":"2fac6332e6891d6aa4b8387ce30ffc0760662b424f023b9b8d1703c38a15c8f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l7ENo69yzj8Gr5Jzrhme46RIJonXg2IiRZyDOXbpQZjgG7DGM1C7m2/gX6YmMXcCZO/pwiCC1xNHiQzJ0/k+BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:28:09.688043Z","bundle_sha256":"8c9c3e8da31d79d0457d50c49adc89521d0ac71e7fc5c460e6e7a02326e703a5"}}