{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7KUPZFW77R64SK6TD7B3WXPIPK","short_pith_number":"pith:7KUPZFW7","canonical_record":{"source":{"id":"2403.06869","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T16:22:41Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"39809979dd4af38bfb10183579c7833bc17268254c3d21e780ca29eaabf45122","abstract_canon_sha256":"8f70bf34e6cbecf1526533e28a2007a340187d5e4e05da0fd089a6b90897a267"},"schema_version":"1.0"},"canonical_sha256":"faa8fc96dffc7dc92bd31fc3bb5de87aaacbeffc81623583af7ad43109d36742","source":{"kind":"arxiv","id":"2403.06869","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06869","created_at":"2026-07-05T10:58:15Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06869v3","created_at":"2026-07-05T10:58:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06869","created_at":"2026-07-05T10:58:15Z"},{"alias_kind":"pith_short_12","alias_value":"7KUPZFW77R64","created_at":"2026-07-05T10:58:15Z"},{"alias_kind":"pith_short_16","alias_value":"7KUPZFW77R64SK6T","created_at":"2026-07-05T10:58:15Z"},{"alias_kind":"pith_short_8","alias_value":"7KUPZFW7","created_at":"2026-07-05T10:58:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7KUPZFW77R64SK6TD7B3WXPIPK","target":"record","payload":{"canonical_record":{"source":{"id":"2403.06869","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T16:22:41Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"39809979dd4af38bfb10183579c7833bc17268254c3d21e780ca29eaabf45122","abstract_canon_sha256":"8f70bf34e6cbecf1526533e28a2007a340187d5e4e05da0fd089a6b90897a267"},"schema_version":"1.0"},"canonical_sha256":"faa8fc96dffc7dc92bd31fc3bb5de87aaacbeffc81623583af7ad43109d36742","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:15.286078Z","signature_b64":"AMmfD3vOr7L7PmO5OdO7upM3y4hk8UtFhOkRen8xYphmF1qrGt+aoBDge3i/mAKL7/dfeyY+Jv/JI/SHgYQbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"faa8fc96dffc7dc92bd31fc3bb5de87aaacbeffc81623583af7ad43109d36742","last_reissued_at":"2026-07-05T10:58:15.285529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:15.285529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.06869","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:58:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ACGqQNv3wz/38irGTNqf2Xj5JPQVSBVIBMacibizo45y22jEpdZRLU4C6QvrdDuHum/vKWhUZFskgjl9H2EYDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:13:23.499732Z"},"content_sha256":"a50a32bb53b52e27217014c27f2b3e177f40fbbf2f8edd03d056b9e90405e347","schema_version":"1.0","event_id":"sha256:a50a32bb53b52e27217014c27f2b3e177f40fbbf2f8edd03d056b9e90405e347"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7KUPZFW77R64SK6TD7B3WXPIPK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Impact of Noisy Supervision in Foundation Model Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Bhiksha Raj, Hao Chen, Hongxin Wei, Jindong Wang, Masashi Sugiyama, Ran Tao, Xing Xie, Zihan Wang","submitted_at":"2024-03-11T16:22:41Z","abstract_excerpt":"Foundation models are usually pre-trained on large-scale datasets and then adapted to downstream tasks through tuning. However, the large-scale pre-training datasets, often inaccessible or too expensive to handle, can contain label noise that may adversely affect the generalization of the model and pose unexpected risks. This paper stands out as the first work to comprehensively understand and analyze the nature of noise in pre-training datasets and then effectively mitigate its impacts on downstream tasks. Specifically, through extensive experiments of fully-supervised and image-text contrast"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06869","kind":"arxiv","version":3},"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/2403.06869/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":"2026-07-05T10:58:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F3mJuSULNGInrw5xsuqPQFtrgJ4sm8+TY1Exg4appS7QuQUA8ADsPwRokXiUbZHhpPBF0oil+dv7xUhUdrDRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:13:23.500101Z"},"content_sha256":"7c19c13c8b677ee99f9a5b3f9dbcd592b663072b9d70edceaf78f7c7c2a64d86","schema_version":"1.0","event_id":"sha256:7c19c13c8b677ee99f9a5b3f9dbcd592b663072b9d70edceaf78f7c7c2a64d86"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7KUPZFW77R64SK6TD7B3WXPIPK/bundle.json","state_url":"https://pith.science/pith/7KUPZFW77R64SK6TD7B3WXPIPK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7KUPZFW77R64SK6TD7B3WXPIPK/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":"2026-07-07T04:13:23Z","links":{"resolver":"https://pith.science/pith/7KUPZFW77R64SK6TD7B3WXPIPK","bundle":"https://pith.science/pith/7KUPZFW77R64SK6TD7B3WXPIPK/bundle.json","state":"https://pith.science/pith/7KUPZFW77R64SK6TD7B3WXPIPK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7KUPZFW77R64SK6TD7B3WXPIPK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7KUPZFW77R64SK6TD7B3WXPIPK","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":"8f70bf34e6cbecf1526533e28a2007a340187d5e4e05da0fd089a6b90897a267","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T16:22:41Z","title_canon_sha256":"39809979dd4af38bfb10183579c7833bc17268254c3d21e780ca29eaabf45122"},"schema_version":"1.0","source":{"id":"2403.06869","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06869","created_at":"2026-07-05T10:58:15Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06869v3","created_at":"2026-07-05T10:58:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06869","created_at":"2026-07-05T10:58:15Z"},{"alias_kind":"pith_short_12","alias_value":"7KUPZFW77R64","created_at":"2026-07-05T10:58:15Z"},{"alias_kind":"pith_short_16","alias_value":"7KUPZFW77R64SK6T","created_at":"2026-07-05T10:58:15Z"},{"alias_kind":"pith_short_8","alias_value":"7KUPZFW7","created_at":"2026-07-05T10:58:15Z"}],"graph_snapshots":[{"event_id":"sha256:7c19c13c8b677ee99f9a5b3f9dbcd592b663072b9d70edceaf78f7c7c2a64d86","target":"graph","created_at":"2026-07-05T10:58:15Z","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/2403.06869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foundation models are usually pre-trained on large-scale datasets and then adapted to downstream tasks through tuning. However, the large-scale pre-training datasets, often inaccessible or too expensive to handle, can contain label noise that may adversely affect the generalization of the model and pose unexpected risks. This paper stands out as the first work to comprehensively understand and analyze the nature of noise in pre-training datasets and then effectively mitigate its impacts on downstream tasks. Specifically, through extensive experiments of fully-supervised and image-text contrast","authors_text":"Bhiksha Raj, Hao Chen, Hongxin Wei, Jindong Wang, Masashi Sugiyama, Ran Tao, Xing Xie, Zihan Wang","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T16:22:41Z","title":"Impact of Noisy Supervision in Foundation Model Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06869","kind":"arxiv","version":3},"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:a50a32bb53b52e27217014c27f2b3e177f40fbbf2f8edd03d056b9e90405e347","target":"record","created_at":"2026-07-05T10:58:15Z","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":"8f70bf34e6cbecf1526533e28a2007a340187d5e4e05da0fd089a6b90897a267","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T16:22:41Z","title_canon_sha256":"39809979dd4af38bfb10183579c7833bc17268254c3d21e780ca29eaabf45122"},"schema_version":"1.0","source":{"id":"2403.06869","kind":"arxiv","version":3}},"canonical_sha256":"faa8fc96dffc7dc92bd31fc3bb5de87aaacbeffc81623583af7ad43109d36742","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"faa8fc96dffc7dc92bd31fc3bb5de87aaacbeffc81623583af7ad43109d36742","first_computed_at":"2026-07-05T10:58:15.285529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:15.285529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AMmfD3vOr7L7PmO5OdO7upM3y4hk8UtFhOkRen8xYphmF1qrGt+aoBDge3i/mAKL7/dfeyY+Jv/JI/SHgYQbCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:15.286078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06869","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a50a32bb53b52e27217014c27f2b3e177f40fbbf2f8edd03d056b9e90405e347","sha256:7c19c13c8b677ee99f9a5b3f9dbcd592b663072b9d70edceaf78f7c7c2a64d86"],"state_sha256":"c9a70aa97051cbcc75a2167cd03b5ae9a6d018380e049ef445cfca7301104f30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"neaE49HAreB9xIdGXUxmVaRxGelZks6S9LwR/RxFoD4iAGVTUynKyyMhuLwjUWc0alqS2Lo16FR/KReuCVjAAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:13:23.502049Z","bundle_sha256":"8f333da00bebff4896a2afbb2f79cb5c86583820778acab135ef435e1eb34ec4"}}