{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ASEKCBTDOQZKVX2FPOB6IR6NEH","short_pith_number":"pith:ASEKCBTD","canonical_record":{"source":{"id":"2403.08632","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-13T15:46:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e81c8f84d35bfab99db244171b0eba26c22c1a9ba26f56ee82b5e95a7a437d71","abstract_canon_sha256":"7b4e4b0b225ac85e2bf0146e77411c07fcaeb2d4422cbc8bed55b1591a45b3fb"},"schema_version":"1.0"},"canonical_sha256":"0488a106637432aadf457b83e447cd21f01b074bde442b645d6eaf5fd9c81988","source":{"kind":"arxiv","id":"2403.08632","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.08632","created_at":"2026-07-05T10:22:44Z"},{"alias_kind":"arxiv_version","alias_value":"2403.08632v2","created_at":"2026-07-05T10:22:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08632","created_at":"2026-07-05T10:22:44Z"},{"alias_kind":"pith_short_12","alias_value":"ASEKCBTDOQZK","created_at":"2026-07-05T10:22:44Z"},{"alias_kind":"pith_short_16","alias_value":"ASEKCBTDOQZKVX2F","created_at":"2026-07-05T10:22:44Z"},{"alias_kind":"pith_short_8","alias_value":"ASEKCBTD","created_at":"2026-07-05T10:22:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ASEKCBTDOQZKVX2FPOB6IR6NEH","target":"record","payload":{"canonical_record":{"source":{"id":"2403.08632","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-13T15:46:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e81c8f84d35bfab99db244171b0eba26c22c1a9ba26f56ee82b5e95a7a437d71","abstract_canon_sha256":"7b4e4b0b225ac85e2bf0146e77411c07fcaeb2d4422cbc8bed55b1591a45b3fb"},"schema_version":"1.0"},"canonical_sha256":"0488a106637432aadf457b83e447cd21f01b074bde442b645d6eaf5fd9c81988","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:44.788067Z","signature_b64":"Ws0wrXeorCdXVQtkVEiuLONn6RedDo3enoCOZfhurLSKA7tnBXr/MVQgqEdqrZQpUHg6B6cK2B2HAiRrTg9yCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0488a106637432aadf457b83e447cd21f01b074bde442b645d6eaf5fd9c81988","last_reissued_at":"2026-07-05T10:22:44.787330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:44.787330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.08632","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zn+SRgollI9/a8t7ZCbVk1nTWrvUH3bmRT+hyji5tElK1udES/6Bbri9CvRRbUys8EuEDkmJyBnWAA5UCjWUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:57:18.300418Z"},"content_sha256":"8457e8b92df32fba7ad75a14c7e9284bc0d8f9506fa737758c0a4cd4459c15ae","schema_version":"1.0","event_id":"sha256:8457e8b92df32fba7ad75a14c7e9284bc0d8f9506fa737758c0a4cd4459c15ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ASEKCBTDOQZKVX2FPOB6IR6NEH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Decade's Battle on Dataset Bias: Are We There Yet?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kaiming He, Zhuang Liu","submitted_at":"2024-03-13T15:46:37Z","abstract_excerpt":"We revisit the \"dataset classification\" experiment suggested by Torralba & Efros (2011) a decade ago, in the new era with large-scale, diverse, and hopefully less biased datasets as well as more capable neural network architectures. Surprisingly, we observe that modern neural networks can achieve excellent accuracy in classifying which dataset an image is from: e.g., we report 84.7% accuracy on held-out validation data for the three-way classification problem consisting of the YFCC, CC, and DataComp datasets. Our further experiments show that such a dataset classifier could learn semantic feat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08632","kind":"arxiv","version":2},"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/2403.08632/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":"2026-07-05T10:22:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OpWctPpu2qhobsCZIYGnjuq8nPf9avZdug7CwyFMPbg+9NrtoI/PHjof32za/9RzecvPzDyZPpt6SMWlHlTpAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:57:18.301419Z"},"content_sha256":"f90a107fbe0422e497475943dd2d7757438ccfe0ab64c546d98410a9ceab8e55","schema_version":"1.0","event_id":"sha256:f90a107fbe0422e497475943dd2d7757438ccfe0ab64c546d98410a9ceab8e55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ASEKCBTDOQZKVX2FPOB6IR6NEH/bundle.json","state_url":"https://pith.science/pith/ASEKCBTDOQZKVX2FPOB6IR6NEH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ASEKCBTDOQZKVX2FPOB6IR6NEH/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":"2026-08-04T22:57:18Z","links":{"resolver":"https://pith.science/pith/ASEKCBTDOQZKVX2FPOB6IR6NEH","bundle":"https://pith.science/pith/ASEKCBTDOQZKVX2FPOB6IR6NEH/bundle.json","state":"https://pith.science/pith/ASEKCBTDOQZKVX2FPOB6IR6NEH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ASEKCBTDOQZKVX2FPOB6IR6NEH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ASEKCBTDOQZKVX2FPOB6IR6NEH","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":"7b4e4b0b225ac85e2bf0146e77411c07fcaeb2d4422cbc8bed55b1591a45b3fb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-13T15:46:37Z","title_canon_sha256":"e81c8f84d35bfab99db244171b0eba26c22c1a9ba26f56ee82b5e95a7a437d71"},"schema_version":"1.0","source":{"id":"2403.08632","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.08632","created_at":"2026-07-05T10:22:44Z"},{"alias_kind":"arxiv_version","alias_value":"2403.08632v2","created_at":"2026-07-05T10:22:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08632","created_at":"2026-07-05T10:22:44Z"},{"alias_kind":"pith_short_12","alias_value":"ASEKCBTDOQZK","created_at":"2026-07-05T10:22:44Z"},{"alias_kind":"pith_short_16","alias_value":"ASEKCBTDOQZKVX2F","created_at":"2026-07-05T10:22:44Z"},{"alias_kind":"pith_short_8","alias_value":"ASEKCBTD","created_at":"2026-07-05T10:22:44Z"}],"graph_snapshots":[{"event_id":"sha256:f90a107fbe0422e497475943dd2d7757438ccfe0ab64c546d98410a9ceab8e55","target":"graph","created_at":"2026-07-05T10:22:44Z","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/2403.08632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We revisit the \"dataset classification\" experiment suggested by Torralba & Efros (2011) a decade ago, in the new era with large-scale, diverse, and hopefully less biased datasets as well as more capable neural network architectures. Surprisingly, we observe that modern neural networks can achieve excellent accuracy in classifying which dataset an image is from: e.g., we report 84.7% accuracy on held-out validation data for the three-way classification problem consisting of the YFCC, CC, and DataComp datasets. Our further experiments show that such a dataset classifier could learn semantic feat","authors_text":"Kaiming He, Zhuang Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-13T15:46:37Z","title":"A Decade's Battle on Dataset Bias: Are We There Yet?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08632","kind":"arxiv","version":2},"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":"sha256:8457e8b92df32fba7ad75a14c7e9284bc0d8f9506fa737758c0a4cd4459c15ae","target":"record","created_at":"2026-07-05T10:22:44Z","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":"7b4e4b0b225ac85e2bf0146e77411c07fcaeb2d4422cbc8bed55b1591a45b3fb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-13T15:46:37Z","title_canon_sha256":"e81c8f84d35bfab99db244171b0eba26c22c1a9ba26f56ee82b5e95a7a437d71"},"schema_version":"1.0","source":{"id":"2403.08632","kind":"arxiv","version":2}},"canonical_sha256":"0488a106637432aadf457b83e447cd21f01b074bde442b645d6eaf5fd9c81988","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0488a106637432aadf457b83e447cd21f01b074bde442b645d6eaf5fd9c81988","first_computed_at":"2026-07-05T10:22:44.787330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:44.787330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ws0wrXeorCdXVQtkVEiuLONn6RedDo3enoCOZfhurLSKA7tnBXr/MVQgqEdqrZQpUHg6B6cK2B2HAiRrTg9yCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:44.788067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.08632","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8457e8b92df32fba7ad75a14c7e9284bc0d8f9506fa737758c0a4cd4459c15ae","sha256:f90a107fbe0422e497475943dd2d7757438ccfe0ab64c546d98410a9ceab8e55"],"state_sha256":"15300be05415c9e5b7664d18faa7c6cbe0d6382a9973e85bc637f255d8758f49"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ti6IFkndx7KDE09lwLMHiXSf+vclVMbJfjRDo145tBOTpKkpBoUyGQtUungsdSmSN8u2H8bMPbb82z8P1AMGDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:57:18.306821Z","bundle_sha256":"00b5d0170a34e68042eccc498d406f3ff5bb4ee5066ce3bf9ff09597b8c4d3cd"}}