{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QY2EGDAYQJDTEFV3A2IXCHAOJD","short_pith_number":"pith:QY2EGDAY","canonical_record":{"source":{"id":"2412.01876","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T18:56:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6d076540fd34faddb7efc8f6e470938f17e1fc692f75b7ac7e437f6507b33599","abstract_canon_sha256":"85090137839eab294f74ce05f411263bb7d141afc5333c3dc072dc62fe61d5e2"},"schema_version":"1.0"},"canonical_sha256":"8634430c1882473216bb0691711c0e48ef69a306f13c9e71d0df7884b470a8f5","source":{"kind":"arxiv","id":"2412.01876","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01876","created_at":"2026-07-05T09:43:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01876v1","created_at":"2026-07-05T09:43:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01876","created_at":"2026-07-05T09:43:40Z"},{"alias_kind":"pith_short_12","alias_value":"QY2EGDAYQJDT","created_at":"2026-07-05T09:43:40Z"},{"alias_kind":"pith_short_16","alias_value":"QY2EGDAYQJDTEFV3","created_at":"2026-07-05T09:43:40Z"},{"alias_kind":"pith_short_8","alias_value":"QY2EGDAY","created_at":"2026-07-05T09:43:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QY2EGDAYQJDTEFV3A2IXCHAOJD","target":"record","payload":{"canonical_record":{"source":{"id":"2412.01876","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T18:56:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6d076540fd34faddb7efc8f6e470938f17e1fc692f75b7ac7e437f6507b33599","abstract_canon_sha256":"85090137839eab294f74ce05f411263bb7d141afc5333c3dc072dc62fe61d5e2"},"schema_version":"1.0"},"canonical_sha256":"8634430c1882473216bb0691711c0e48ef69a306f13c9e71d0df7884b470a8f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:40.269976Z","signature_b64":"rzFAje0wzgkQAyzYXbCZjwUfLQtZ3o+Uk3sVA934KyN1JvSiIo4wGHQgEtZpeKWXVTveh2mkEL5ig4zImG26BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8634430c1882473216bb0691711c0e48ef69a306f13c9e71d0df7884b470a8f5","last_reissued_at":"2026-07-05T09:43:40.269497Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:40.269497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.01876","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":"2026-07-05T09:43:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/owu3u2HMTw9h0VgW8uvi37QEaKPPgo3ENm1gV/2OPhSvIeAD6JMwMGuiVOv5Fg1xjGjSwAwKhKJAv+cLD0xCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:08:22.277809Z"},"content_sha256":"327af46c60eee9ca94fd3ef5ca0dfcc53a786c57be70496215aa42db2b9cf044","schema_version":"1.0","event_id":"sha256:327af46c60eee9ca94fd3ef5ca0dfcc53a786c57be70496215aa42db2b9cf044"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QY2EGDAYQJDTEFV3A2IXCHAOJD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Bias in Large-Scale Visual Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Boya Zeng, Yida Yin, Zhuang Liu","submitted_at":"2024-12-02T18:56:52Z","abstract_excerpt":"A recent study has shown that large-scale visual datasets are very biased: they can be easily classified by modern neural networks. However, the concrete forms of bias among these datasets remain unclear. In this study, we propose a framework to identify the unique visual attributes distinguishing these datasets. Our approach applies various transformations to extract semantic, structural, boundary, color, and frequency information from datasets, and assess how much each type of information reflects their bias. We further decompose their semantic bias with object-level analysis, and leverage n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01876","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/2412.01876/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":"2026-07-05T09:43:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PSHl5xGXkuPleA/DUb1x9xg+oPaK0ZgVkeas497KZ7ch6iR1OwPtYrf6+YHngESOdEKivQUW3hgP6o5JweroBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:08:22.278321Z"},"content_sha256":"ef0bece8570d34d394439873d7905ec0bb783303f5b2d4d6485d327af3fef5a6","schema_version":"1.0","event_id":"sha256:ef0bece8570d34d394439873d7905ec0bb783303f5b2d4d6485d327af3fef5a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD/bundle.json","state_url":"https://pith.science/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD/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":"2026-08-08T12:08:22Z","links":{"resolver":"https://pith.science/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD","bundle":"https://pith.science/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD/bundle.json","state":"https://pith.science/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QY2EGDAYQJDTEFV3A2IXCHAOJD","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":"85090137839eab294f74ce05f411263bb7d141afc5333c3dc072dc62fe61d5e2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T18:56:52Z","title_canon_sha256":"6d076540fd34faddb7efc8f6e470938f17e1fc692f75b7ac7e437f6507b33599"},"schema_version":"1.0","source":{"id":"2412.01876","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01876","created_at":"2026-07-05T09:43:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01876v1","created_at":"2026-07-05T09:43:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01876","created_at":"2026-07-05T09:43:40Z"},{"alias_kind":"pith_short_12","alias_value":"QY2EGDAYQJDT","created_at":"2026-07-05T09:43:40Z"},{"alias_kind":"pith_short_16","alias_value":"QY2EGDAYQJDTEFV3","created_at":"2026-07-05T09:43:40Z"},{"alias_kind":"pith_short_8","alias_value":"QY2EGDAY","created_at":"2026-07-05T09:43:40Z"}],"graph_snapshots":[{"event_id":"sha256:ef0bece8570d34d394439873d7905ec0bb783303f5b2d4d6485d327af3fef5a6","target":"graph","created_at":"2026-07-05T09:43:40Z","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/2412.01876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A recent study has shown that large-scale visual datasets are very biased: they can be easily classified by modern neural networks. However, the concrete forms of bias among these datasets remain unclear. In this study, we propose a framework to identify the unique visual attributes distinguishing these datasets. Our approach applies various transformations to extract semantic, structural, boundary, color, and frequency information from datasets, and assess how much each type of information reflects their bias. We further decompose their semantic bias with object-level analysis, and leverage n","authors_text":"Boya Zeng, Yida Yin, Zhuang Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T18:56:52Z","title":"Understanding Bias in Large-Scale Visual Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01876","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":"sha256:327af46c60eee9ca94fd3ef5ca0dfcc53a786c57be70496215aa42db2b9cf044","target":"record","created_at":"2026-07-05T09:43:40Z","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":"85090137839eab294f74ce05f411263bb7d141afc5333c3dc072dc62fe61d5e2","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T18:56:52Z","title_canon_sha256":"6d076540fd34faddb7efc8f6e470938f17e1fc692f75b7ac7e437f6507b33599"},"schema_version":"1.0","source":{"id":"2412.01876","kind":"arxiv","version":1}},"canonical_sha256":"8634430c1882473216bb0691711c0e48ef69a306f13c9e71d0df7884b470a8f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8634430c1882473216bb0691711c0e48ef69a306f13c9e71d0df7884b470a8f5","first_computed_at":"2026-07-05T09:43:40.269497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:43:40.269497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rzFAje0wzgkQAyzYXbCZjwUfLQtZ3o+Uk3sVA934KyN1JvSiIo4wGHQgEtZpeKWXVTveh2mkEL5ig4zImG26BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:43:40.269976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01876","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:327af46c60eee9ca94fd3ef5ca0dfcc53a786c57be70496215aa42db2b9cf044","sha256:ef0bece8570d34d394439873d7905ec0bb783303f5b2d4d6485d327af3fef5a6"],"state_sha256":"8bc0b32b2938b11ee1fd60a945f219af9e31490fb1f55b7023b59e5986edf2d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1GIe7zgdqLq3JUuN7Mh9mKagN6PqXObWJw/u677haFfpLv5qIW0mbL0x9TbdELld9u/s+Yik2ii4hNp4t1+VAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:08:22.286125Z","bundle_sha256":"905b374c5088c12bb036007abecfb3ad1ac06a0d1b29288e837631e1957306ab"}}