{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QY2EGDAYQJDTEFV3A2IXCHAOJD","short_pith_number":"pith:QY2EGDAY","schema_version":"1.0","canonical_sha256":"8634430c1882473216bb0691711c0e48ef69a306f13c9e71d0df7884b470a8f5","source":{"kind":"arxiv","id":"2412.01876","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.01876","created_at":"2026-07-05T09:43:40.269553+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01876v1","created_at":"2026-07-05T09:43:40.269553+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01876","created_at":"2026-07-05T09:43:40.269553+00:00"},{"alias_kind":"pith_short_12","alias_value":"QY2EGDAYQJDT","created_at":"2026-07-05T09:43:40.269553+00:00"},{"alias_kind":"pith_short_16","alias_value":"QY2EGDAYQJDTEFV3","created_at":"2026-07-05T09:43:40.269553+00:00"},{"alias_kind":"pith_short_8","alias_value":"QY2EGDAY","created_at":"2026-07-05T09:43:40.269553+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08979","citing_title":"PRISM: Reducing Spurious Implicit Biases in Vision-Language Models with LLM-Guided Embedding Projection","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD","json":"https://pith.science/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD.json","graph_json":"https://pith.science/api/pith-number/QY2EGDAYQJDTEFV3A2IXCHAOJD/graph.json","events_json":"https://pith.science/api/pith-number/QY2EGDAYQJDTEFV3A2IXCHAOJD/events.json","paper":"https://pith.science/paper/QY2EGDAY"},"agent_actions":{"view_html":"https://pith.science/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD","download_json":"https://pith.science/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD.json","view_paper":"https://pith.science/paper/QY2EGDAY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01876&json=true","fetch_graph":"https://pith.science/api/pith-number/QY2EGDAYQJDTEFV3A2IXCHAOJD/graph.json","fetch_events":"https://pith.science/api/pith-number/QY2EGDAYQJDTEFV3A2IXCHAOJD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD/action/storage_attestation","attest_author":"https://pith.science/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD/action/author_attestation","sign_citation":"https://pith.science/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD/action/citation_signature","submit_replication":"https://pith.science/pith/QY2EGDAYQJDTEFV3A2IXCHAOJD/action/replication_record"}},"created_at":"2026-07-05T09:43:40.269553+00:00","updated_at":"2026-07-05T09:43:40.269553+00:00"}