{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QDOIQ7K7CABELKU2VBJ4MUY52K","short_pith_number":"pith:QDOIQ7K7","schema_version":"1.0","canonical_sha256":"80dc887d5f100245aa9aa853c6531dd2a6f56940e12084fc04eec7cccf186098","source":{"kind":"arxiv","id":"2107.07919","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Bias in Visual Datasets","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eirini Ntoutsi, Ioannis Kompatsiaris, Simone Fabbrizzi, Symeon Papadopoulos","submitted_at":"2021-07-16T14:16:52Z","abstract_excerpt":"Computer Vision (CV) has achieved remarkable results, outperforming humans in several tasks. Nonetheless, it may result in significant discrimination if not handled properly as CV systems highly depend on the data they are fed with and can learn and amplify biases within such data. Thus, the problems of understanding and discovering biases are of utmost importance. Yet, there is no comprehensive survey on bias in visual datasets. Hence, this work aims to: i) describe the biases that might manifest in visual datasets; ii) review the literature on methods for bias discovery and quantification in"},"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":"2107.07919","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-16T14:16:52Z","cross_cats_sorted":[],"title_canon_sha256":"1ec4b5f3de3fdeb3ed72f8f7d0bf5fa77cfcfc0a0d0a79238aed7d3a5db9c5b5","abstract_canon_sha256":"1bc495ca4091c17fc664e39032a7bbc5c8ebaaccbb44b18ee015eb0d04055db1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:13.002335Z","signature_b64":"XF/P8ejkIegO2Ya95xZSL2bgyRBH1PNS1XUwVnhkjjhqrCz1qBVhwcr5UacFOE2VzHXIbdr770afMR8LsBeEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80dc887d5f100245aa9aa853c6531dd2a6f56940e12084fc04eec7cccf186098","last_reissued_at":"2026-07-05T04:34:13.001869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:13.001869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Bias in Visual Datasets","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eirini Ntoutsi, Ioannis Kompatsiaris, Simone Fabbrizzi, Symeon Papadopoulos","submitted_at":"2021-07-16T14:16:52Z","abstract_excerpt":"Computer Vision (CV) has achieved remarkable results, outperforming humans in several tasks. Nonetheless, it may result in significant discrimination if not handled properly as CV systems highly depend on the data they are fed with and can learn and amplify biases within such data. Thus, the problems of understanding and discovering biases are of utmost importance. Yet, there is no comprehensive survey on bias in visual datasets. Hence, this work aims to: i) describe the biases that might manifest in visual datasets; ii) review the literature on methods for bias discovery and quantification in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07919","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/2107.07919/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":"2107.07919","created_at":"2026-07-05T04:34:13.001919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.07919v2","created_at":"2026-07-05T04:34:13.001919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07919","created_at":"2026-07-05T04:34:13.001919+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDOIQ7K7CABE","created_at":"2026-07-05T04:34:13.001919+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDOIQ7K7CABELKU2","created_at":"2026-07-05T04:34:13.001919+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDOIQ7K7","created_at":"2026-07-05T04:34:13.001919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2205.08809","citing_title":"Software Fairness: An Analysis and Survey","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QDOIQ7K7CABELKU2VBJ4MUY52K","json":"https://pith.science/pith/QDOIQ7K7CABELKU2VBJ4MUY52K.json","graph_json":"https://pith.science/api/pith-number/QDOIQ7K7CABELKU2VBJ4MUY52K/graph.json","events_json":"https://pith.science/api/pith-number/QDOIQ7K7CABELKU2VBJ4MUY52K/events.json","paper":"https://pith.science/paper/QDOIQ7K7"},"agent_actions":{"view_html":"https://pith.science/pith/QDOIQ7K7CABELKU2VBJ4MUY52K","download_json":"https://pith.science/pith/QDOIQ7K7CABELKU2VBJ4MUY52K.json","view_paper":"https://pith.science/paper/QDOIQ7K7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.07919&json=true","fetch_graph":"https://pith.science/api/pith-number/QDOIQ7K7CABELKU2VBJ4MUY52K/graph.json","fetch_events":"https://pith.science/api/pith-number/QDOIQ7K7CABELKU2VBJ4MUY52K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDOIQ7K7CABELKU2VBJ4MUY52K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDOIQ7K7CABELKU2VBJ4MUY52K/action/storage_attestation","attest_author":"https://pith.science/pith/QDOIQ7K7CABELKU2VBJ4MUY52K/action/author_attestation","sign_citation":"https://pith.science/pith/QDOIQ7K7CABELKU2VBJ4MUY52K/action/citation_signature","submit_replication":"https://pith.science/pith/QDOIQ7K7CABELKU2VBJ4MUY52K/action/replication_record"}},"created_at":"2026-07-05T04:34:13.001919+00:00","updated_at":"2026-07-05T04:34:13.001919+00:00"}