{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AKFAPELQI2GJ5BE6D75H3BTW2H","short_pith_number":"pith:AKFAPELQ","schema_version":"1.0","canonical_sha256":"028a079170468c9e849e1ffa7d8676d1d6e1380757a54fd84bf4d026a07fa47a","source":{"kind":"arxiv","id":"2006.16923","version":2},"attestation_state":"computed","paper":{"title":"Large image datasets: A pyrrhic win for computer vision?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.ML"],"primary_cat":"cs.CY","authors_text":"Abeba Birhane, Vinay Uday Prabhu","submitted_at":"2020-06-24T06:41:32Z","abstract_excerpt":"In this paper we investigate problematic practices and consequences of large scale vision datasets. We examine broad issues such as the question of consent and justice as well as specific concerns such as the inclusion of verifiably pornographic images in datasets. Taking the ImageNet-ILSVRC-2012 dataset as an example, we perform a cross-sectional model-based quantitative census covering factors such as age, gender, NSFW content scoring, class-wise accuracy, human-cardinality-analysis, and the semanticity of the image class information in order to statistically investigate the extent and subtl"},"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":"2006.16923","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2020-06-24T06:41:32Z","cross_cats_sorted":["stat.AP","stat.ML"],"title_canon_sha256":"f12396927c15267fa7c1790322dd75bb98d75ed3043e99e3fa5bbc02e6e433c0","abstract_canon_sha256":"66e5c107f50ce65365271b597fa9e2085f3ea53ec234c0e262f0dcea385a088a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:21:49.054437Z","signature_b64":"WzFyesSeBCFnPWdZYW45bLmHdUT3q/CN9mylzROTt+mNkmHsz7DQXV1qSJHQPOFTNq7uFaxF7inCnnuD/CiKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"028a079170468c9e849e1ffa7d8676d1d6e1380757a54fd84bf4d026a07fa47a","last_reissued_at":"2026-07-05T01:21:49.053999Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:21:49.053999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large image datasets: A pyrrhic win for computer vision?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP","stat.ML"],"primary_cat":"cs.CY","authors_text":"Abeba Birhane, Vinay Uday Prabhu","submitted_at":"2020-06-24T06:41:32Z","abstract_excerpt":"In this paper we investigate problematic practices and consequences of large scale vision datasets. We examine broad issues such as the question of consent and justice as well as specific concerns such as the inclusion of verifiably pornographic images in datasets. Taking the ImageNet-ILSVRC-2012 dataset as an example, we perform a cross-sectional model-based quantitative census covering factors such as age, gender, NSFW content scoring, class-wise accuracy, human-cardinality-analysis, and the semanticity of the image class information in order to statistically investigate the extent and subtl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.16923","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/2006.16923/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":"2006.16923","created_at":"2026-07-05T01:21:49.054055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.16923v2","created_at":"2026-07-05T01:21:49.054055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.16923","created_at":"2026-07-05T01:21:49.054055+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKFAPELQI2GJ","created_at":"2026-07-05T01:21:49.054055+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKFAPELQI2GJ5BE6","created_at":"2026-07-05T01:21:49.054055+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKFAPELQ","created_at":"2026-07-05T01:21:49.054055+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.18347","citing_title":"Multilingual Training and Evaluation Resources for Vision-Language Models","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2606.09881","citing_title":"Toward Calibrated, Fair, and accurate Deepfake Detection","ref_index":251,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04759","citing_title":"How to Stop Playing Whack-a-Mole: Mapping the Ecosystem of Technologies Facilitating AI-Generated Non-Consensual Intimate Images","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2205.11487","citing_title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2101.00027","citing_title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18347","citing_title":"Multilingual Training and Evaluation Resources for Vision-Language Models","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AKFAPELQI2GJ5BE6D75H3BTW2H","json":"https://pith.science/pith/AKFAPELQI2GJ5BE6D75H3BTW2H.json","graph_json":"https://pith.science/api/pith-number/AKFAPELQI2GJ5BE6D75H3BTW2H/graph.json","events_json":"https://pith.science/api/pith-number/AKFAPELQI2GJ5BE6D75H3BTW2H/events.json","paper":"https://pith.science/paper/AKFAPELQ"},"agent_actions":{"view_html":"https://pith.science/pith/AKFAPELQI2GJ5BE6D75H3BTW2H","download_json":"https://pith.science/pith/AKFAPELQI2GJ5BE6D75H3BTW2H.json","view_paper":"https://pith.science/paper/AKFAPELQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.16923&json=true","fetch_graph":"https://pith.science/api/pith-number/AKFAPELQI2GJ5BE6D75H3BTW2H/graph.json","fetch_events":"https://pith.science/api/pith-number/AKFAPELQI2GJ5BE6D75H3BTW2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKFAPELQI2GJ5BE6D75H3BTW2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKFAPELQI2GJ5BE6D75H3BTW2H/action/storage_attestation","attest_author":"https://pith.science/pith/AKFAPELQI2GJ5BE6D75H3BTW2H/action/author_attestation","sign_citation":"https://pith.science/pith/AKFAPELQI2GJ5BE6D75H3BTW2H/action/citation_signature","submit_replication":"https://pith.science/pith/AKFAPELQI2GJ5BE6D75H3BTW2H/action/replication_record"}},"created_at":"2026-07-05T01:21:49.054055+00:00","updated_at":"2026-07-05T01:21:49.054055+00:00"}