{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EFVVAJRIXAUOEXXJNPYPHSXFAU","short_pith_number":"pith:EFVVAJRI","schema_version":"1.0","canonical_sha256":"216b502628b828e25ee96bf0f3cae5052a871037b811e05316322c6653166560","source":{"kind":"arxiv","id":"1912.00578","version":1},"attestation_state":"computed","paper":{"title":"Exposing and Correcting the Gender Bias in Image Captioning Datasets and Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Forsyth, Shruti Bhargava","submitted_at":"2019-12-02T04:14:39Z","abstract_excerpt":"The task of image captioning implicitly involves gender identification. However, due to the gender bias in data, gender identification by an image captioning model suffers. Also, the gender-activity bias, owing to the word-by-word prediction, influences other words in the caption prediction, resulting in the well-known problem of label bias. In this work, we investigate gender bias in the COCO captioning dataset and show that it engenders not only from the statistical distribution of genders with contexts but also from the flawed annotation by the human annotators. We look at the issues create"},"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":"1912.00578","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-02T04:14:39Z","cross_cats_sorted":[],"title_canon_sha256":"221262d5b4c556cb1165ebf769282333244d07048178b9c44fbb11cd7aa4c0b0","abstract_canon_sha256":"2bc03bbbe827efd9a3873d47a7730df9ad6ac59e6112b5785b1272b959c35b05"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:15.010644Z","signature_b64":"eL768VsUG0O4LidxdKnOo47E2eFZdQ/mh7RmgE1Dcs1n6YVnJYb6HZjsWa1mxEqJO4FGEjkc2FhGXZp8xepJAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"216b502628b828e25ee96bf0f3cae5052a871037b811e05316322c6653166560","last_reissued_at":"2026-07-05T00:23:15.010261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:15.010261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exposing and Correcting the Gender Bias in Image Captioning Datasets and Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Forsyth, Shruti Bhargava","submitted_at":"2019-12-02T04:14:39Z","abstract_excerpt":"The task of image captioning implicitly involves gender identification. However, due to the gender bias in data, gender identification by an image captioning model suffers. Also, the gender-activity bias, owing to the word-by-word prediction, influences other words in the caption prediction, resulting in the well-known problem of label bias. In this work, we investigate gender bias in the COCO captioning dataset and show that it engenders not only from the statistical distribution of genders with contexts but also from the flawed annotation by the human annotators. We look at the issues create"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.00578","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/1912.00578/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":"1912.00578","created_at":"2026-07-05T00:23:15.010339+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.00578v1","created_at":"2026-07-05T00:23:15.010339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.00578","created_at":"2026-07-05T00:23:15.010339+00:00"},{"alias_kind":"pith_short_12","alias_value":"EFVVAJRIXAUO","created_at":"2026-07-05T00:23:15.010339+00:00"},{"alias_kind":"pith_short_16","alias_value":"EFVVAJRIXAUOEXXJ","created_at":"2026-07-05T00:23:15.010339+00:00"},{"alias_kind":"pith_short_8","alias_value":"EFVVAJRI","created_at":"2026-07-05T00:23:15.010339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17505","citing_title":"More is Less? A Simulation-Based Approach to Dynamic Interactions between Biases in Multimodal Models","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EFVVAJRIXAUOEXXJNPYPHSXFAU","json":"https://pith.science/pith/EFVVAJRIXAUOEXXJNPYPHSXFAU.json","graph_json":"https://pith.science/api/pith-number/EFVVAJRIXAUOEXXJNPYPHSXFAU/graph.json","events_json":"https://pith.science/api/pith-number/EFVVAJRIXAUOEXXJNPYPHSXFAU/events.json","paper":"https://pith.science/paper/EFVVAJRI"},"agent_actions":{"view_html":"https://pith.science/pith/EFVVAJRIXAUOEXXJNPYPHSXFAU","download_json":"https://pith.science/pith/EFVVAJRIXAUOEXXJNPYPHSXFAU.json","view_paper":"https://pith.science/paper/EFVVAJRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.00578&json=true","fetch_graph":"https://pith.science/api/pith-number/EFVVAJRIXAUOEXXJNPYPHSXFAU/graph.json","fetch_events":"https://pith.science/api/pith-number/EFVVAJRIXAUOEXXJNPYPHSXFAU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EFVVAJRIXAUOEXXJNPYPHSXFAU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EFVVAJRIXAUOEXXJNPYPHSXFAU/action/storage_attestation","attest_author":"https://pith.science/pith/EFVVAJRIXAUOEXXJNPYPHSXFAU/action/author_attestation","sign_citation":"https://pith.science/pith/EFVVAJRIXAUOEXXJNPYPHSXFAU/action/citation_signature","submit_replication":"https://pith.science/pith/EFVVAJRIXAUOEXXJNPYPHSXFAU/action/replication_record"}},"created_at":"2026-07-05T00:23:15.010339+00:00","updated_at":"2026-07-05T00:23:15.010339+00:00"}