{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZWOD473FQ4PYAXHT5IXBLC4ZPH","short_pith_number":"pith:ZWOD473F","schema_version":"1.0","canonical_sha256":"cd9c3e7f65871f805cf3ea2e158b9979cc810526264c858a3376d7dcc8f747e1","source":{"kind":"arxiv","id":"1807.00517","version":1},"attestation_state":"computed","paper":{"title":"Women also Snowboard: Overcoming Bias in Captioning Models (Extended Abstract)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Kate Saenko, Kaylee Burns, Lisa Anne Hendricks, Trevor Darrell","submitted_at":"2018-07-02T08:15:11Z","abstract_excerpt":"Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image captioning models tend to exaggerate biases present in training data. This can lead to incorrect captions in domains where unbiased captions are desired, or required, due to over reliance on the learned prior and image context. We investigate generation of gender specific caption words (e.g. man, woman) based on the person's appearance or the image context. We introduce a new Equalizer model that ensures equal gender "},"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":"1807.00517","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-02T08:15:11Z","cross_cats_sorted":[],"title_canon_sha256":"3e372db117f3951ca4bd587dc78c1eedd6358d46def8c16c32899f8bd5b42d71","abstract_canon_sha256":"438a9ce74504faf92f0af0f1d2baf26783f757f0bd33a51b8b58d2963f8ea5ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:52.328411Z","signature_b64":"XzUkDvtey/7Dht1m8BbE2PHUrka9QamyCzR0dhICCYbeaFR+rVZ49DtndMrRqBCKH2S+igOH/EYrDaEvwyRPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd9c3e7f65871f805cf3ea2e158b9979cc810526264c858a3376d7dcc8f747e1","last_reissued_at":"2026-05-18T00:11:52.327722Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:52.327722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Women also Snowboard: Overcoming Bias in Captioning Models (Extended Abstract)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anna Rohrbach, Kate Saenko, Kaylee Burns, Lisa Anne Hendricks, Trevor Darrell","submitted_at":"2018-07-02T08:15:11Z","abstract_excerpt":"Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image captioning models tend to exaggerate biases present in training data. This can lead to incorrect captions in domains where unbiased captions are desired, or required, due to over reliance on the learned prior and image context. We investigate generation of gender specific caption words (e.g. man, woman) based on the person's appearance or the image context. We introduce a new Equalizer model that ensures equal gender "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00517","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":""},"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":"1807.00517","created_at":"2026-05-18T00:11:52.327818+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.00517v1","created_at":"2026-05-18T00:11:52.327818+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00517","created_at":"2026-05-18T00:11:52.327818+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWOD473FQ4PY","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWOD473FQ4PYAXHT","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWOD473F","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWOD473FQ4PYAXHT5IXBLC4ZPH","json":"https://pith.science/pith/ZWOD473FQ4PYAXHT5IXBLC4ZPH.json","graph_json":"https://pith.science/api/pith-number/ZWOD473FQ4PYAXHT5IXBLC4ZPH/graph.json","events_json":"https://pith.science/api/pith-number/ZWOD473FQ4PYAXHT5IXBLC4ZPH/events.json","paper":"https://pith.science/paper/ZWOD473F"},"agent_actions":{"view_html":"https://pith.science/pith/ZWOD473FQ4PYAXHT5IXBLC4ZPH","download_json":"https://pith.science/pith/ZWOD473FQ4PYAXHT5IXBLC4ZPH.json","view_paper":"https://pith.science/paper/ZWOD473F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.00517&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWOD473FQ4PYAXHT5IXBLC4ZPH/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWOD473FQ4PYAXHT5IXBLC4ZPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWOD473FQ4PYAXHT5IXBLC4ZPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWOD473FQ4PYAXHT5IXBLC4ZPH/action/storage_attestation","attest_author":"https://pith.science/pith/ZWOD473FQ4PYAXHT5IXBLC4ZPH/action/author_attestation","sign_citation":"https://pith.science/pith/ZWOD473FQ4PYAXHT5IXBLC4ZPH/action/citation_signature","submit_replication":"https://pith.science/pith/ZWOD473FQ4PYAXHT5IXBLC4ZPH/action/replication_record"}},"created_at":"2026-05-18T00:11:52.327818+00:00","updated_at":"2026-05-18T00:11:52.327818+00:00"}