{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MVTJV3JHQLEOFVQAFI5Q3JZF5B","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0654281d1c90c1a17b8da3d553f514e780437c627f8152328c4c49a3c8f8762c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T00:02:32Z","title_canon_sha256":"2206e5c15d5f2a405102ecb0b86c5a1266ad686e5826a0e498cdd67508ea3075"},"schema_version":"1.0","source":{"id":"2104.08666","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08666","created_at":"2026-07-05T04:24:55Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08666v2","created_at":"2026-07-05T04:24:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08666","created_at":"2026-07-05T04:24:55Z"},{"alias_kind":"pith_short_12","alias_value":"MVTJV3JHQLEO","created_at":"2026-07-05T04:24:55Z"},{"alias_kind":"pith_short_16","alias_value":"MVTJV3JHQLEOFVQA","created_at":"2026-07-05T04:24:55Z"},{"alias_kind":"pith_short_8","alias_value":"MVTJV3JH","created_at":"2026-07-05T04:24:55Z"}],"graph_snapshots":[{"event_id":"sha256:fe2ce3377e843f87b225394e906398ddec6455b5aec42bc63b91dae481990afa","target":"graph","created_at":"2026-07-05T04:24:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2104.08666/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Numerous works have analyzed biases in vision and pre-trained language models individually - however, less attention has been paid to how these biases interact in multimodal settings. This work extends text-based bias analysis methods to investigate multimodal language models, and analyzes intra- and inter-modality associations and biases learned by these models. Specifically, we demonstrate that VL-BERT (Su et al., 2020) exhibits gender biases, often preferring to reinforce a stereotype over faithfully describing the visual scene. We demonstrate these findings on a controlled case-study and e","authors_text":"Tejas Srinivasan, Yonatan Bisk","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T00:02:32Z","title":"Worst of Both Worlds: Biases Compound in Pre-trained Vision-and-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08666","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fba4ddc4d1b3b84227ba96bf261619353b0ff630d76475164d19e1dcc1dc4db5","target":"record","created_at":"2026-07-05T04:24:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0654281d1c90c1a17b8da3d553f514e780437c627f8152328c4c49a3c8f8762c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-18T00:02:32Z","title_canon_sha256":"2206e5c15d5f2a405102ecb0b86c5a1266ad686e5826a0e498cdd67508ea3075"},"schema_version":"1.0","source":{"id":"2104.08666","kind":"arxiv","version":2}},"canonical_sha256":"65669aed2782c8e2d6002a3b0da725e850606f71b375d41cd94d39c73fa6930a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65669aed2782c8e2d6002a3b0da725e850606f71b375d41cd94d39c73fa6930a","first_computed_at":"2026-07-05T04:24:55.199238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:55.199238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FLGRnSDP3CL057n9xEq/X4h27jREU8/HcJO0fKc9Tkbso3jWb4uVwrwTeDSd7N0EcJl2YXSh0n0AdyM6AkDQBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:55.199698Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.08666","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fba4ddc4d1b3b84227ba96bf261619353b0ff630d76475164d19e1dcc1dc4db5","sha256:fe2ce3377e843f87b225394e906398ddec6455b5aec42bc63b91dae481990afa"],"state_sha256":"2377d75fa2f9e4b42556c3556364eb2b97212f89f07ad07714052e8e0634f73e"}