{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7BAZFFWBAYYAJMMFDWP65P3FP4","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":"e567b5d651182836f5852983f655ce735fc79be8236b3f1ed7052fe074ee0654","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-01T19:41:28Z","title_canon_sha256":"f8527f14760862e44c7775da97b019cd996e9b020e7e27989b91922d60e13dc3"},"schema_version":"1.0","source":{"id":"2411.00997","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00997","created_at":"2026-07-05T09:29:53Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00997v1","created_at":"2026-07-05T09:29:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00997","created_at":"2026-07-05T09:29:53Z"},{"alias_kind":"pith_short_12","alias_value":"7BAZFFWBAYYA","created_at":"2026-07-05T09:29:53Z"},{"alias_kind":"pith_short_16","alias_value":"7BAZFFWBAYYAJMMF","created_at":"2026-07-05T09:29:53Z"},{"alias_kind":"pith_short_8","alias_value":"7BAZFFWB","created_at":"2026-07-05T09:29:53Z"}],"graph_snapshots":[{"event_id":"sha256:a5c7199e02c75fd32e1bdaa2b495f775e5f9f5738cc83944484d3c12c8f90250","target":"graph","created_at":"2026-07-05T09:29:53Z","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/2411.00997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models, like CLIP (Contrastive Language Image Pretraining), are becoming increasingly popular for a wide range of multimodal retrieval tasks. However, prior work has shown that large language and deep vision models can learn historical biases contained in their training sets, leading to perpetuation of stereotypes and potential downstream harm. In this work, we conduct a systematic analysis of the social biases that are present in CLIP, with a focus on the interaction between image and text modalities. We first propose a taxonomy of social biases called So-B-IT, which contains ","authors_text":"Haoran Zhang, Kimia Hamidieh, Marzyeh Ghassemi, Thomas Hartvigsen, Walter Gerych","cross_cats":["cs.AI","cs.CL","cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-01T19:41:28Z","title":"Identifying Implicit Social Biases in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00997","kind":"arxiv","version":1},"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:fedf00ec909391e7dd749aa2a9b762cc2a9d1d1d3a658f8c52e5420debbec5e9","target":"record","created_at":"2026-07-05T09:29:53Z","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":"e567b5d651182836f5852983f655ce735fc79be8236b3f1ed7052fe074ee0654","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-01T19:41:28Z","title_canon_sha256":"f8527f14760862e44c7775da97b019cd996e9b020e7e27989b91922d60e13dc3"},"schema_version":"1.0","source":{"id":"2411.00997","kind":"arxiv","version":1}},"canonical_sha256":"f8419296c1063004b1851d9feebf657f243af57c01dad858259715cc442e7c8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8419296c1063004b1851d9feebf657f243af57c01dad858259715cc442e7c8d","first_computed_at":"2026-07-05T09:29:53.673642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:53.673642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PREtJybaMmpucz1D3t2e/7/QzHcTxUXNvckUwEZNsRuN08SZt1aYdZqvPikCsiNGmTNmu008fuS9t3T7z0BHCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:53.674070Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.00997","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fedf00ec909391e7dd749aa2a9b762cc2a9d1d1d3a658f8c52e5420debbec5e9","sha256:a5c7199e02c75fd32e1bdaa2b495f775e5f9f5738cc83944484d3c12c8f90250"],"state_sha256":"d36236d6c90533379cfc821b971ba86464c3f1f1db55cf0ab6ebe3f48b9a1c37"}