{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4ND6HOXNVXMASISQ5J6RKE2LNI","short_pith_number":"pith:4ND6HOXN","canonical_record":{"source":{"id":"2310.17530","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-26T16:19:19Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"29ddc170263e741f6fe5afc791495b22a86268fdd711ac663da009181a4c1ca8","abstract_canon_sha256":"3191e05b088cb957cbbc67cc1d6f67fe7319fb8f5ab8ab14dd717c97871bfe42"},"schema_version":"1.0"},"canonical_sha256":"e347e3baedadd8092250ea7d15134b6a3d87c76369fb0d05f882b6f433ba5458","source":{"kind":"arxiv","id":"2310.17530","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17530","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17530v1","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17530","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"4ND6HOXNVXMA","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"4ND6HOXNVXMASISQ","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"4ND6HOXN","created_at":"2026-07-05T07:05:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4ND6HOXNVXMASISQ5J6RKE2LNI","target":"record","payload":{"canonical_record":{"source":{"id":"2310.17530","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-26T16:19:19Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"29ddc170263e741f6fe5afc791495b22a86268fdd711ac663da009181a4c1ca8","abstract_canon_sha256":"3191e05b088cb957cbbc67cc1d6f67fe7319fb8f5ab8ab14dd717c97871bfe42"},"schema_version":"1.0"},"canonical_sha256":"e347e3baedadd8092250ea7d15134b6a3d87c76369fb0d05f882b6f433ba5458","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:35.731583Z","signature_b64":"ftL6chiz2wYVgr0eHiJrBZHmcGGvcpaHF9XraUOyhUTh5vxDr9dEWkv6tNGkzPsgQihnV6ZsJPVKnhA3Xi85AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e347e3baedadd8092250ea7d15134b6a3d87c76369fb0d05f882b6f433ba5458","last_reissued_at":"2026-07-05T07:05:35.731152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:35.731152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.17530","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:05:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eJhezua5PKUrDNhmOEvSVuVuV7EJzIx+jAW+5OQOufZmQDVRQSnvkI0y8DhIKCaw1GqDCkRlmyOW8wCjXHyIBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:59:49.572132Z"},"content_sha256":"75a5669c54dbdd7b2876bc5c437fe22a382bcfe7571997326f89991c0eefa847","schema_version":"1.0","event_id":"sha256:75a5669c54dbdd7b2876bc5c437fe22a382bcfe7571997326f89991c0eefa847"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4ND6HOXNVXMASISQ5J6RKE2LNI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Desmond Elliott, Emanuele Bugliarello, Laura Cabello, Stephanie Brandl","submitted_at":"2023-10-26T16:19:19Z","abstract_excerpt":"Pretrained machine learning models are known to perpetuate and even amplify existing biases in data, which can result in unfair outcomes that ultimately impact user experience. Therefore, it is crucial to understand the mechanisms behind those prejudicial biases to ensure that model performance does not result in discriminatory behaviour toward certain groups or populations. In this work, we define gender bias as our case study. We quantify bias amplification in pretraining and after fine-tuning on three families of vision-and-language models. We investigate the connection, if any, between the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17530","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/2310.17530/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:05:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o+sew+PX/FZIDwvxCBC6eVfSakTaOCpRDRQuaJ5cDD2SF/ZX8ypYdTOtxhcLa0HgKvXRbOMuMCkqvK+gPu6CAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:59:49.572630Z"},"content_sha256":"b84bbc49bc1c3968fff2a741063372aca33d792e8661ebd80e5cbd132a5eea3c","schema_version":"1.0","event_id":"sha256:b84bbc49bc1c3968fff2a741063372aca33d792e8661ebd80e5cbd132a5eea3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4ND6HOXNVXMASISQ5J6RKE2LNI/bundle.json","state_url":"https://pith.science/pith/4ND6HOXNVXMASISQ5J6RKE2LNI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4ND6HOXNVXMASISQ5J6RKE2LNI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T10:59:49Z","links":{"resolver":"https://pith.science/pith/4ND6HOXNVXMASISQ5J6RKE2LNI","bundle":"https://pith.science/pith/4ND6HOXNVXMASISQ5J6RKE2LNI/bundle.json","state":"https://pith.science/pith/4ND6HOXNVXMASISQ5J6RKE2LNI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4ND6HOXNVXMASISQ5J6RKE2LNI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4ND6HOXNVXMASISQ5J6RKE2LNI","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":"3191e05b088cb957cbbc67cc1d6f67fe7319fb8f5ab8ab14dd717c97871bfe42","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-26T16:19:19Z","title_canon_sha256":"29ddc170263e741f6fe5afc791495b22a86268fdd711ac663da009181a4c1ca8"},"schema_version":"1.0","source":{"id":"2310.17530","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17530","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17530v1","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17530","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"4ND6HOXNVXMA","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"4ND6HOXNVXMASISQ","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"4ND6HOXN","created_at":"2026-07-05T07:05:35Z"}],"graph_snapshots":[{"event_id":"sha256:b84bbc49bc1c3968fff2a741063372aca33d792e8661ebd80e5cbd132a5eea3c","target":"graph","created_at":"2026-07-05T07:05:35Z","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/2310.17530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained machine learning models are known to perpetuate and even amplify existing biases in data, which can result in unfair outcomes that ultimately impact user experience. Therefore, it is crucial to understand the mechanisms behind those prejudicial biases to ensure that model performance does not result in discriminatory behaviour toward certain groups or populations. In this work, we define gender bias as our case study. We quantify bias amplification in pretraining and after fine-tuning on three families of vision-and-language models. We investigate the connection, if any, between the","authors_text":"Desmond Elliott, Emanuele Bugliarello, Laura Cabello, Stephanie Brandl","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-26T16:19:19Z","title":"Evaluating Bias and Fairness in Gender-Neutral Pretrained Vision-and-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17530","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":"sha256:75a5669c54dbdd7b2876bc5c437fe22a382bcfe7571997326f89991c0eefa847","target":"record","created_at":"2026-07-05T07:05:35Z","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":"3191e05b088cb957cbbc67cc1d6f67fe7319fb8f5ab8ab14dd717c97871bfe42","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-26T16:19:19Z","title_canon_sha256":"29ddc170263e741f6fe5afc791495b22a86268fdd711ac663da009181a4c1ca8"},"schema_version":"1.0","source":{"id":"2310.17530","kind":"arxiv","version":1}},"canonical_sha256":"e347e3baedadd8092250ea7d15134b6a3d87c76369fb0d05f882b6f433ba5458","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e347e3baedadd8092250ea7d15134b6a3d87c76369fb0d05f882b6f433ba5458","first_computed_at":"2026-07-05T07:05:35.731152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:35.731152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ftL6chiz2wYVgr0eHiJrBZHmcGGvcpaHF9XraUOyhUTh5vxDr9dEWkv6tNGkzPsgQihnV6ZsJPVKnhA3Xi85AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:35.731583Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17530","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75a5669c54dbdd7b2876bc5c437fe22a382bcfe7571997326f89991c0eefa847","sha256:b84bbc49bc1c3968fff2a741063372aca33d792e8661ebd80e5cbd132a5eea3c"],"state_sha256":"ee7bcb9941ce06ce02009ee419816e964ec810257f46b4ae8a351d0c188f2cef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kqv+U2/uxhQHAf67RapuEDVbNrib6AxfX4EYgpMMr3/E2o+eYDxgwHaU3e6x19RUzbmvAKdpg8kWTPKVvop/CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T10:59:49.576642Z","bundle_sha256":"3e58f9b63f6b501d34f319ff9e68df8da5c8fb11e4ad190a9c33543af5b1aae2"}}