{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XXIRI5ULMTJZWAWNOG55N5Z65K","short_pith_number":"pith:XXIRI5UL","canonical_record":{"source":{"id":"2406.12138","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-17T22:58:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"12bfbc90e923674d7aa529a3d0113b3ef9fa1cda48a8dbbf5daa725afa9826c6","abstract_canon_sha256":"d468e04500cc3e903463bf8e6f69ec6ced3774d796af2ae503db552afe5f81f9"},"schema_version":"1.0"},"canonical_sha256":"bdd114768b64d39b02cd71bbd6f73eeaaa9ad45650d2607bde68f10165eefe25","source":{"kind":"arxiv","id":"2406.12138","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12138","created_at":"2026-07-05T08:33:06Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12138v1","created_at":"2026-07-05T08:33:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12138","created_at":"2026-07-05T08:33:06Z"},{"alias_kind":"pith_short_12","alias_value":"XXIRI5ULMTJZ","created_at":"2026-07-05T08:33:06Z"},{"alias_kind":"pith_short_16","alias_value":"XXIRI5ULMTJZWAWN","created_at":"2026-07-05T08:33:06Z"},{"alias_kind":"pith_short_8","alias_value":"XXIRI5UL","created_at":"2026-07-05T08:33:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XXIRI5ULMTJZWAWNOG55N5Z65K","target":"record","payload":{"canonical_record":{"source":{"id":"2406.12138","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-17T22:58:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"12bfbc90e923674d7aa529a3d0113b3ef9fa1cda48a8dbbf5daa725afa9826c6","abstract_canon_sha256":"d468e04500cc3e903463bf8e6f69ec6ced3774d796af2ae503db552afe5f81f9"},"schema_version":"1.0"},"canonical_sha256":"bdd114768b64d39b02cd71bbd6f73eeaaa9ad45650d2607bde68f10165eefe25","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:06.991531Z","signature_b64":"Nviq6ThXoErCIVUHY1h4RFGDtJxYcv/SKdEwgJhU7Y/0H0LFi0+ruMJKtUv2ynergt3Zm5LSk4R/ajF37t3bBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdd114768b64d39b02cd71bbd6f73eeaaa9ad45650d2607bde68f10165eefe25","last_reissued_at":"2026-07-05T08:33:06.991025Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:06.991025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.12138","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":"2026-07-05T08:33:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AoQdadoqZ0kRtY7ipqJhBu1s1dn7EgE9ItsXkFakiS82/UoU/05O7adLatcAG99hj0eIBedImuNDyXr43gA4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:54:58.182463Z"},"content_sha256":"2af0d212f31ab6d6e935b476770a6a09a9c8cfe2e3a3ab8cffb7389fa14a6f6a","schema_version":"1.0","event_id":"sha256:2af0d212f31ab6d6e935b476770a6a09a9c8cfe2e3a3ab8cffb7389fa14a6f6a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XXIRI5ULMTJZWAWNOG55N5Z65K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bias in Text Embedding Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jessica Cervi, Nestor Maslej, Vasyl Rakivnenko, Volodymyr Zhukov","submitted_at":"2024-06-17T22:58:36Z","abstract_excerpt":"Text embedding is becoming an increasingly popular AI methodology, especially among businesses, yet the potential of text embedding models to be biased is not well understood. This paper examines the degree to which a selection of popular text embedding models are biased, particularly along gendered dimensions. More specifically, this paper studies the degree to which these models associate a list of given professions with gendered terms. The analysis reveals that text embedding models are prone to gendered biases but in varying ways. Although there are certain inter-model commonalities, for i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12138","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/2406.12138/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":"2026-07-05T08:33:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eItY2BMmlxLYurEbt1JTh4QEYnTOv8ELt/A+18UNdvbOpK5xQYmxyBElfqt9xqS0OF5wIhJcSlyYym4gobXVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:54:58.183410Z"},"content_sha256":"046afdefd0b22b32520d2ca9d5d476566edad2cf00f14c216a04757851dc3510","schema_version":"1.0","event_id":"sha256:046afdefd0b22b32520d2ca9d5d476566edad2cf00f14c216a04757851dc3510"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XXIRI5ULMTJZWAWNOG55N5Z65K/bundle.json","state_url":"https://pith.science/pith/XXIRI5ULMTJZWAWNOG55N5Z65K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XXIRI5ULMTJZWAWNOG55N5Z65K/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":"2026-08-10T06:54:58Z","links":{"resolver":"https://pith.science/pith/XXIRI5ULMTJZWAWNOG55N5Z65K","bundle":"https://pith.science/pith/XXIRI5ULMTJZWAWNOG55N5Z65K/bundle.json","state":"https://pith.science/pith/XXIRI5ULMTJZWAWNOG55N5Z65K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XXIRI5ULMTJZWAWNOG55N5Z65K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XXIRI5ULMTJZWAWNOG55N5Z65K","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":"d468e04500cc3e903463bf8e6f69ec6ced3774d796af2ae503db552afe5f81f9","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-17T22:58:36Z","title_canon_sha256":"12bfbc90e923674d7aa529a3d0113b3ef9fa1cda48a8dbbf5daa725afa9826c6"},"schema_version":"1.0","source":{"id":"2406.12138","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12138","created_at":"2026-07-05T08:33:06Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12138v1","created_at":"2026-07-05T08:33:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12138","created_at":"2026-07-05T08:33:06Z"},{"alias_kind":"pith_short_12","alias_value":"XXIRI5ULMTJZ","created_at":"2026-07-05T08:33:06Z"},{"alias_kind":"pith_short_16","alias_value":"XXIRI5ULMTJZWAWN","created_at":"2026-07-05T08:33:06Z"},{"alias_kind":"pith_short_8","alias_value":"XXIRI5UL","created_at":"2026-07-05T08:33:06Z"}],"graph_snapshots":[{"event_id":"sha256:046afdefd0b22b32520d2ca9d5d476566edad2cf00f14c216a04757851dc3510","target":"graph","created_at":"2026-07-05T08:33:06Z","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/2406.12138/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text embedding is becoming an increasingly popular AI methodology, especially among businesses, yet the potential of text embedding models to be biased is not well understood. This paper examines the degree to which a selection of popular text embedding models are biased, particularly along gendered dimensions. More specifically, this paper studies the degree to which these models associate a list of given professions with gendered terms. The analysis reveals that text embedding models are prone to gendered biases but in varying ways. Although there are certain inter-model commonalities, for i","authors_text":"Jessica Cervi, Nestor Maslej, Vasyl Rakivnenko, Volodymyr Zhukov","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-17T22:58:36Z","title":"Bias in Text Embedding Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12138","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":"sha256:2af0d212f31ab6d6e935b476770a6a09a9c8cfe2e3a3ab8cffb7389fa14a6f6a","target":"record","created_at":"2026-07-05T08:33:06Z","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":"d468e04500cc3e903463bf8e6f69ec6ced3774d796af2ae503db552afe5f81f9","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-17T22:58:36Z","title_canon_sha256":"12bfbc90e923674d7aa529a3d0113b3ef9fa1cda48a8dbbf5daa725afa9826c6"},"schema_version":"1.0","source":{"id":"2406.12138","kind":"arxiv","version":1}},"canonical_sha256":"bdd114768b64d39b02cd71bbd6f73eeaaa9ad45650d2607bde68f10165eefe25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bdd114768b64d39b02cd71bbd6f73eeaaa9ad45650d2607bde68f10165eefe25","first_computed_at":"2026-07-05T08:33:06.991025Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:33:06.991025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nviq6ThXoErCIVUHY1h4RFGDtJxYcv/SKdEwgJhU7Y/0H0LFi0+ruMJKtUv2ynergt3Zm5LSk4R/ajF37t3bBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:33:06.991531Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12138","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2af0d212f31ab6d6e935b476770a6a09a9c8cfe2e3a3ab8cffb7389fa14a6f6a","sha256:046afdefd0b22b32520d2ca9d5d476566edad2cf00f14c216a04757851dc3510"],"state_sha256":"d1265096af7bfb8f7dd951869f316f908e1938da23a81a0ee29fc2303beefaa2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7duy6aUmz84QjdwS9RDNANQpG/DeCnw5fdjGxksf+pHbOWagLgO/WWWvO8Q80dquTLQHmuGx0I7N5lxvXX80DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:54:58.195801Z","bundle_sha256":"4e9312951954e8d9459c610d2717a6f005f1402304eda9de6c6702bb3cc1d71a"}}