{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:54UWIFZHI2DUVQPOCW6IGBCPEB","short_pith_number":"pith:54UWIFZH","canonical_record":{"source":{"id":"2310.12127","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T17:36:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fa8c53d110a6ddd528d78d23162193a85f46f9d0be078e7ce8b124debc6677f4","abstract_canon_sha256":"9673a4325ea4f76e1b00cdb40f2dc5b37e06315ae913f150785dd784ec791187"},"schema_version":"1.0"},"canonical_sha256":"ef2964172746874ac1ee15bc83044f2077327b37f8b2cd9e084b501dd8ee574a","source":{"kind":"arxiv","id":"2310.12127","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12127","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12127v2","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12127","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"54UWIFZHI2DU","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"54UWIFZHI2DUVQPO","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"54UWIFZH","created_at":"2026-07-05T07:04:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:54UWIFZHI2DUVQPOCW6IGBCPEB","target":"record","payload":{"canonical_record":{"source":{"id":"2310.12127","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T17:36:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fa8c53d110a6ddd528d78d23162193a85f46f9d0be078e7ce8b124debc6677f4","abstract_canon_sha256":"9673a4325ea4f76e1b00cdb40f2dc5b37e06315ae913f150785dd784ec791187"},"schema_version":"1.0"},"canonical_sha256":"ef2964172746874ac1ee15bc83044f2077327b37f8b2cd9e084b501dd8ee574a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:51.685149Z","signature_b64":"/xn8tzzotuA8ObmJm8i6YT+e+zHd+ix1chCEFD7JMnvfOCxfaRI8TrWfViYAcr+cGarNQg8w35dpKT5qHqwSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef2964172746874ac1ee15bc83044f2077327b37f8b2cd9e084b501dd8ee574a","last_reissued_at":"2026-07-05T07:04:51.684725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:51.684725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.12127","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FUOcMfR0TjYpnwYTX1nL3aRNuAixTWTg7FiYs4Ry+3DSAyIwNhbOiILtvJITv0j83DxuvC1byU35341CdMYJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:45:33.361421Z"},"content_sha256":"5e6b9b43206542a900face4a3f6df05497afb84cb77de58e54a17729d340310d","schema_version":"1.0","event_id":"sha256:5e6b9b43206542a900face4a3f6df05497afb84cb77de58e54a17729d340310d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:54UWIFZHI2DUVQPOCW6IGBCPEB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anne Lauscher, Debora Nozza, Flor Miriam Plaza-del-Arco, Giuseppe Attanasio","submitted_at":"2023-10-18T17:36:55Z","abstract_excerpt":"Recent instruction fine-tuned models can solve multiple NLP tasks when prompted to do so, with machine translation (MT) being a prominent use case. However, current research often focuses on standard performance benchmarks, leaving compelling fairness and ethical considerations behind. In MT, this might lead to misgendered translations, resulting, among other harms, in the perpetuation of stereotypes and prejudices. In this work, we address this gap by investigating whether and to what extent such models exhibit gender bias in machine translation and how we can mitigate it. Concretely, we comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12127","kind":"arxiv","version":2},"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/2310.12127/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":"2026-07-05T07:04:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x46TYCufrF7RelJPuEgddXHtLsjloVPtoE9aLdmRAFyXpeCkP4QVpqPCH0q3kCMiyitf4/7Xo82F3WY9hQclBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:45:33.361716Z"},"content_sha256":"fad47a1a951e67defaad01dc51d3c59f9e732954846d5624cbe5fe8c810e070e","schema_version":"1.0","event_id":"sha256:fad47a1a951e67defaad01dc51d3c59f9e732954846d5624cbe5fe8c810e070e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/54UWIFZHI2DUVQPOCW6IGBCPEB/bundle.json","state_url":"https://pith.science/pith/54UWIFZHI2DUVQPOCW6IGBCPEB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/54UWIFZHI2DUVQPOCW6IGBCPEB/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":"2026-07-31T13:45:33Z","links":{"resolver":"https://pith.science/pith/54UWIFZHI2DUVQPOCW6IGBCPEB","bundle":"https://pith.science/pith/54UWIFZHI2DUVQPOCW6IGBCPEB/bundle.json","state":"https://pith.science/pith/54UWIFZHI2DUVQPOCW6IGBCPEB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/54UWIFZHI2DUVQPOCW6IGBCPEB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:54UWIFZHI2DUVQPOCW6IGBCPEB","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":"9673a4325ea4f76e1b00cdb40f2dc5b37e06315ae913f150785dd784ec791187","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T17:36:55Z","title_canon_sha256":"fa8c53d110a6ddd528d78d23162193a85f46f9d0be078e7ce8b124debc6677f4"},"schema_version":"1.0","source":{"id":"2310.12127","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12127","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12127v2","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12127","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"54UWIFZHI2DU","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"54UWIFZHI2DUVQPO","created_at":"2026-07-05T07:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"54UWIFZH","created_at":"2026-07-05T07:04:51Z"}],"graph_snapshots":[{"event_id":"sha256:fad47a1a951e67defaad01dc51d3c59f9e732954846d5624cbe5fe8c810e070e","target":"graph","created_at":"2026-07-05T07:04:51Z","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/2310.12127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent instruction fine-tuned models can solve multiple NLP tasks when prompted to do so, with machine translation (MT) being a prominent use case. However, current research often focuses on standard performance benchmarks, leaving compelling fairness and ethical considerations behind. In MT, this might lead to misgendered translations, resulting, among other harms, in the perpetuation of stereotypes and prejudices. In this work, we address this gap by investigating whether and to what extent such models exhibit gender bias in machine translation and how we can mitigate it. Concretely, we comp","authors_text":"Anne Lauscher, Debora Nozza, Flor Miriam Plaza-del-Arco, Giuseppe Attanasio","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T17:36:55Z","title":"A Tale of Pronouns: Interpretability Informs Gender Bias Mitigation for Fairer Instruction-Tuned Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12127","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":"sha256:5e6b9b43206542a900face4a3f6df05497afb84cb77de58e54a17729d340310d","target":"record","created_at":"2026-07-05T07:04:51Z","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":"9673a4325ea4f76e1b00cdb40f2dc5b37e06315ae913f150785dd784ec791187","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-18T17:36:55Z","title_canon_sha256":"fa8c53d110a6ddd528d78d23162193a85f46f9d0be078e7ce8b124debc6677f4"},"schema_version":"1.0","source":{"id":"2310.12127","kind":"arxiv","version":2}},"canonical_sha256":"ef2964172746874ac1ee15bc83044f2077327b37f8b2cd9e084b501dd8ee574a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef2964172746874ac1ee15bc83044f2077327b37f8b2cd9e084b501dd8ee574a","first_computed_at":"2026-07-05T07:04:51.684725Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:51.684725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/xn8tzzotuA8ObmJm8i6YT+e+zHd+ix1chCEFD7JMnvfOCxfaRI8TrWfViYAcr+cGarNQg8w35dpKT5qHqwSDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:51.685149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.12127","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e6b9b43206542a900face4a3f6df05497afb84cb77de58e54a17729d340310d","sha256:fad47a1a951e67defaad01dc51d3c59f9e732954846d5624cbe5fe8c810e070e"],"state_sha256":"5366c3f7271caa8b2070bfd98682c02c08345fce6fc0ec70dc88cd1e54579503"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VxGfX/JMP5UXOCT+gjNwUrj0wg8GqMPHHcnErEq1no/7M3djTl7v5p5C/0KTXRXikV5vseK7if+5KmIqTzgoDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T13:45:33.364648Z","bundle_sha256":"f95e55f5f1401bcad5f221e0bf0e851c643aae1fae50134c943e6cc43f7e35e4"}}