{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XQQFRL4FIY4FRIYANHLSITNL7F","short_pith_number":"pith:XQQFRL4F","canonical_record":{"source":{"id":"2309.12491","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T21:21:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7bf7714810fa3e9890b74d25cd6932f6279da801286f83af3ff612aef85148bb","abstract_canon_sha256":"41c8e7659246674315902f41f1ced2613d049c4af076f4d645f426f1305ace03"},"schema_version":"1.0"},"canonical_sha256":"bc2058af85463858a30069d7244dabf9597d893793b773d33cc74c65a2b3d86a","source":{"kind":"arxiv","id":"2309.12491","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.12491","created_at":"2026-07-05T06:55:59Z"},{"alias_kind":"arxiv_version","alias_value":"2309.12491v2","created_at":"2026-07-05T06:55:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12491","created_at":"2026-07-05T06:55:59Z"},{"alias_kind":"pith_short_12","alias_value":"XQQFRL4FIY4F","created_at":"2026-07-05T06:55:59Z"},{"alias_kind":"pith_short_16","alias_value":"XQQFRL4FIY4FRIYA","created_at":"2026-07-05T06:55:59Z"},{"alias_kind":"pith_short_8","alias_value":"XQQFRL4F","created_at":"2026-07-05T06:55:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XQQFRL4FIY4FRIYANHLSITNL7F","target":"record","payload":{"canonical_record":{"source":{"id":"2309.12491","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T21:21:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7bf7714810fa3e9890b74d25cd6932f6279da801286f83af3ff612aef85148bb","abstract_canon_sha256":"41c8e7659246674315902f41f1ced2613d049c4af076f4d645f426f1305ace03"},"schema_version":"1.0"},"canonical_sha256":"bc2058af85463858a30069d7244dabf9597d893793b773d33cc74c65a2b3d86a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:59.453378Z","signature_b64":"IVVh7fC0HcjlAkh04c3lAVpO4d72i6BHUMrXEzkiI02ois67dIBZfo9UeDdYKTgLUnnA4Nh+J4cshPjt44fZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc2058af85463858a30069d7244dabf9597d893793b773d33cc74c65a2b3d86a","last_reissued_at":"2026-07-05T06:55:59.452805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:59.452805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.12491","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":"2026-07-05T06:55:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fhTB8APNttko7t+edVxok/InIyXc1MBtSl37s1CTUOIYHwKo63JHTQMbV1dVBV8l7VYIi+nj6SZKsnw9D6CtBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:33:52.165783Z"},"content_sha256":"542ff8e35f6bc137cd2f48f678cb11f67339a7e9fa7e99f704caebdc2d8beaeb","schema_version":"1.0","event_id":"sha256:542ff8e35f6bc137cd2f48f678cb11f67339a7e9fa7e99f704caebdc2d8beaeb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XQQFRL4FIY4FRIYANHLSITNL7F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bar Iluz, David Mare\\v{c}ek, Gabriel Stanovsky, Tomasz Limisiewicz","submitted_at":"2023-09-21T21:21:55Z","abstract_excerpt":"We study the effect of tokenization on gender bias in machine translation, an aspect that has been largely overlooked in previous works. Specifically, we focus on the interactions between the frequency of gendered profession names in training data, their representation in the subword tokenizer's vocabulary, and gender bias. We observe that female and non-stereotypical gender inflections of profession names (e.g., Spanish \"doctora\" for \"female doctor\") tend to be split into multiple subword tokens. Our results indicate that the imbalance of gender forms in the model's training corpus is a major"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12491","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/2309.12491/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":"2026-07-05T06:55:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"En6G+LrDpwTtpjOq4fP5c0MieS+8Oi4bUKWyE70PSQoddedZEMrZe0O5+NtmTyKIfll4USjm2oh6unrD+XR9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:33:52.166326Z"},"content_sha256":"13121654c1a2f35e05905b6142a0840f6dd6fa633fad31c88112090e1d9236dc","schema_version":"1.0","event_id":"sha256:13121654c1a2f35e05905b6142a0840f6dd6fa633fad31c88112090e1d9236dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XQQFRL4FIY4FRIYANHLSITNL7F/bundle.json","state_url":"https://pith.science/pith/XQQFRL4FIY4FRIYANHLSITNL7F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XQQFRL4FIY4FRIYANHLSITNL7F/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":"2026-08-07T18:33:52Z","links":{"resolver":"https://pith.science/pith/XQQFRL4FIY4FRIYANHLSITNL7F","bundle":"https://pith.science/pith/XQQFRL4FIY4FRIYANHLSITNL7F/bundle.json","state":"https://pith.science/pith/XQQFRL4FIY4FRIYANHLSITNL7F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XQQFRL4FIY4FRIYANHLSITNL7F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XQQFRL4FIY4FRIYANHLSITNL7F","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":"41c8e7659246674315902f41f1ced2613d049c4af076f4d645f426f1305ace03","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T21:21:55Z","title_canon_sha256":"7bf7714810fa3e9890b74d25cd6932f6279da801286f83af3ff612aef85148bb"},"schema_version":"1.0","source":{"id":"2309.12491","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.12491","created_at":"2026-07-05T06:55:59Z"},{"alias_kind":"arxiv_version","alias_value":"2309.12491v2","created_at":"2026-07-05T06:55:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12491","created_at":"2026-07-05T06:55:59Z"},{"alias_kind":"pith_short_12","alias_value":"XQQFRL4FIY4F","created_at":"2026-07-05T06:55:59Z"},{"alias_kind":"pith_short_16","alias_value":"XQQFRL4FIY4FRIYA","created_at":"2026-07-05T06:55:59Z"},{"alias_kind":"pith_short_8","alias_value":"XQQFRL4F","created_at":"2026-07-05T06:55:59Z"}],"graph_snapshots":[{"event_id":"sha256:13121654c1a2f35e05905b6142a0840f6dd6fa633fad31c88112090e1d9236dc","target":"graph","created_at":"2026-07-05T06:55:59Z","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/2309.12491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the effect of tokenization on gender bias in machine translation, an aspect that has been largely overlooked in previous works. Specifically, we focus on the interactions between the frequency of gendered profession names in training data, their representation in the subword tokenizer's vocabulary, and gender bias. We observe that female and non-stereotypical gender inflections of profession names (e.g., Spanish \"doctora\" for \"female doctor\") tend to be split into multiple subword tokens. Our results indicate that the imbalance of gender forms in the model's training corpus is a major","authors_text":"Bar Iluz, David Mare\\v{c}ek, Gabriel Stanovsky, Tomasz Limisiewicz","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T21:21:55Z","title":"Exploring the Impact of Training Data Distribution and Subword Tokenization on Gender Bias in Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12491","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":"sha256:542ff8e35f6bc137cd2f48f678cb11f67339a7e9fa7e99f704caebdc2d8beaeb","target":"record","created_at":"2026-07-05T06:55:59Z","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":"41c8e7659246674315902f41f1ced2613d049c4af076f4d645f426f1305ace03","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-21T21:21:55Z","title_canon_sha256":"7bf7714810fa3e9890b74d25cd6932f6279da801286f83af3ff612aef85148bb"},"schema_version":"1.0","source":{"id":"2309.12491","kind":"arxiv","version":2}},"canonical_sha256":"bc2058af85463858a30069d7244dabf9597d893793b773d33cc74c65a2b3d86a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc2058af85463858a30069d7244dabf9597d893793b773d33cc74c65a2b3d86a","first_computed_at":"2026-07-05T06:55:59.452805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:55:59.452805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IVVh7fC0HcjlAkh04c3lAVpO4d72i6BHUMrXEzkiI02ois67dIBZfo9UeDdYKTgLUnnA4Nh+J4cshPjt44fZCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:55:59.453378Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.12491","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:542ff8e35f6bc137cd2f48f678cb11f67339a7e9fa7e99f704caebdc2d8beaeb","sha256:13121654c1a2f35e05905b6142a0840f6dd6fa633fad31c88112090e1d9236dc"],"state_sha256":"4bf95c3ec327566ff8c645457b5b8ae46b689628903d9afff300196d98bc1c79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q5vhPXY7O6r6Zoo19+zzve15f4uGvvk4cTjTrol0dKVOlnbeJqxKyzFL7teAymjF12QkWfKdHDh8FDeaMucnBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:33:52.170355Z","bundle_sha256":"04c28f048658aefe537265721a2e20214cadc357f4ef4181ed6ac9eca485c60f"}}