{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6LIJHQJXHLR6LWZM2ZNJH3FMCJ","short_pith_number":"pith:6LIJHQJX","canonical_record":{"source":{"id":"2308.16871","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-31T17:20:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"270b37a11769054d6949cd78a3d425706c9625ffb83d34011d725111c14f0a19","abstract_canon_sha256":"5540ad05e1c2c546edeac5b6fb0b6cfde42890cdf6409bc7fc8483c6ec8a3bb5"},"schema_version":"1.0"},"canonical_sha256":"f2d093c1373ae3e5db2cd65a93ecac126f08f9dfbcf43955dcedddc6d1cfa2d8","source":{"kind":"arxiv","id":"2308.16871","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.16871","created_at":"2026-07-05T06:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"2308.16871v1","created_at":"2026-07-05T06:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16871","created_at":"2026-07-05T06:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"6LIJHQJXHLR6","created_at":"2026-07-05T06:46:40Z"},{"alias_kind":"pith_short_16","alias_value":"6LIJHQJXHLR6LWZM","created_at":"2026-07-05T06:46:40Z"},{"alias_kind":"pith_short_8","alias_value":"6LIJHQJX","created_at":"2026-07-05T06:46:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6LIJHQJXHLR6LWZM2ZNJH3FMCJ","target":"record","payload":{"canonical_record":{"source":{"id":"2308.16871","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-31T17:20:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"270b37a11769054d6949cd78a3d425706c9625ffb83d34011d725111c14f0a19","abstract_canon_sha256":"5540ad05e1c2c546edeac5b6fb0b6cfde42890cdf6409bc7fc8483c6ec8a3bb5"},"schema_version":"1.0"},"canonical_sha256":"f2d093c1373ae3e5db2cd65a93ecac126f08f9dfbcf43955dcedddc6d1cfa2d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:40.584870Z","signature_b64":"05XtflecTZiupNEn+9QUD2vmoLoVYpAkCHoBG6eBB0tJmaHFmAw/4vAmbp9tT0ThmxxQm6nkTa0AWTr8Yt2pAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2d093c1373ae3e5db2cd65a93ecac126f08f9dfbcf43955dcedddc6d1cfa2d8","last_reissued_at":"2026-07-05T06:46:40.584309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:40.584309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.16871","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":"2026-07-05T06:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sAdJUNFnBQlRx6He+uma4ix9dzcpdaBG/XFmnSOJSipTCSCv3rLjE5Wdv12L50em/a6BH7sgUTix3s3M31kcCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:50:03.832793Z"},"content_sha256":"f7c438abcd034cd43419a330ce4b0f6b3ca891c2b5a84f863467f55daa6d3aa6","schema_version":"1.0","event_id":"sha256:f7c438abcd034cd43419a330ce4b0f6b3ca891c2b5a84f863467f55daa6d3aa6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6LIJHQJXHLR6LWZM2ZNJH3FMCJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Gender-GAP Pipeline: A Gender-Aware Polyglot Pipeline for Gender Characterisation in 55 Languages","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adina Williams, Belen Alastruey, Benjamin Muller, Christophe Ropers, Elahe Kalbassi, Eric Michael Smith, Luke Zettlemoyer, Marta R. Costa-juss\\`a, Pierre Andrews, Prangthip Hansanti","submitted_at":"2023-08-31T17:20:50Z","abstract_excerpt":"Gender biases in language generation systems are challenging to mitigate. One possible source for these biases is gender representation disparities in the training and evaluation data. Despite recent progress in documenting this problem and many attempts at mitigating it, we still lack shared methodology and tooling to report gender representation in large datasets. Such quantitative reporting will enable further mitigation, e.g., via data augmentation. This paper describes the Gender-GAP Pipeline (for Gender-Aware Polyglot Pipeline), an automatic pipeline to characterize gender representation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16871","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/2308.16871/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":"2026-07-05T06:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EBFf34JjjRXxKaPUwYaRVPfuthSnSg2vJuFFfSQT565UCx6GPH9VJrElY5K/QmGdWMyJ5RpmROnpi51Lu1myBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T01:50:03.833296Z"},"content_sha256":"6e11747a5a791459f800ffd69d5bf4268da49b4b5f962423e65e06677463bb97","schema_version":"1.0","event_id":"sha256:6e11747a5a791459f800ffd69d5bf4268da49b4b5f962423e65e06677463bb97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6LIJHQJXHLR6LWZM2ZNJH3FMCJ/bundle.json","state_url":"https://pith.science/pith/6LIJHQJXHLR6LWZM2ZNJH3FMCJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6LIJHQJXHLR6LWZM2ZNJH3FMCJ/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":"2026-08-20T01:50:03Z","links":{"resolver":"https://pith.science/pith/6LIJHQJXHLR6LWZM2ZNJH3FMCJ","bundle":"https://pith.science/pith/6LIJHQJXHLR6LWZM2ZNJH3FMCJ/bundle.json","state":"https://pith.science/pith/6LIJHQJXHLR6LWZM2ZNJH3FMCJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6LIJHQJXHLR6LWZM2ZNJH3FMCJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6LIJHQJXHLR6LWZM2ZNJH3FMCJ","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":"5540ad05e1c2c546edeac5b6fb0b6cfde42890cdf6409bc7fc8483c6ec8a3bb5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-31T17:20:50Z","title_canon_sha256":"270b37a11769054d6949cd78a3d425706c9625ffb83d34011d725111c14f0a19"},"schema_version":"1.0","source":{"id":"2308.16871","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.16871","created_at":"2026-07-05T06:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"2308.16871v1","created_at":"2026-07-05T06:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16871","created_at":"2026-07-05T06:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"6LIJHQJXHLR6","created_at":"2026-07-05T06:46:40Z"},{"alias_kind":"pith_short_16","alias_value":"6LIJHQJXHLR6LWZM","created_at":"2026-07-05T06:46:40Z"},{"alias_kind":"pith_short_8","alias_value":"6LIJHQJX","created_at":"2026-07-05T06:46:40Z"}],"graph_snapshots":[{"event_id":"sha256:6e11747a5a791459f800ffd69d5bf4268da49b4b5f962423e65e06677463bb97","target":"graph","created_at":"2026-07-05T06:46:40Z","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/2308.16871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gender biases in language generation systems are challenging to mitigate. One possible source for these biases is gender representation disparities in the training and evaluation data. Despite recent progress in documenting this problem and many attempts at mitigating it, we still lack shared methodology and tooling to report gender representation in large datasets. Such quantitative reporting will enable further mitigation, e.g., via data augmentation. This paper describes the Gender-GAP Pipeline (for Gender-Aware Polyglot Pipeline), an automatic pipeline to characterize gender representation","authors_text":"Adina Williams, Belen Alastruey, Benjamin Muller, Christophe Ropers, Elahe Kalbassi, Eric Michael Smith, Luke Zettlemoyer, Marta R. Costa-juss\\`a, Pierre Andrews, Prangthip Hansanti","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-31T17:20:50Z","title":"The Gender-GAP Pipeline: A Gender-Aware Polyglot Pipeline for Gender Characterisation in 55 Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16871","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:f7c438abcd034cd43419a330ce4b0f6b3ca891c2b5a84f863467f55daa6d3aa6","target":"record","created_at":"2026-07-05T06:46:40Z","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":"5540ad05e1c2c546edeac5b6fb0b6cfde42890cdf6409bc7fc8483c6ec8a3bb5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-31T17:20:50Z","title_canon_sha256":"270b37a11769054d6949cd78a3d425706c9625ffb83d34011d725111c14f0a19"},"schema_version":"1.0","source":{"id":"2308.16871","kind":"arxiv","version":1}},"canonical_sha256":"f2d093c1373ae3e5db2cd65a93ecac126f08f9dfbcf43955dcedddc6d1cfa2d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2d093c1373ae3e5db2cd65a93ecac126f08f9dfbcf43955dcedddc6d1cfa2d8","first_computed_at":"2026-07-05T06:46:40.584309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:46:40.584309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"05XtflecTZiupNEn+9QUD2vmoLoVYpAkCHoBG6eBB0tJmaHFmAw/4vAmbp9tT0ThmxxQm6nkTa0AWTr8Yt2pAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:46:40.584870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.16871","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7c438abcd034cd43419a330ce4b0f6b3ca891c2b5a84f863467f55daa6d3aa6","sha256:6e11747a5a791459f800ffd69d5bf4268da49b4b5f962423e65e06677463bb97"],"state_sha256":"dd52fd1a72b2838f8b7c95b031f1323a8e365d3b76c927fafa5770b842c6bfb0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qMaERjVh0jlkm8GZCwMbIDbHcZcwM39REtHbGQX0FsG6qwbWbYEjZtdgndcYZXSfFwcrpqiqh+lGVDEq6ypOCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T01:50:03.837543Z","bundle_sha256":"48ebbf4c8bbc8dfa3caa5cb974ca423b85354e3c901188a9d2d72f3058d03208"}}