{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YEZF5HEVTUCGJGRTVXU7HK6F7K","short_pith_number":"pith:YEZF5HEV","canonical_record":{"source":{"id":"2105.00908","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-03T14:45:10Z","cross_cats_sorted":[],"title_canon_sha256":"df107b89063ec035198c9b80b762016f568fa32b203de7de8707b6360d209542","abstract_canon_sha256":"fc210752af2df24acad736902084d5db1c3926c8cab4f6275b44866f64ba9bf9"},"schema_version":"1.0"},"canonical_sha256":"c1325e9c959d04649a33ade9f3abc5fabb4c077e41e8abb6f90bf83dc5579692","source":{"kind":"arxiv","id":"2105.00908","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.00908","created_at":"2026-07-05T02:37:46Z"},{"alias_kind":"arxiv_version","alias_value":"2105.00908v3","created_at":"2026-07-05T02:37:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.00908","created_at":"2026-07-05T02:37:46Z"},{"alias_kind":"pith_short_12","alias_value":"YEZF5HEVTUCG","created_at":"2026-07-05T02:37:46Z"},{"alias_kind":"pith_short_16","alias_value":"YEZF5HEVTUCGJGRT","created_at":"2026-07-05T02:37:46Z"},{"alias_kind":"pith_short_8","alias_value":"YEZF5HEV","created_at":"2026-07-05T02:37:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YEZF5HEVTUCGJGRTVXU7HK6F7K","target":"record","payload":{"canonical_record":{"source":{"id":"2105.00908","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-03T14:45:10Z","cross_cats_sorted":[],"title_canon_sha256":"df107b89063ec035198c9b80b762016f568fa32b203de7de8707b6360d209542","abstract_canon_sha256":"fc210752af2df24acad736902084d5db1c3926c8cab4f6275b44866f64ba9bf9"},"schema_version":"1.0"},"canonical_sha256":"c1325e9c959d04649a33ade9f3abc5fabb4c077e41e8abb6f90bf83dc5579692","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:46.737903Z","signature_b64":"jDie6AAyk6Y6yWfn17pJTxRIsEb/bdpoLFowfRWqIZZnRs7KxEFkZbzr5ASqtx4ZsG2oM/jW0FqoJXvIQ4VvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1325e9c959d04649a33ade9f3abc5fabb4c077e41e8abb6f90bf83dc5579692","last_reissued_at":"2026-07-05T02:37:46.737452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:46.737452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.00908","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:37:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vn140Zapkbw4lSjLo/XdUWq/qHOULZ+ypFN8ivM9VxWpP++8sqVqk5cFoD8tPs90vQAHOq1KvcsggVYkZE14Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:56:56.903660Z"},"content_sha256":"38f0a81ac93289cd5a36deac40d0de1475b32642098d7228cce2f4103a927fc3","schema_version":"1.0","event_id":"sha256:38f0a81ac93289cd5a36deac40d0de1475b32642098d7228cce2f4103a927fc3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YEZF5HEVTUCGJGRTVXU7HK6F7K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Impact of Gender Debiased Word Embeddings in Language Modeling","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christine Basta, Marta R. Costa-juss\\`a","submitted_at":"2021-05-03T14:45:10Z","abstract_excerpt":"Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing. A key path towards fairness is to understand, analyse and interpret our data and algorithms. Recent studies have shown that the human-generated data used in training is an apparent factor of getting biases. In addition, current algorithms have also been proven to amplify biases from data.\n  To further address these concerns, in this paper, we study how an state-of-the-art recurrent neural language model behaves when trained on data, which under-represents"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.00908","kind":"arxiv","version":3},"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/2105.00908/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":"2026-07-05T02:37:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/akoibu3SYDPeQ1G53/QQLBpOSDYZkc3z+/TRwC3RXeyVJVjdZbKlaslYDXoaTbM6A841JXD4jHwe914M0VaDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:56:56.904292Z"},"content_sha256":"b0de2d88ee2eb5e1b5024ee1e93a9d84a9da672e94559070efcf2fb61662e632","schema_version":"1.0","event_id":"sha256:b0de2d88ee2eb5e1b5024ee1e93a9d84a9da672e94559070efcf2fb61662e632"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YEZF5HEVTUCGJGRTVXU7HK6F7K/bundle.json","state_url":"https://pith.science/pith/YEZF5HEVTUCGJGRTVXU7HK6F7K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YEZF5HEVTUCGJGRTVXU7HK6F7K/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":"2026-08-21T13:56:56Z","links":{"resolver":"https://pith.science/pith/YEZF5HEVTUCGJGRTVXU7HK6F7K","bundle":"https://pith.science/pith/YEZF5HEVTUCGJGRTVXU7HK6F7K/bundle.json","state":"https://pith.science/pith/YEZF5HEVTUCGJGRTVXU7HK6F7K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YEZF5HEVTUCGJGRTVXU7HK6F7K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YEZF5HEVTUCGJGRTVXU7HK6F7K","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":"fc210752af2df24acad736902084d5db1c3926c8cab4f6275b44866f64ba9bf9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-03T14:45:10Z","title_canon_sha256":"df107b89063ec035198c9b80b762016f568fa32b203de7de8707b6360d209542"},"schema_version":"1.0","source":{"id":"2105.00908","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.00908","created_at":"2026-07-05T02:37:46Z"},{"alias_kind":"arxiv_version","alias_value":"2105.00908v3","created_at":"2026-07-05T02:37:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.00908","created_at":"2026-07-05T02:37:46Z"},{"alias_kind":"pith_short_12","alias_value":"YEZF5HEVTUCG","created_at":"2026-07-05T02:37:46Z"},{"alias_kind":"pith_short_16","alias_value":"YEZF5HEVTUCGJGRT","created_at":"2026-07-05T02:37:46Z"},{"alias_kind":"pith_short_8","alias_value":"YEZF5HEV","created_at":"2026-07-05T02:37:46Z"}],"graph_snapshots":[{"event_id":"sha256:b0de2d88ee2eb5e1b5024ee1e93a9d84a9da672e94559070efcf2fb61662e632","target":"graph","created_at":"2026-07-05T02:37:46Z","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/2105.00908/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gender, race and social biases have recently been detected as evident examples of unfairness in applications of Natural Language Processing. A key path towards fairness is to understand, analyse and interpret our data and algorithms. Recent studies have shown that the human-generated data used in training is an apparent factor of getting biases. In addition, current algorithms have also been proven to amplify biases from data.\n  To further address these concerns, in this paper, we study how an state-of-the-art recurrent neural language model behaves when trained on data, which under-represents","authors_text":"Christine Basta, Marta R. Costa-juss\\`a","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-03T14:45:10Z","title":"Impact of Gender Debiased Word Embeddings in Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.00908","kind":"arxiv","version":3},"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":"sha256:38f0a81ac93289cd5a36deac40d0de1475b32642098d7228cce2f4103a927fc3","target":"record","created_at":"2026-07-05T02:37:46Z","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":"fc210752af2df24acad736902084d5db1c3926c8cab4f6275b44866f64ba9bf9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-03T14:45:10Z","title_canon_sha256":"df107b89063ec035198c9b80b762016f568fa32b203de7de8707b6360d209542"},"schema_version":"1.0","source":{"id":"2105.00908","kind":"arxiv","version":3}},"canonical_sha256":"c1325e9c959d04649a33ade9f3abc5fabb4c077e41e8abb6f90bf83dc5579692","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1325e9c959d04649a33ade9f3abc5fabb4c077e41e8abb6f90bf83dc5579692","first_computed_at":"2026-07-05T02:37:46.737452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:37:46.737452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jDie6AAyk6Y6yWfn17pJTxRIsEb/bdpoLFowfRWqIZZnRs7KxEFkZbzr5ASqtx4ZsG2oM/jW0FqoJXvIQ4VvBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:37:46.737903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.00908","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38f0a81ac93289cd5a36deac40d0de1475b32642098d7228cce2f4103a927fc3","sha256:b0de2d88ee2eb5e1b5024ee1e93a9d84a9da672e94559070efcf2fb61662e632"],"state_sha256":"c4ccfa3bcc1eb4fb7f9dffb25b0cb3e653d85b9acfa4db44843082ced2330131"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PH/20xd9vnpmnn0UXFJj1gtJl4n7QsEw8y0VJMR+GFjDAGFNFxg3JV1tDsI8WXABYIKlGRcGxWaYiRT+qaWpAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T13:56:56.910087Z","bundle_sha256":"a86cc2bf216c4e92f46d34d99faf89cb0049e2aabe14a52c7228b12097c5d2b6"}}