{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XMR3PBCFLC5PGIZWFXZDZYT4GL","short_pith_number":"pith:XMR3PBCF","canonical_record":{"source":{"id":"1909.00871","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-02T21:33:03Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"800d4a09b42e02296cfb1f7cec72da54eee2537069d8fced6bc52beabd575b82","abstract_canon_sha256":"e5335ff3d04985aab6ff8397b0e9cb32f9e8a47013bee8277f01f168b133e96d"},"schema_version":"1.0"},"canonical_sha256":"bb23b7844558baf323362df23ce27c32e066a2508d7cbb5dd2aa1b76417a54f4","source":{"kind":"arxiv","id":"1909.00871","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.00871","created_at":"2026-07-05T00:38:33Z"},{"alias_kind":"arxiv_version","alias_value":"1909.00871v3","created_at":"2026-07-05T00:38:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00871","created_at":"2026-07-05T00:38:33Z"},{"alias_kind":"pith_short_12","alias_value":"XMR3PBCFLC5P","created_at":"2026-07-05T00:38:33Z"},{"alias_kind":"pith_short_16","alias_value":"XMR3PBCFLC5PGIZW","created_at":"2026-07-05T00:38:33Z"},{"alias_kind":"pith_short_8","alias_value":"XMR3PBCF","created_at":"2026-07-05T00:38:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XMR3PBCFLC5PGIZWFXZDZYT4GL","target":"record","payload":{"canonical_record":{"source":{"id":"1909.00871","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-02T21:33:03Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"800d4a09b42e02296cfb1f7cec72da54eee2537069d8fced6bc52beabd575b82","abstract_canon_sha256":"e5335ff3d04985aab6ff8397b0e9cb32f9e8a47013bee8277f01f168b133e96d"},"schema_version":"1.0"},"canonical_sha256":"bb23b7844558baf323362df23ce27c32e066a2508d7cbb5dd2aa1b76417a54f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:38:33.608073Z","signature_b64":"mHfbkjBuqFsfXr060X5g3Az6mqsetTIJiZDVJTNfnQFANQ1653J4lBYt2CX2rgLbWLjU6W1rcGzx1MhNku9aBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb23b7844558baf323362df23ce27c32e066a2508d7cbb5dd2aa1b76417a54f4","last_reissued_at":"2026-07-05T00:38:33.607660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:38:33.607660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.00871","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":"2026-07-05T00:38:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DznBTFbjokDZShx1XkTverP0+rB1RNidjKUB08KekWeriEZLlISmBYt1riTp2GuBhU8Yso09Di6tPiMdN5uWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:40:19.945959Z"},"content_sha256":"c67d23f3d873d6344c06c6398f7807813c31167f3258e870884690fa0d3baeaa","schema_version":"1.0","event_id":"sha256:c67d23f3d873d6344c06c6398f7807813c31167f3258e870884690fa0d3baeaa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XMR3PBCFLC5PGIZWFXZDZYT4GL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Hila Gonen, Rowan Hall Maudslay, Ryan Cotterell, Simone Teufel","submitted_at":"2019-09-02T21:33:03Z","abstract_excerpt":"This paper treats gender bias latent in word embeddings. Previous mitigation attempts rely on the operationalisation of gender bias as a projection over a linear subspace. An alternative approach is Counterfactual Data Augmentation (CDA), in which a corpus is duplicated and augmented to remove bias, e.g. by swapping all inherently-gendered words in the copy. We perform an empirical comparison of these approaches on the English Gigaword and Wikipedia, and find that whilst both successfully reduce direct bias and perform well in tasks which quantify embedding quality, CDA variants outperform pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00871","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/1909.00871/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":"2026-07-05T00:38:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AO4OZ1tInlT6b8SeAzhuh7+o1GOCGrh0e8rDnBg2P7ZqUz93QWvvlZUMtqzDz+Hrj9iwLj5Bc5PQxb+Iovj0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:40:19.946484Z"},"content_sha256":"b7dd6f7fbc72a5f0f792d6bc0748967f5ac49a2a3f9f6a80dc099d54fc2b6af5","schema_version":"1.0","event_id":"sha256:b7dd6f7fbc72a5f0f792d6bc0748967f5ac49a2a3f9f6a80dc099d54fc2b6af5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XMR3PBCFLC5PGIZWFXZDZYT4GL/bundle.json","state_url":"https://pith.science/pith/XMR3PBCFLC5PGIZWFXZDZYT4GL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XMR3PBCFLC5PGIZWFXZDZYT4GL/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":"2026-08-03T21:40:19Z","links":{"resolver":"https://pith.science/pith/XMR3PBCFLC5PGIZWFXZDZYT4GL","bundle":"https://pith.science/pith/XMR3PBCFLC5PGIZWFXZDZYT4GL/bundle.json","state":"https://pith.science/pith/XMR3PBCFLC5PGIZWFXZDZYT4GL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XMR3PBCFLC5PGIZWFXZDZYT4GL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XMR3PBCFLC5PGIZWFXZDZYT4GL","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":"e5335ff3d04985aab6ff8397b0e9cb32f9e8a47013bee8277f01f168b133e96d","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-02T21:33:03Z","title_canon_sha256":"800d4a09b42e02296cfb1f7cec72da54eee2537069d8fced6bc52beabd575b82"},"schema_version":"1.0","source":{"id":"1909.00871","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.00871","created_at":"2026-07-05T00:38:33Z"},{"alias_kind":"arxiv_version","alias_value":"1909.00871v3","created_at":"2026-07-05T00:38:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00871","created_at":"2026-07-05T00:38:33Z"},{"alias_kind":"pith_short_12","alias_value":"XMR3PBCFLC5P","created_at":"2026-07-05T00:38:33Z"},{"alias_kind":"pith_short_16","alias_value":"XMR3PBCFLC5PGIZW","created_at":"2026-07-05T00:38:33Z"},{"alias_kind":"pith_short_8","alias_value":"XMR3PBCF","created_at":"2026-07-05T00:38:33Z"}],"graph_snapshots":[{"event_id":"sha256:b7dd6f7fbc72a5f0f792d6bc0748967f5ac49a2a3f9f6a80dc099d54fc2b6af5","target":"graph","created_at":"2026-07-05T00:38:33Z","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/1909.00871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper treats gender bias latent in word embeddings. Previous mitigation attempts rely on the operationalisation of gender bias as a projection over a linear subspace. An alternative approach is Counterfactual Data Augmentation (CDA), in which a corpus is duplicated and augmented to remove bias, e.g. by swapping all inherently-gendered words in the copy. We perform an empirical comparison of these approaches on the English Gigaword and Wikipedia, and find that whilst both successfully reduce direct bias and perform well in tasks which quantify embedding quality, CDA variants outperform pro","authors_text":"Hila Gonen, Rowan Hall Maudslay, Ryan Cotterell, Simone Teufel","cross_cats":["cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-02T21:33:03Z","title":"It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00871","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:c67d23f3d873d6344c06c6398f7807813c31167f3258e870884690fa0d3baeaa","target":"record","created_at":"2026-07-05T00:38:33Z","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":"e5335ff3d04985aab6ff8397b0e9cb32f9e8a47013bee8277f01f168b133e96d","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-02T21:33:03Z","title_canon_sha256":"800d4a09b42e02296cfb1f7cec72da54eee2537069d8fced6bc52beabd575b82"},"schema_version":"1.0","source":{"id":"1909.00871","kind":"arxiv","version":3}},"canonical_sha256":"bb23b7844558baf323362df23ce27c32e066a2508d7cbb5dd2aa1b76417a54f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb23b7844558baf323362df23ce27c32e066a2508d7cbb5dd2aa1b76417a54f4","first_computed_at":"2026-07-05T00:38:33.607660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:38:33.607660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mHfbkjBuqFsfXr060X5g3Az6mqsetTIJiZDVJTNfnQFANQ1653J4lBYt2CX2rgLbWLjU6W1rcGzx1MhNku9aBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:38:33.608073Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.00871","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c67d23f3d873d6344c06c6398f7807813c31167f3258e870884690fa0d3baeaa","sha256:b7dd6f7fbc72a5f0f792d6bc0748967f5ac49a2a3f9f6a80dc099d54fc2b6af5"],"state_sha256":"bb6b8ff555441dc36521cdf0f3b4ce721ffb8dd94ab2ea5d1e28c4475246cba7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A+u5hY2sjDjfdkNlX0fLZeoh/NhqnYq8LM0w8bXyL5ONT3bAsc1xLgZ5ygQg6Hu8xwvw2IipNXxEndsYRzaPBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:40:19.953794Z","bundle_sha256":"68bb1eeac69dce75f0cd95138fac9fcea21e2b9f4a14b8246e7182b653b1b465"}}