{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:FAVMIKTSXOL4QTKBRTTODEVZOO","short_pith_number":"pith:FAVMIKTS","canonical_record":{"source":{"id":"1906.07337","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-18T01:58:56Z","cross_cats_sorted":[],"title_canon_sha256":"7c3ba3446021a9828a81382313277793fea93ace9317288d7e2f20274fcf93a7","abstract_canon_sha256":"e61bd4e3066c1560f48323ea602d0454a5c3a90c20a51ff7dd45fba79a5b8d06"},"schema_version":"1.0"},"canonical_sha256":"282ac42a72bb97c84d418ce6e192b973b75e49b927e49d47f9427bae36e39888","source":{"kind":"arxiv","id":"1906.07337","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.07337","created_at":"2026-05-17T23:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"1906.07337v1","created_at":"2026-05-17T23:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07337","created_at":"2026-05-17T23:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"FAVMIKTSXOL4","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FAVMIKTSXOL4QTKB","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FAVMIKTS","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:FAVMIKTSXOL4QTKBRTTODEVZOO","target":"record","payload":{"canonical_record":{"source":{"id":"1906.07337","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-18T01:58:56Z","cross_cats_sorted":[],"title_canon_sha256":"7c3ba3446021a9828a81382313277793fea93ace9317288d7e2f20274fcf93a7","abstract_canon_sha256":"e61bd4e3066c1560f48323ea602d0454a5c3a90c20a51ff7dd45fba79a5b8d06"},"schema_version":"1.0"},"canonical_sha256":"282ac42a72bb97c84d418ce6e192b973b75e49b927e49d47f9427bae36e39888","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:08.164595Z","signature_b64":"hVWshWZc+aL1YuRqsh5ixCu648sqSwJa006cV8HK2o612bwjPKbTweq2+/5YPoZ+qHNRe/wcgMBYAZr1WGEEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"282ac42a72bb97c84d418ce6e192b973b75e49b927e49d47f9427bae36e39888","last_reissued_at":"2026-05-17T23:43:08.163845Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:08.163845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.07337","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":"2026-05-17T23:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gtthn/tT6hNNjTLBa/EXLOx3xMveWyT/q4UhUNMV8ILQuXXEK6g7TF0o220olEa7ysxqmkGKga794DAXZ2tMAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:00:09.024253Z"},"content_sha256":"09500ceb3bdcd9870e03b17000b12d37a5c678363cd8d7f368e531e081d60aac","schema_version":"1.0","event_id":"sha256:09500ceb3bdcd9870e03b17000b12d37a5c678363cd8d7f368e531e081d60aac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:FAVMIKTSXOL4QTKBRTTODEVZOO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Measuring Bias in Contextualized Word Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alan W Black, Ayush Pareek, Keita Kurita, Nidhi Vyas, Yulia Tsvetkov","submitted_at":"2019-06-18T01:58:56Z","abstract_excerpt":"Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social stereotypes present in the data as well. In this study, we (1)~propose a template-based method to quantify bias in BERT; (2)~show that this method obtains more consistent results in capturing social biases than the traditional cosine based method; and (3)~conduct a case study, evaluating gender bias in a downstream task of Gender Pronoun Resolution. Although our case "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07337","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":""},"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":"2026-05-17T23:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yZwSLPku85ooqtfdLzHc5wmijB3UZuv/FSpQkimqc3v4vUNhFPjmZKDKVcm628vPs3fjnFx0GpheF1d/CAIsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:00:09.024904Z"},"content_sha256":"64072ff3e2ccef86a0064448419d3de026d6408db4e682b60fcae4bad7600228","schema_version":"1.0","event_id":"sha256:64072ff3e2ccef86a0064448419d3de026d6408db4e682b60fcae4bad7600228"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FAVMIKTSXOL4QTKBRTTODEVZOO/bundle.json","state_url":"https://pith.science/pith/FAVMIKTSXOL4QTKBRTTODEVZOO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FAVMIKTSXOL4QTKBRTTODEVZOO/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":"2026-05-28T23:00:09Z","links":{"resolver":"https://pith.science/pith/FAVMIKTSXOL4QTKBRTTODEVZOO","bundle":"https://pith.science/pith/FAVMIKTSXOL4QTKBRTTODEVZOO/bundle.json","state":"https://pith.science/pith/FAVMIKTSXOL4QTKBRTTODEVZOO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FAVMIKTSXOL4QTKBRTTODEVZOO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FAVMIKTSXOL4QTKBRTTODEVZOO","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":"e61bd4e3066c1560f48323ea602d0454a5c3a90c20a51ff7dd45fba79a5b8d06","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-18T01:58:56Z","title_canon_sha256":"7c3ba3446021a9828a81382313277793fea93ace9317288d7e2f20274fcf93a7"},"schema_version":"1.0","source":{"id":"1906.07337","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.07337","created_at":"2026-05-17T23:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"1906.07337v1","created_at":"2026-05-17T23:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07337","created_at":"2026-05-17T23:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"FAVMIKTSXOL4","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FAVMIKTSXOL4QTKB","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FAVMIKTS","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:64072ff3e2ccef86a0064448419d3de026d6408db4e682b60fcae4bad7600228","target":"graph","created_at":"2026-05-17T23:43:08Z","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"},"paper":{"abstract_excerpt":"Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social stereotypes present in the data as well. In this study, we (1)~propose a template-based method to quantify bias in BERT; (2)~show that this method obtains more consistent results in capturing social biases than the traditional cosine based method; and (3)~conduct a case study, evaluating gender bias in a downstream task of Gender Pronoun Resolution. Although our case ","authors_text":"Alan W Black, Ayush Pareek, Keita Kurita, Nidhi Vyas, Yulia Tsvetkov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-18T01:58:56Z","title":"Measuring Bias in Contextualized Word Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07337","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":"sha256:09500ceb3bdcd9870e03b17000b12d37a5c678363cd8d7f368e531e081d60aac","target":"record","created_at":"2026-05-17T23:43:08Z","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":"e61bd4e3066c1560f48323ea602d0454a5c3a90c20a51ff7dd45fba79a5b8d06","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-18T01:58:56Z","title_canon_sha256":"7c3ba3446021a9828a81382313277793fea93ace9317288d7e2f20274fcf93a7"},"schema_version":"1.0","source":{"id":"1906.07337","kind":"arxiv","version":1}},"canonical_sha256":"282ac42a72bb97c84d418ce6e192b973b75e49b927e49d47f9427bae36e39888","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"282ac42a72bb97c84d418ce6e192b973b75e49b927e49d47f9427bae36e39888","first_computed_at":"2026-05-17T23:43:08.163845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:08.163845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hVWshWZc+aL1YuRqsh5ixCu648sqSwJa006cV8HK2o612bwjPKbTweq2+/5YPoZ+qHNRe/wcgMBYAZr1WGEEDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:08.164595Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.07337","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09500ceb3bdcd9870e03b17000b12d37a5c678363cd8d7f368e531e081d60aac","sha256:64072ff3e2ccef86a0064448419d3de026d6408db4e682b60fcae4bad7600228"],"state_sha256":"aae0f28e9db31fcd811ff1cfd3ac136899e86d49268f338879ccb2246d37325f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G9jcQqp7Yq3Ymzk1XtwUgxF1mi3kun2VlJ5RplTRpATS9Vypk05v2qmlRS5i4jDlTvgnOfO9W3O10GQc2X+5AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T23:00:09.028142Z","bundle_sha256":"0de122396d9c79d4a8c39a0f81363e72412d81c9e481b8fc703047045fbcc3be"}}