{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RLAUC45M2KFW5IBB2DP6OFGKXG","short_pith_number":"pith:RLAUC45M","canonical_record":{"source":{"id":"1812.10424","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-13T21:00:05Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"4316c9619d106961a862047c2afe26b56ddc256fd6e2649f4c64f553dfb415b2","abstract_canon_sha256":"9ae10687e1eba279455e861bcbaa83fb5c426ded7c768d9a419b16054a54dc9c"},"schema_version":"1.0"},"canonical_sha256":"8ac14173acd28b6ea021d0dfe714cab9887539e1ec21b8b677305bd3048ff385","source":{"kind":"arxiv","id":"1812.10424","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.10424","created_at":"2026-07-05T02:35:09Z"},{"alias_kind":"arxiv_version","alias_value":"1812.10424v4","created_at":"2026-07-05T02:35:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10424","created_at":"2026-07-05T02:35:09Z"},{"alias_kind":"pith_short_12","alias_value":"RLAUC45M2KFW","created_at":"2026-07-05T02:35:09Z"},{"alias_kind":"pith_short_16","alias_value":"RLAUC45M2KFW5IBB","created_at":"2026-07-05T02:35:09Z"},{"alias_kind":"pith_short_8","alias_value":"RLAUC45M","created_at":"2026-07-05T02:35:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RLAUC45M2KFW5IBB2DP6OFGKXG","target":"record","payload":{"canonical_record":{"source":{"id":"1812.10424","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-13T21:00:05Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"4316c9619d106961a862047c2afe26b56ddc256fd6e2649f4c64f553dfb415b2","abstract_canon_sha256":"9ae10687e1eba279455e861bcbaa83fb5c426ded7c768d9a419b16054a54dc9c"},"schema_version":"1.0"},"canonical_sha256":"8ac14173acd28b6ea021d0dfe714cab9887539e1ec21b8b677305bd3048ff385","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:35:09.914908Z","signature_b64":"Z/jUAN9wRlrSQavMyLrwVykZa2ZYj6/YZ2PeV7tI5a5KR5wWFAkrHFRcTWXRtxM+C6wVEKouQK8wOt5HyusWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ac14173acd28b6ea021d0dfe714cab9887539e1ec21b8b677305bd3048ff385","last_reissued_at":"2026-07-05T02:35:09.914439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:35:09.914439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.10424","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:35:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f3eDtrJLS/oo+10UOHnARSCcQmXuf5Q5LLkRQq21QbUD3C5metIewyL2WGah2dVorbK7LLCeERYuwWFueYXpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:19:10.672069Z"},"content_sha256":"63ac9ae5d96ed2211682690bc3f9343c3313762d45e66b85035acacf5c897809","schema_version":"1.0","event_id":"sha256:63ac9ae5d96ed2211682690bc3f9343c3313762d45e66b85035acacf5c897809"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RLAUC45M2KFW5IBB2DP6OFGKXG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Measuring Societal Biases from Text Corpora with Smoothed First-Order Co-occurrence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Allan Hanbury, James Henderson, Navid Rekabsaz, Robert West","submitted_at":"2018-12-13T21:00:05Z","abstract_excerpt":"Text corpora are widely used resources for measuring societal biases and stereotypes. The common approach to measuring such biases using a corpus is by calculating the similarities between the embedding vector of a word (like nurse) and the vectors of the representative words of the concepts of interest (such as genders). In this study, we show that, depending on what one aims to quantify as bias, this commonly-used approach can introduce non-relevant concepts into bias measurement. We propose an alternative approach to bias measurement utilizing the smoothed first-order co-occurrence relation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10424","kind":"arxiv","version":4},"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/1812.10424/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":"2026-07-05T02:35:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BmJT3DgrDt1R1hEXdMDHLJRadmnLPSGDavqV3KVCMIaM2aBTyRfsQIduJh7gFYNUX0GBK+ZgbA516NXP1GW7Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:19:10.673409Z"},"content_sha256":"ca111e132e33093c1a10889474a7096f3bd7de0c2fb116cbd1cfe80ff009ef11","schema_version":"1.0","event_id":"sha256:ca111e132e33093c1a10889474a7096f3bd7de0c2fb116cbd1cfe80ff009ef11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RLAUC45M2KFW5IBB2DP6OFGKXG/bundle.json","state_url":"https://pith.science/pith/RLAUC45M2KFW5IBB2DP6OFGKXG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RLAUC45M2KFW5IBB2DP6OFGKXG/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":"2026-08-04T06:19:10Z","links":{"resolver":"https://pith.science/pith/RLAUC45M2KFW5IBB2DP6OFGKXG","bundle":"https://pith.science/pith/RLAUC45M2KFW5IBB2DP6OFGKXG/bundle.json","state":"https://pith.science/pith/RLAUC45M2KFW5IBB2DP6OFGKXG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RLAUC45M2KFW5IBB2DP6OFGKXG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RLAUC45M2KFW5IBB2DP6OFGKXG","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":"9ae10687e1eba279455e861bcbaa83fb5c426ded7c768d9a419b16054a54dc9c","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-13T21:00:05Z","title_canon_sha256":"4316c9619d106961a862047c2afe26b56ddc256fd6e2649f4c64f553dfb415b2"},"schema_version":"1.0","source":{"id":"1812.10424","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.10424","created_at":"2026-07-05T02:35:09Z"},{"alias_kind":"arxiv_version","alias_value":"1812.10424v4","created_at":"2026-07-05T02:35:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10424","created_at":"2026-07-05T02:35:09Z"},{"alias_kind":"pith_short_12","alias_value":"RLAUC45M2KFW","created_at":"2026-07-05T02:35:09Z"},{"alias_kind":"pith_short_16","alias_value":"RLAUC45M2KFW5IBB","created_at":"2026-07-05T02:35:09Z"},{"alias_kind":"pith_short_8","alias_value":"RLAUC45M","created_at":"2026-07-05T02:35:09Z"}],"graph_snapshots":[{"event_id":"sha256:ca111e132e33093c1a10889474a7096f3bd7de0c2fb116cbd1cfe80ff009ef11","target":"graph","created_at":"2026-07-05T02:35:09Z","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/1812.10424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text corpora are widely used resources for measuring societal biases and stereotypes. The common approach to measuring such biases using a corpus is by calculating the similarities between the embedding vector of a word (like nurse) and the vectors of the representative words of the concepts of interest (such as genders). In this study, we show that, depending on what one aims to quantify as bias, this commonly-used approach can introduce non-relevant concepts into bias measurement. We propose an alternative approach to bias measurement utilizing the smoothed first-order co-occurrence relation","authors_text":"Allan Hanbury, James Henderson, Navid Rekabsaz, Robert West","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-13T21:00:05Z","title":"Measuring Societal Biases from Text Corpora with Smoothed First-Order Co-occurrence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10424","kind":"arxiv","version":4},"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":"sha256:63ac9ae5d96ed2211682690bc3f9343c3313762d45e66b85035acacf5c897809","target":"record","created_at":"2026-07-05T02:35:09Z","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":"9ae10687e1eba279455e861bcbaa83fb5c426ded7c768d9a419b16054a54dc9c","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-13T21:00:05Z","title_canon_sha256":"4316c9619d106961a862047c2afe26b56ddc256fd6e2649f4c64f553dfb415b2"},"schema_version":"1.0","source":{"id":"1812.10424","kind":"arxiv","version":4}},"canonical_sha256":"8ac14173acd28b6ea021d0dfe714cab9887539e1ec21b8b677305bd3048ff385","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ac14173acd28b6ea021d0dfe714cab9887539e1ec21b8b677305bd3048ff385","first_computed_at":"2026-07-05T02:35:09.914439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:35:09.914439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z/jUAN9wRlrSQavMyLrwVykZa2ZYj6/YZ2PeV7tI5a5KR5wWFAkrHFRcTWXRtxM+C6wVEKouQK8wOt5HyusWCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:35:09.914908Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.10424","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63ac9ae5d96ed2211682690bc3f9343c3313762d45e66b85035acacf5c897809","sha256:ca111e132e33093c1a10889474a7096f3bd7de0c2fb116cbd1cfe80ff009ef11"],"state_sha256":"ef303465e5432bfeb290cb03768044c153b011c14cbdaace1ab79b9c226e401c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E9CfKzHMuUN/a1TX6NFnP4qb30gHWjwcoBGvUnbvs05nmgk2/GN82EF9+x53HcXxqcpcX/u2enU2PkHgAym0BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:19:10.681733Z","bundle_sha256":"56de5596013603eed6a989592ef3a22f0a5c492cc291f625f57d00ce570e7d34"}}