{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7OTHUUBTY6BRNUXACPRCO35L3S","short_pith_number":"pith:7OTHUUBT","canonical_record":{"source":{"id":"2004.14088","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T11:22:19Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"a366d4dbc65f227f1b7301693af2f07c3494bedff5cc920c2d2046b9f4b4c8f0","abstract_canon_sha256":"9f8c1b59b19141305a819c1d5cea5369d6c50361dc9a7877829e2301487d20ea"},"schema_version":"1.0"},"canonical_sha256":"fba67a5033c78316d2e013e2276fabdcb21ef4e6bdd96c97e7d3b50799339d95","source":{"kind":"arxiv","id":"2004.14088","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14088","created_at":"2026-07-05T01:28:30Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14088v3","created_at":"2026-07-05T01:28:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14088","created_at":"2026-07-05T01:28:30Z"},{"alias_kind":"pith_short_12","alias_value":"7OTHUUBTY6BR","created_at":"2026-07-05T01:28:30Z"},{"alias_kind":"pith_short_16","alias_value":"7OTHUUBTY6BRNUXA","created_at":"2026-07-05T01:28:30Z"},{"alias_kind":"pith_short_8","alias_value":"7OTHUUBT","created_at":"2026-07-05T01:28:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7OTHUUBTY6BRNUXACPRCO35L3S","target":"record","payload":{"canonical_record":{"source":{"id":"2004.14088","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T11:22:19Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"a366d4dbc65f227f1b7301693af2f07c3494bedff5cc920c2d2046b9f4b4c8f0","abstract_canon_sha256":"9f8c1b59b19141305a819c1d5cea5369d6c50361dc9a7877829e2301487d20ea"},"schema_version":"1.0"},"canonical_sha256":"fba67a5033c78316d2e013e2276fabdcb21ef4e6bdd96c97e7d3b50799339d95","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:28:30.361844Z","signature_b64":"dFox8rcw7CHSMU1doT9oL3Jhc65LgyfXV8w8gzbqyK8yqSKe1LzylTu0dd9VFH96DsYOyGQyu56GvBriJ4ItDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fba67a5033c78316d2e013e2276fabdcb21ef4e6bdd96c97e7d3b50799339d95","last_reissued_at":"2026-07-05T01:28:30.361344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:28:30.361344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.14088","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":"2026-07-05T01:28:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"atiuaHGhjoOPw2vi1vXiDQ26UI3iIAc3gLYRivjLTTlhOk8pAZfm3AZDgRoS3SsPM8uy3SGsUx8wYrAtGyxPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:01:54.852515Z"},"content_sha256":"aa776d2e3fe9055f50111f53b580944e1c076d801fe4185ecf8dc8c53031724b","schema_version":"1.0","event_id":"sha256:aa776d2e3fe9055f50111f53b580944e1c076d801fe4185ecf8dc8c53031724b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7OTHUUBTY6BRNUXACPRCO35L3S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Bing Bai, Conghui Zhu, Guanhua Zhang, Junqi Zhang, Kun Bai, Tiejun Zhao","submitted_at":"2020-04-29T11:22:19Z","abstract_excerpt":"With the recent proliferation of the use of text classifications, researchers have found that there are certain unintended biases in text classification datasets. For example, texts containing some demographic identity-terms (e.g., \"gay\", \"black\") are more likely to be abusive in existing abusive language detection datasets. As a result, models trained with these datasets may consider sentences like \"She makes me happy to be gay\" as abusive simply because of the word \"gay.\" In this paper, we formalize the unintended biases in text classification datasets as a kind of selection bias from the no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14088","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/2004.14088/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":"2026-07-05T01:28:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FbywXe2Y9PEngf6GjWpYMXYdw8pM5xcMqEhytOahczU7lzK4bYkTfvoorPEQwxkrZXZgb1Dpw3mNUTP6qxuyDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:01:54.852899Z"},"content_sha256":"63e1248fc47b88e72efc8ac255b0b3cd80d032934fe30d0db9f09dc2e6fb4200","schema_version":"1.0","event_id":"sha256:63e1248fc47b88e72efc8ac255b0b3cd80d032934fe30d0db9f09dc2e6fb4200"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7OTHUUBTY6BRNUXACPRCO35L3S/bundle.json","state_url":"https://pith.science/pith/7OTHUUBTY6BRNUXACPRCO35L3S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7OTHUUBTY6BRNUXACPRCO35L3S/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":"2026-07-09T05:01:54Z","links":{"resolver":"https://pith.science/pith/7OTHUUBTY6BRNUXACPRCO35L3S","bundle":"https://pith.science/pith/7OTHUUBTY6BRNUXACPRCO35L3S/bundle.json","state":"https://pith.science/pith/7OTHUUBTY6BRNUXACPRCO35L3S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7OTHUUBTY6BRNUXACPRCO35L3S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7OTHUUBTY6BRNUXACPRCO35L3S","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":"9f8c1b59b19141305a819c1d5cea5369d6c50361dc9a7877829e2301487d20ea","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T11:22:19Z","title_canon_sha256":"a366d4dbc65f227f1b7301693af2f07c3494bedff5cc920c2d2046b9f4b4c8f0"},"schema_version":"1.0","source":{"id":"2004.14088","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14088","created_at":"2026-07-05T01:28:30Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14088v3","created_at":"2026-07-05T01:28:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14088","created_at":"2026-07-05T01:28:30Z"},{"alias_kind":"pith_short_12","alias_value":"7OTHUUBTY6BR","created_at":"2026-07-05T01:28:30Z"},{"alias_kind":"pith_short_16","alias_value":"7OTHUUBTY6BRNUXA","created_at":"2026-07-05T01:28:30Z"},{"alias_kind":"pith_short_8","alias_value":"7OTHUUBT","created_at":"2026-07-05T01:28:30Z"}],"graph_snapshots":[{"event_id":"sha256:63e1248fc47b88e72efc8ac255b0b3cd80d032934fe30d0db9f09dc2e6fb4200","target":"graph","created_at":"2026-07-05T01:28:30Z","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/2004.14088/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the recent proliferation of the use of text classifications, researchers have found that there are certain unintended biases in text classification datasets. For example, texts containing some demographic identity-terms (e.g., \"gay\", \"black\") are more likely to be abusive in existing abusive language detection datasets. As a result, models trained with these datasets may consider sentences like \"She makes me happy to be gay\" as abusive simply because of the word \"gay.\" In this paper, we formalize the unintended biases in text classification datasets as a kind of selection bias from the no","authors_text":"Bing Bai, Conghui Zhu, Guanhua Zhang, Junqi Zhang, Kun Bai, Tiejun Zhao","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T11:22:19Z","title":"Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14088","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:aa776d2e3fe9055f50111f53b580944e1c076d801fe4185ecf8dc8c53031724b","target":"record","created_at":"2026-07-05T01:28:30Z","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":"9f8c1b59b19141305a819c1d5cea5369d6c50361dc9a7877829e2301487d20ea","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T11:22:19Z","title_canon_sha256":"a366d4dbc65f227f1b7301693af2f07c3494bedff5cc920c2d2046b9f4b4c8f0"},"schema_version":"1.0","source":{"id":"2004.14088","kind":"arxiv","version":3}},"canonical_sha256":"fba67a5033c78316d2e013e2276fabdcb21ef4e6bdd96c97e7d3b50799339d95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fba67a5033c78316d2e013e2276fabdcb21ef4e6bdd96c97e7d3b50799339d95","first_computed_at":"2026-07-05T01:28:30.361344Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:28:30.361344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dFox8rcw7CHSMU1doT9oL3Jhc65LgyfXV8w8gzbqyK8yqSKe1LzylTu0dd9VFH96DsYOyGQyu56GvBriJ4ItDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:28:30.361844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14088","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa776d2e3fe9055f50111f53b580944e1c076d801fe4185ecf8dc8c53031724b","sha256:63e1248fc47b88e72efc8ac255b0b3cd80d032934fe30d0db9f09dc2e6fb4200"],"state_sha256":"a5bb60b147fb6531bfa0baf4182c72e12bf729ce6de08fbfc4242172788d7078"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S/McdzNqHUJCis4W0Xgfw4KyeQAQgD+Hq94zddZkFsP8aUT06OIl8gY8+bkD1lEw+V5ENFFuO0XNe0M6nHioCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:01:54.854962Z","bundle_sha256":"967a0ce2fd0f0a8f152d0bd712a9bea498c9b506415101aba5d7ec8f8e2e5cb5"}}