{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:EY37HIVNFT4CM4H7WCOZHSIZ2G","short_pith_number":"pith:EY37HIVN","canonical_record":{"source":{"id":"2109.02691","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-06T18:40:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4d9e22191633d337d0d435ff6094ec26574523c6a070f1347b270258fb10ba38","abstract_canon_sha256":"38b67c6c9435f23bf1a5b82fce9c1692c61b666c04dd14c796b185487e249d23"},"schema_version":"1.0"},"canonical_sha256":"2637f3a2ad2cf82670ffb09d93c919d198abbe7735fa52ebe2f72c1d721189a6","source":{"kind":"arxiv","id":"2109.02691","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02691","created_at":"2026-07-05T05:06:52Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02691v1","created_at":"2026-07-05T05:06:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02691","created_at":"2026-07-05T05:06:52Z"},{"alias_kind":"pith_short_12","alias_value":"EY37HIVNFT4C","created_at":"2026-07-05T05:06:52Z"},{"alias_kind":"pith_short_16","alias_value":"EY37HIVNFT4CM4H7","created_at":"2026-07-05T05:06:52Z"},{"alias_kind":"pith_short_8","alias_value":"EY37HIVN","created_at":"2026-07-05T05:06:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:EY37HIVNFT4CM4H7WCOZHSIZ2G","target":"record","payload":{"canonical_record":{"source":{"id":"2109.02691","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-06T18:40:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4d9e22191633d337d0d435ff6094ec26574523c6a070f1347b270258fb10ba38","abstract_canon_sha256":"38b67c6c9435f23bf1a5b82fce9c1692c61b666c04dd14c796b185487e249d23"},"schema_version":"1.0"},"canonical_sha256":"2637f3a2ad2cf82670ffb09d93c919d198abbe7735fa52ebe2f72c1d721189a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:52.143979Z","signature_b64":"fY2Of5nrbcLHTNb7SC2iE84zyq76IWt66fqgHrqHh0FN7Vrcw8t4V1uSAVGvY5X2Zp824oIJ1H2PY02eIqgLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2637f3a2ad2cf82670ffb09d93c919d198abbe7735fa52ebe2f72c1d721189a6","last_reissued_at":"2026-07-05T05:06:52.143623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:52.143623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.02691","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":"2026-07-05T05:06:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HewU4F4i0HK9soqhts5XMy1kWIDIzJrF5nr4rWdSZKGLuXUxwEZS7cH+6ALa/ZkONHajysE0nR5bI9w9ji05Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T11:42:04.878177Z"},"content_sha256":"6a003f45d4e16f7ad44297870ef75018d4c0e1d8fcd40565cabf8cfa8516a88f","schema_version":"1.0","event_id":"sha256:6a003f45d4e16f7ad44297870ef75018d4c0e1d8fcd40565cabf8cfa8516a88f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:EY37HIVNFT4CM4H7WCOZHSIZ2G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SS-BERT: Mitigating Identity Terms Bias in Toxic Comment Classification by Utilising the Notion of \"Subjectivity\" and \"Identity Terms\"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Frank Hopfgartner, Zhixue Zhao, Ziqi Zhang","submitted_at":"2021-09-06T18:40:06Z","abstract_excerpt":"Toxic comment classification models are often found biased toward identity terms which are terms characterizing a specific group of people such as \"Muslim\" and \"black\". Such bias is commonly reflected in false-positive predictions, i.e. non-toxic comments with identity terms. In this work, we propose a novel approach to tackle such bias in toxic comment classification, leveraging the notion of subjectivity level of a comment and the presence of identity terms. We hypothesize that when a comment is made about a group of people that is characterized by an identity term, the likelihood of that co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02691","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.02691/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":"2026-07-05T05:06:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ax7HEPHQIKKRGaAj0lpGs+sPDPM0xDdWiZGRPZh21meMDAYx+QruqAXW9PFdYp7biCJxv5J71oIkfHA9FX14Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T11:42:04.879328Z"},"content_sha256":"378eab1a5749c795e85a1751acb2fd99ca8c3155efe638b0cfec2546d8df8bf1","schema_version":"1.0","event_id":"sha256:378eab1a5749c795e85a1751acb2fd99ca8c3155efe638b0cfec2546d8df8bf1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EY37HIVNFT4CM4H7WCOZHSIZ2G/bundle.json","state_url":"https://pith.science/pith/EY37HIVNFT4CM4H7WCOZHSIZ2G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EY37HIVNFT4CM4H7WCOZHSIZ2G/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":"2026-08-13T11:42:04Z","links":{"resolver":"https://pith.science/pith/EY37HIVNFT4CM4H7WCOZHSIZ2G","bundle":"https://pith.science/pith/EY37HIVNFT4CM4H7WCOZHSIZ2G/bundle.json","state":"https://pith.science/pith/EY37HIVNFT4CM4H7WCOZHSIZ2G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EY37HIVNFT4CM4H7WCOZHSIZ2G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EY37HIVNFT4CM4H7WCOZHSIZ2G","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":"38b67c6c9435f23bf1a5b82fce9c1692c61b666c04dd14c796b185487e249d23","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-06T18:40:06Z","title_canon_sha256":"4d9e22191633d337d0d435ff6094ec26574523c6a070f1347b270258fb10ba38"},"schema_version":"1.0","source":{"id":"2109.02691","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.02691","created_at":"2026-07-05T05:06:52Z"},{"alias_kind":"arxiv_version","alias_value":"2109.02691v1","created_at":"2026-07-05T05:06:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02691","created_at":"2026-07-05T05:06:52Z"},{"alias_kind":"pith_short_12","alias_value":"EY37HIVNFT4C","created_at":"2026-07-05T05:06:52Z"},{"alias_kind":"pith_short_16","alias_value":"EY37HIVNFT4CM4H7","created_at":"2026-07-05T05:06:52Z"},{"alias_kind":"pith_short_8","alias_value":"EY37HIVN","created_at":"2026-07-05T05:06:52Z"}],"graph_snapshots":[{"event_id":"sha256:378eab1a5749c795e85a1751acb2fd99ca8c3155efe638b0cfec2546d8df8bf1","target":"graph","created_at":"2026-07-05T05:06:52Z","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/2109.02691/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Toxic comment classification models are often found biased toward identity terms which are terms characterizing a specific group of people such as \"Muslim\" and \"black\". Such bias is commonly reflected in false-positive predictions, i.e. non-toxic comments with identity terms. In this work, we propose a novel approach to tackle such bias in toxic comment classification, leveraging the notion of subjectivity level of a comment and the presence of identity terms. We hypothesize that when a comment is made about a group of people that is characterized by an identity term, the likelihood of that co","authors_text":"Frank Hopfgartner, Zhixue Zhao, Ziqi Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-06T18:40:06Z","title":"SS-BERT: Mitigating Identity Terms Bias in Toxic Comment Classification by Utilising the Notion of \"Subjectivity\" and \"Identity Terms\""},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02691","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":"sha256:6a003f45d4e16f7ad44297870ef75018d4c0e1d8fcd40565cabf8cfa8516a88f","target":"record","created_at":"2026-07-05T05:06:52Z","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":"38b67c6c9435f23bf1a5b82fce9c1692c61b666c04dd14c796b185487e249d23","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-06T18:40:06Z","title_canon_sha256":"4d9e22191633d337d0d435ff6094ec26574523c6a070f1347b270258fb10ba38"},"schema_version":"1.0","source":{"id":"2109.02691","kind":"arxiv","version":1}},"canonical_sha256":"2637f3a2ad2cf82670ffb09d93c919d198abbe7735fa52ebe2f72c1d721189a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2637f3a2ad2cf82670ffb09d93c919d198abbe7735fa52ebe2f72c1d721189a6","first_computed_at":"2026-07-05T05:06:52.143623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:52.143623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fY2Of5nrbcLHTNb7SC2iE84zyq76IWt66fqgHrqHh0FN7Vrcw8t4V1uSAVGvY5X2Zp824oIJ1H2PY02eIqgLAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:52.143979Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.02691","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a003f45d4e16f7ad44297870ef75018d4c0e1d8fcd40565cabf8cfa8516a88f","sha256:378eab1a5749c795e85a1751acb2fd99ca8c3155efe638b0cfec2546d8df8bf1"],"state_sha256":"5bb672b7ee81d0505cefacf088e39b8b98b6a75910ecb37bd148658d60b22838"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q+1aHtU1pDsplrHdLln4w3SsmR0kK8j/JFiy4qicuCpN7F/e1k6NOdDIxuSUcwGQvKaIosCUCZqaygmquZj8DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T11:42:04.884129Z","bundle_sha256":"23c130793f5f952214b73d99958b3605af3d458a30d1b3d11606e4d542892050"}}