{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4OW4S2K7BWYDM7GHCYZQNME62H","short_pith_number":"pith:4OW4S2K7","schema_version":"1.0","canonical_sha256":"e3adc9695f0db0367cc7163306b09ed1e359a321f64f26e27838df67fd31d70b","source":{"kind":"arxiv","id":"2305.13589","version":1},"attestation_state":"computed","paper":{"title":"BiasX: \"Thinking Slow\" in Toxic Content Moderation with Explanations of Implied Social Biases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liwei Jiang, Maarten Sap, Sravani Nanduri, Tongshuang Wu, Yiming Zhang","submitted_at":"2023-05-23T01:45:18Z","abstract_excerpt":"Toxicity annotators and content moderators often default to mental shortcuts when making decisions. This can lead to subtle toxicity being missed, and seemingly toxic but harmless content being over-detected. We introduce BiasX, a framework that enhances content moderation setups with free-text explanations of statements' implied social biases, and explore its effectiveness through a large-scale crowdsourced user study. We show that indeed, participants substantially benefit from explanations for correctly identifying subtly (non-)toxic content. The quality of explanations is critical: imperfe"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.13589","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T01:45:18Z","cross_cats_sorted":[],"title_canon_sha256":"f251f16826abc2e93c3f507eed978d97e92f7d40ecaf26b65fa929bf3aadd1f1","abstract_canon_sha256":"c561a4d6ce917d12c100dfaa177079c99c26c5ed767eea5eacecdb32c69d29b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:54.693410Z","signature_b64":"hEkO3r+3DiI/dEDAnocuKKG5V15FxGaegYe3pQgFZl8z0hzw3N9XUbtaeL76koBlHAbvAEbEv2gqwDLmkupqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3adc9695f0db0367cc7163306b09ed1e359a321f64f26e27838df67fd31d70b","last_reissued_at":"2026-07-05T06:12:54.692985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:54.692985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BiasX: \"Thinking Slow\" in Toxic Content Moderation with Explanations of Implied Social Biases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liwei Jiang, Maarten Sap, Sravani Nanduri, Tongshuang Wu, Yiming Zhang","submitted_at":"2023-05-23T01:45:18Z","abstract_excerpt":"Toxicity annotators and content moderators often default to mental shortcuts when making decisions. This can lead to subtle toxicity being missed, and seemingly toxic but harmless content being over-detected. We introduce BiasX, a framework that enhances content moderation setups with free-text explanations of statements' implied social biases, and explore its effectiveness through a large-scale crowdsourced user study. We show that indeed, participants substantially benefit from explanations for correctly identifying subtly (non-)toxic content. The quality of explanations is critical: imperfe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13589","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/2305.13589/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.13589","created_at":"2026-07-05T06:12:54.693042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13589v1","created_at":"2026-07-05T06:12:54.693042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13589","created_at":"2026-07-05T06:12:54.693042+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OW4S2K7BWYD","created_at":"2026-07-05T06:12:54.693042+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OW4S2K7BWYDM7GH","created_at":"2026-07-05T06:12:54.693042+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OW4S2K7","created_at":"2026-07-05T06:12:54.693042+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09004","citing_title":"Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OW4S2K7BWYDM7GHCYZQNME62H","json":"https://pith.science/pith/4OW4S2K7BWYDM7GHCYZQNME62H.json","graph_json":"https://pith.science/api/pith-number/4OW4S2K7BWYDM7GHCYZQNME62H/graph.json","events_json":"https://pith.science/api/pith-number/4OW4S2K7BWYDM7GHCYZQNME62H/events.json","paper":"https://pith.science/paper/4OW4S2K7"},"agent_actions":{"view_html":"https://pith.science/pith/4OW4S2K7BWYDM7GHCYZQNME62H","download_json":"https://pith.science/pith/4OW4S2K7BWYDM7GHCYZQNME62H.json","view_paper":"https://pith.science/paper/4OW4S2K7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13589&json=true","fetch_graph":"https://pith.science/api/pith-number/4OW4S2K7BWYDM7GHCYZQNME62H/graph.json","fetch_events":"https://pith.science/api/pith-number/4OW4S2K7BWYDM7GHCYZQNME62H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OW4S2K7BWYDM7GHCYZQNME62H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OW4S2K7BWYDM7GHCYZQNME62H/action/storage_attestation","attest_author":"https://pith.science/pith/4OW4S2K7BWYDM7GHCYZQNME62H/action/author_attestation","sign_citation":"https://pith.science/pith/4OW4S2K7BWYDM7GHCYZQNME62H/action/citation_signature","submit_replication":"https://pith.science/pith/4OW4S2K7BWYDM7GHCYZQNME62H/action/replication_record"}},"created_at":"2026-07-05T06:12:54.693042+00:00","updated_at":"2026-07-05T06:12:54.693042+00:00"}