{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LUNM7OW7EIGYQJJRVGLJLTQCJT","short_pith_number":"pith:LUNM7OW7","schema_version":"1.0","canonical_sha256":"5d1acfbadf220d882531a99695ce024cd84871f3f2df61348361ecbca7129134","source":{"kind":"arxiv","id":"2507.05455","version":2},"attestation_state":"computed","paper":{"title":"ModelCitizens: Representing Community Voices in Online Safety","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashima Suvarna, Christina Chance, Hamid Palangi, Karolina Naranjo, Saadia Gabriel, Sophie Hao, Thomas Hartvigsen","submitted_at":"2025-07-07T20:15:18Z","abstract_excerpt":"Automatic toxic language detection is critical for creating safe, inclusive online spaces. However, it is a highly subjective task, with perceptions of toxic language shaped by community norms and lived experience. Existing toxicity detection models are typically trained on annotations that collapse diverse annotator perspectives into a single ground truth, erasing important context-specific notions of toxicity such as reclaimed language. To address this, we introduce MODELCITIZENS, a dataset of 6.8K social media posts and 40K toxicity annotations across diverse identity groups. To capture the"},"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":"2507.05455","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-07T20:15:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4705e356747bcbb51da5b165dced536a5c9afd4e5b4e1baabe7e2683da1af87e","abstract_canon_sha256":"796755c0807c2352e158398612ec0354e12c296af99c6cc9057e0f9bd1d26149"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:11.762796Z","signature_b64":"A/AX/RUweIAsJGEazgyUyExYhoGWA/9cN64L8oIKKEUWBfL/8cepZO1Tpzsj1QXlkVncH9GT2rue8IAMY/SzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d1acfbadf220d882531a99695ce024cd84871f3f2df61348361ecbca7129134","last_reissued_at":"2026-07-05T11:34:11.762310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:11.762310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ModelCitizens: Representing Community Voices in Online Safety","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashima Suvarna, Christina Chance, Hamid Palangi, Karolina Naranjo, Saadia Gabriel, Sophie Hao, Thomas Hartvigsen","submitted_at":"2025-07-07T20:15:18Z","abstract_excerpt":"Automatic toxic language detection is critical for creating safe, inclusive online spaces. However, it is a highly subjective task, with perceptions of toxic language shaped by community norms and lived experience. Existing toxicity detection models are typically trained on annotations that collapse diverse annotator perspectives into a single ground truth, erasing important context-specific notions of toxicity such as reclaimed language. To address this, we introduce MODELCITIZENS, a dataset of 6.8K social media posts and 40K toxicity annotations across diverse identity groups. To capture the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05455","kind":"arxiv","version":2},"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/2507.05455/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":"2507.05455","created_at":"2026-07-05T11:34:11.762380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05455v2","created_at":"2026-07-05T11:34:11.762380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05455","created_at":"2026-07-05T11:34:11.762380+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUNM7OW7EIGY","created_at":"2026-07-05T11:34:11.762380+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUNM7OW7EIGYQJJR","created_at":"2026-07-05T11:34:11.762380+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUNM7OW7","created_at":"2026-07-05T11:34:11.762380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUNM7OW7EIGYQJJRVGLJLTQCJT","json":"https://pith.science/pith/LUNM7OW7EIGYQJJRVGLJLTQCJT.json","graph_json":"https://pith.science/api/pith-number/LUNM7OW7EIGYQJJRVGLJLTQCJT/graph.json","events_json":"https://pith.science/api/pith-number/LUNM7OW7EIGYQJJRVGLJLTQCJT/events.json","paper":"https://pith.science/paper/LUNM7OW7"},"agent_actions":{"view_html":"https://pith.science/pith/LUNM7OW7EIGYQJJRVGLJLTQCJT","download_json":"https://pith.science/pith/LUNM7OW7EIGYQJJRVGLJLTQCJT.json","view_paper":"https://pith.science/paper/LUNM7OW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05455&json=true","fetch_graph":"https://pith.science/api/pith-number/LUNM7OW7EIGYQJJRVGLJLTQCJT/graph.json","fetch_events":"https://pith.science/api/pith-number/LUNM7OW7EIGYQJJRVGLJLTQCJT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUNM7OW7EIGYQJJRVGLJLTQCJT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUNM7OW7EIGYQJJRVGLJLTQCJT/action/storage_attestation","attest_author":"https://pith.science/pith/LUNM7OW7EIGYQJJRVGLJLTQCJT/action/author_attestation","sign_citation":"https://pith.science/pith/LUNM7OW7EIGYQJJRVGLJLTQCJT/action/citation_signature","submit_replication":"https://pith.science/pith/LUNM7OW7EIGYQJJRVGLJLTQCJT/action/replication_record"}},"created_at":"2026-07-05T11:34:11.762380+00:00","updated_at":"2026-07-05T11:34:11.762380+00:00"}