{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ADCAF7KKTM7XJ26CXXM6BDPNCP","short_pith_number":"pith:ADCAF7KK","schema_version":"1.0","canonical_sha256":"00c402fd4a9b3f74ebc2bdd9e08ded13f16a6ffc4362198d1636b467cedc8c85","source":{"kind":"arxiv","id":"2605.12702","version":1},"attestation_state":"computed","paper":{"title":"DisaBench: A Participatory Evaluation Framework for Disability Harms in Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"General-purpose safety benchmarks for language models miss disability harms because those harms are personal, intersectional, and community-defined.","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Christina Mallon, Eugenia Kim, Ioana Tanase","submitted_at":"2026-05-12T19:56:36Z","abstract_excerpt":"General-purpose safety benchmarks for large language models do not adequately evaluate disability-related harms. We introduce DisaBench: a taxonomy of twelve disability harm categories co-created with people with disabilities and red teaming experts, a taxonomy-driven evaluation methodology that pairs benign and adversarial prompts across seven life domains, and a dataset of 175 prompts with human-annotated labels on 525 prompt-response pairs. Annotation by four evaluators with lived disability experience reveals three findings: harm rates vary sharply by disability type and will compound in n"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.12702","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T19:56:36Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"6fb39e2dd6e77e9e25ad22877a79a5e5dfbde489116044bc2c7c23ba3607e569","abstract_canon_sha256":"aca6e65451063f282db65bb2f2f61c9c8eb6423de6257f06bc3bd7ecb1e1590f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:49.672209Z","signature_b64":"3YrqMvI9UCPmCiZR+yG3+MREcg6uhDXYha7kXjBxGAbMn+puAlyHLyVo2Gg2iEvPWdh+MnK/gN8SNqhn1A+1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00c402fd4a9b3f74ebc2bdd9e08ded13f16a6ffc4362198d1636b467cedc8c85","last_reissued_at":"2026-05-18T03:09:49.671324Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:49.671324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DisaBench: A Participatory Evaluation Framework for Disability Harms in Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"General-purpose safety benchmarks for language models miss disability harms because those harms are personal, intersectional, and community-defined.","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Christina Mallon, Eugenia Kim, Ioana Tanase","submitted_at":"2026-05-12T19:56:36Z","abstract_excerpt":"General-purpose safety benchmarks for large language models do not adequately evaluate disability-related harms. We introduce DisaBench: a taxonomy of twelve disability harm categories co-created with people with disabilities and red teaming experts, a taxonomy-driven evaluation methodology that pairs benign and adversarial prompts across seven life domains, and a dataset of 175 prompts with human-annotated labels on 525 prompt-response pairs. Annotation by four evaluators with lived disability experience reveals three findings: harm rates vary sharply by disability type and will compound in n"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Disability harm is simultaneously personal, intersectional, and community-defined: it cannot be isolated from the full context of who a person is, and general-purpose benchmarks systematically miss it.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The taxonomy and 175 prompts co-created with four evaluators with lived experience are sufficient to capture the range of disability harms across cultures, time, and non-text modalities.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DisaBench supplies a participatory taxonomy of twelve disability harm types, paired benign-adversarial prompts across seven life domains, and human-annotated data showing that standard safety tests miss context-dependent harms.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"General-purpose safety benchmarks for language models miss disability harms because those harms are personal, intersectional, and community-defined.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"59cb294152cf3cfd27f7b2df38e0467e15e27da0e4bf372b65db2927ae39daae"},"source":{"id":"2605.12702","kind":"arxiv","version":1},"verdict":{"id":"349ab228-6906-4ba6-ae03-4a1dbe6ed5b8","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:05:54.469728Z","strongest_claim":"Disability harm is simultaneously personal, intersectional, and community-defined: it cannot be isolated from the full context of who a person is, and general-purpose benchmarks systematically miss it.","one_line_summary":"DisaBench supplies a participatory taxonomy of twelve disability harm types, paired benign-adversarial prompts across seven life domains, and human-annotated data showing that standard safety tests miss context-dependent harms.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The taxonomy and 175 prompts co-created with four evaluators with lived experience are sufficient to capture the range of disability harms across cultures, time, and non-text modalities.","pith_extraction_headline":"General-purpose safety benchmarks for language models miss disability harms because those harms are personal, intersectional, and community-defined."},"references":{"count":45,"sample":[{"doi":"","year":2001,"title":"2001 , address =","work_id":"cebb7cbf-88a3-443d-8e4c-9d09cbe97fd6","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"2011 , address =","work_id":"50c70b1f-585f-45ed-8329-15ed16da500a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"2024 , howpublished =","work_id":"df930ec5-3ad9-4914-b196-ac7912e6c387","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Applied Sciences , volume =","work_id":"804251fd-cced-4db5-a24a-0dc8a22b30b0","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"American Journal of Orthopsychiatry , volume =","work_id":"a13d9467-45c8-4a44-92d4-3154a709e6ec","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":45,"snapshot_sha256":"c3744ef261c58a33edfd5f879d8f6cf4e618da8c39c4579f14ca74c5bc0dcac0","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"527aed6884eedfcc15e216248218a7add859675edd997e3bec68b29faf27fc6f"},"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":"2605.12702","created_at":"2026-05-18T03:09:49.671441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12702v1","created_at":"2026-05-18T03:09:49.671441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12702","created_at":"2026-05-18T03:09:49.671441+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADCAF7KKTM7X","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADCAF7KKTM7XJ26C","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADCAF7KK","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP","json":"https://pith.science/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP.json","graph_json":"https://pith.science/api/pith-number/ADCAF7KKTM7XJ26CXXM6BDPNCP/graph.json","events_json":"https://pith.science/api/pith-number/ADCAF7KKTM7XJ26CXXM6BDPNCP/events.json","paper":"https://pith.science/paper/ADCAF7KK"},"agent_actions":{"view_html":"https://pith.science/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP","download_json":"https://pith.science/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP.json","view_paper":"https://pith.science/paper/ADCAF7KK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12702&json=true","fetch_graph":"https://pith.science/api/pith-number/ADCAF7KKTM7XJ26CXXM6BDPNCP/graph.json","fetch_events":"https://pith.science/api/pith-number/ADCAF7KKTM7XJ26CXXM6BDPNCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP/action/storage_attestation","attest_author":"https://pith.science/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP/action/author_attestation","sign_citation":"https://pith.science/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP/action/citation_signature","submit_replication":"https://pith.science/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP/action/replication_record"}},"created_at":"2026-05-18T03:09:49.671441+00:00","updated_at":"2026-05-18T03:09:49.671441+00:00"}