{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ADCAF7KKTM7XJ26CXXM6BDPNCP","short_pith_number":"pith:ADCAF7KK","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"},"canonical_sha256":"00c402fd4a9b3f74ebc2bdd9e08ded13f16a6ffc4362198d1636b467cedc8c85","source":{"kind":"arxiv","id":"2605.12702","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12702","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12702v1","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12702","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"pith_short_12","alias_value":"ADCAF7KKTM7X","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ADCAF7KKTM7XJ26C","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ADCAF7KK","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ADCAF7KKTM7XJ26CXXM6BDPNCP","target":"record","payload":{"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"},"canonical_sha256":"00c402fd4a9b3f74ebc2bdd9e08ded13f16a6ffc4362198d1636b467cedc8c85","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"},"source_kind":"arxiv","source_id":"2605.12702","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":"2026-05-18T03:09:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9NoVyEIfnAZ+04CubGVybmcDSknuUL1VkFP2yrhvFo/tPKdKhiyM4OVqA3jer+H1wfKQth4fCFK7f3YuHWNlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:03:37.424509Z"},"content_sha256":"895e7421ffacfbf34713c4f006db7ed74d7272f1aa58362d37e86813219e688c","schema_version":"1.0","event_id":"sha256:895e7421ffacfbf34713c4f006db7ed74d7272f1aa58362d37e86813219e688c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ADCAF7KKTM7XJ26CXXM6BDPNCP","target":"graph","payload":{"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"},"verdict_id":"349ab228-6906-4ba6-ae03-4a1dbe6ed5b8"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CGMlTSaloIOHPQMsDr+zaVDFKGXNowHu10VbVTqQACyREAbDgcTEJDfq03Vz7F2tMa3CviAfCcWdOyQB2F4CAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:03:37.425546Z"},"content_sha256":"fb92bd9a095ba02437a61cadb36995d9aee4cd829e9fcf3688716481c2dae3da","schema_version":"1.0","event_id":"sha256:fb92bd9a095ba02437a61cadb36995d9aee4cd829e9fcf3688716481c2dae3da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP/bundle.json","state_url":"https://pith.science/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP/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":"2026-05-25T17:03:37Z","links":{"resolver":"https://pith.science/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP","bundle":"https://pith.science/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP/bundle.json","state":"https://pith.science/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ADCAF7KKTM7XJ26CXXM6BDPNCP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ADCAF7KKTM7XJ26CXXM6BDPNCP","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":"aca6e65451063f282db65bb2f2f61c9c8eb6423de6257f06bc3bd7ecb1e1590f","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T19:56:36Z","title_canon_sha256":"6fb39e2dd6e77e9e25ad22877a79a5e5dfbde489116044bc2c7c23ba3607e569"},"schema_version":"1.0","source":{"id":"2605.12702","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12702","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12702v1","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12702","created_at":"2026-05-18T03:09:49Z"},{"alias_kind":"pith_short_12","alias_value":"ADCAF7KKTM7X","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ADCAF7KKTM7XJ26C","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ADCAF7KK","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:fb92bd9a095ba02437a61cadb36995d9aee4cd829e9fcf3688716481c2dae3da","target":"graph","created_at":"2026-05-18T03:09:49Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"General-purpose safety benchmarks for language models miss disability harms because those harms are personal, intersectional, and community-defined."}],"snapshot_sha256":"59cb294152cf3cfd27f7b2df38e0467e15e27da0e4bf372b65db2927ae39daae"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"527aed6884eedfcc15e216248218a7add859675edd997e3bec68b29faf27fc6f"},"paper":{"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","authors_text":"Christina Mallon, Eugenia Kim, Ioana Tanase","cross_cats":["cs.HC"],"headline":"General-purpose safety benchmarks for language models miss disability harms because those harms are personal, intersectional, and community-defined.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T19:56:36Z","title":"DisaBench: A Participatory Evaluation Framework for Disability Harms in Language Models"},"references":{"count":45,"internal_anchors":2,"resolved_work":45,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"2001 , address =","work_id":"cebb7cbf-88a3-443d-8e4c-9d09cbe97fd6","year":2001},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"2011 , address =","work_id":"50c70b1f-585f-45ed-8329-15ed16da500a","year":2011},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"2024 , howpublished =","work_id":"df930ec5-3ad9-4914-b196-ac7912e6c387","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Applied Sciences , volume =","work_id":"804251fd-cced-4db5-a24a-0dc8a22b30b0","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"American Journal of Orthopsychiatry , volume =","work_id":"a13d9467-45c8-4a44-92d4-3154a709e6ec","year":2023}],"snapshot_sha256":"c3744ef261c58a33edfd5f879d8f6cf4e618da8c39c4579f14ca74c5bc0dcac0"},"source":{"id":"2605.12702","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:05:54.469728Z","id":"349ab228-6906-4ba6-ae03-4a1dbe6ed5b8","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"General-purpose safety benchmarks for language models miss disability harms because those harms are personal, intersectional, and community-defined.","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.","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."}},"verdict_id":"349ab228-6906-4ba6-ae03-4a1dbe6ed5b8"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:895e7421ffacfbf34713c4f006db7ed74d7272f1aa58362d37e86813219e688c","target":"record","created_at":"2026-05-18T03:09:49Z","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":"aca6e65451063f282db65bb2f2f61c9c8eb6423de6257f06bc3bd7ecb1e1590f","cross_cats_sorted":["cs.HC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-12T19:56:36Z","title_canon_sha256":"6fb39e2dd6e77e9e25ad22877a79a5e5dfbde489116044bc2c7c23ba3607e569"},"schema_version":"1.0","source":{"id":"2605.12702","kind":"arxiv","version":1}},"canonical_sha256":"00c402fd4a9b3f74ebc2bdd9e08ded13f16a6ffc4362198d1636b467cedc8c85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00c402fd4a9b3f74ebc2bdd9e08ded13f16a6ffc4362198d1636b467cedc8c85","first_computed_at":"2026-05-18T03:09:49.671324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:49.671324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3YrqMvI9UCPmCiZR+yG3+MREcg6uhDXYha7kXjBxGAbMn+puAlyHLyVo2Gg2iEvPWdh+MnK/gN8SNqhn1A+1DA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:49.672209Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12702","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:895e7421ffacfbf34713c4f006db7ed74d7272f1aa58362d37e86813219e688c","sha256:fb92bd9a095ba02437a61cadb36995d9aee4cd829e9fcf3688716481c2dae3da"],"state_sha256":"f21be862491e960284f47d086d1379a66bc0d8244e822c3bdfcff8efb6145afe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9UlIXBdaWNZeoo2kR8UKfDTi/A+cZjEDYFfRYnuzWbw330kDjXH1fsrX/TvqDs0JDVt26FvFowz8NDMHzqLIBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:03:37.429859Z","bundle_sha256":"b32beae507956101f214bd68cccbe8d98354404a9f9281d8aab9c14f583222c7"}}