{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JMCQJUWDO2TRXGD6KJPZ26O62I","short_pith_number":"pith:JMCQJUWD","schema_version":"1.0","canonical_sha256":"4b0504d2c376a71b987e525f9d79ded23b1e1d4f6f5fb71881369f7cccb69df7","source":{"kind":"arxiv","id":"2602.05088","version":4},"attestation_state":"computed","paper":{"title":"AI Chatbot Suicide Risk Detection and Response: Human Validation Study of the Open-Source VERA-MH Safety Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adam M. Chekroud, Emily J. Ward, Emily R. Dworkin, Emily Van Ark, Kate H. Bentley, Kelly M. Johnston, Luca Belli, Matt Hawrilenko, Millard Brown, Will Alexander","submitted_at":"2026-02-04T22:17:04Z","abstract_excerpt":"Millions of people now use generative AI chatbots for psychological support. Despite their promise, the most pressing question in AI for mental health is whether these tools are safe. The field currently lacks a validated, automated benchmark for evaluating AI chatbot safety, particularly for users at risk of suicide. The Validation of Ethical and Responsible AI in Mental Health (VERA-MH) evaluation was recently proposed to address this need. This human validation study examined the alignment of VERA-MH safety ratings with expert clinician judgments. We simulated conversations between large la"},"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":"2602.05088","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-04T22:17:04Z","cross_cats_sorted":[],"title_canon_sha256":"d8f450ba6d2c50e9ee4f47f41dd8df61423e2fe802de6938b76cf439123c57d1","abstract_canon_sha256":"80b00eb873d44759ce6e01efc2d309d63b7ab4b410a60a5eb7430ba7528493a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T00:19:12.902407Z","signature_b64":"Gb8GEzAosQceGWDE5Evhr5Fcncj7qbxKGLCotxKfS2kR+zCM3o6hRYW3xVO9SM6BCeZ/WN6yFROeZFJoxAI/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b0504d2c376a71b987e525f9d79ded23b1e1d4f6f5fb71881369f7cccb69df7","last_reissued_at":"2026-07-09T00:19:12.901423Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T00:19:12.901423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI Chatbot Suicide Risk Detection and Response: Human Validation Study of the Open-Source VERA-MH Safety Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adam M. Chekroud, Emily J. Ward, Emily R. Dworkin, Emily Van Ark, Kate H. Bentley, Kelly M. Johnston, Luca Belli, Matt Hawrilenko, Millard Brown, Will Alexander","submitted_at":"2026-02-04T22:17:04Z","abstract_excerpt":"Millions of people now use generative AI chatbots for psychological support. Despite their promise, the most pressing question in AI for mental health is whether these tools are safe. The field currently lacks a validated, automated benchmark for evaluating AI chatbot safety, particularly for users at risk of suicide. The Validation of Ethical and Responsible AI in Mental Health (VERA-MH) evaluation was recently proposed to address this need. This human validation study examined the alignment of VERA-MH safety ratings with expert clinician judgments. We simulated conversations between large la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.05088","kind":"arxiv","version":4},"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/2602.05088/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":"2602.05088","created_at":"2026-07-09T00:19:12.901556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.05088v4","created_at":"2026-07-09T00:19:12.901556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.05088","created_at":"2026-07-09T00:19:12.901556+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMCQJUWDO2TR","created_at":"2026-07-09T00:19:12.901556+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMCQJUWDO2TRXGD6","created_at":"2026-07-09T00:19:12.901556+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMCQJUWD","created_at":"2026-07-09T00:19:12.901556+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.00975","citing_title":"Lost in Delusion: Examining LLM Safety Under User Delusions and Distress","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25273","citing_title":"LLM-as-a-Judge in Healthcare: A Scoping Analysis of Applications, Methods, and Human Alignment","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMCQJUWDO2TRXGD6KJPZ26O62I","json":"https://pith.science/pith/JMCQJUWDO2TRXGD6KJPZ26O62I.json","graph_json":"https://pith.science/api/pith-number/JMCQJUWDO2TRXGD6KJPZ26O62I/graph.json","events_json":"https://pith.science/api/pith-number/JMCQJUWDO2TRXGD6KJPZ26O62I/events.json","paper":"https://pith.science/paper/JMCQJUWD"},"agent_actions":{"view_html":"https://pith.science/pith/JMCQJUWDO2TRXGD6KJPZ26O62I","download_json":"https://pith.science/pith/JMCQJUWDO2TRXGD6KJPZ26O62I.json","view_paper":"https://pith.science/paper/JMCQJUWD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.05088&json=true","fetch_graph":"https://pith.science/api/pith-number/JMCQJUWDO2TRXGD6KJPZ26O62I/graph.json","fetch_events":"https://pith.science/api/pith-number/JMCQJUWDO2TRXGD6KJPZ26O62I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMCQJUWDO2TRXGD6KJPZ26O62I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMCQJUWDO2TRXGD6KJPZ26O62I/action/storage_attestation","attest_author":"https://pith.science/pith/JMCQJUWDO2TRXGD6KJPZ26O62I/action/author_attestation","sign_citation":"https://pith.science/pith/JMCQJUWDO2TRXGD6KJPZ26O62I/action/citation_signature","submit_replication":"https://pith.science/pith/JMCQJUWDO2TRXGD6KJPZ26O62I/action/replication_record"}},"created_at":"2026-07-09T00:19:12.901556+00:00","updated_at":"2026-07-09T00:19:12.901556+00:00"}