{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I5P4WB5BHWGNV76VRFHGSEMJQU","short_pith_number":"pith:I5P4WB5B","schema_version":"1.0","canonical_sha256":"475fcb07a13d8cdaffd5894e69118985084e5554a8c5799d3dd8c91f733f3e65","source":{"kind":"arxiv","id":"2502.00025","version":4},"attestation_state":"computed","paper":{"title":"Explainable AI for Mental Health Emergency Returns: Integrating LLMs with Predictive Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"Abdulaziz Ahmed, Ahmed Alhassan, Badari Birur, Bradley G Burk, Mohammad Saleem, Mohammed Ali Al-Garadi, Mohammed Alzeen, Rachel E Fargason","submitted_at":"2025-01-21T15:41:20Z","abstract_excerpt":"Importance: Emergency department (ED) returns for mental health conditions pose a major healthcare burden, with 24-27% of patients returning within 30 days. Traditional machine learning models for predicting these returns often lack interpretability for clinical use.\n  Objective: To assess whether integrating large language models (LLMs) with machine learning improves predictive accuracy and clinical interpretability of ED mental health return risk models.\n  Methods: This retrospective cohort study analyzed 42,464 ED visits for 27,904 unique mental health patients at an academic medical center"},"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":"2502.00025","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T15:41:20Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"096305f34ec5ec7333f7e168f95762c57604ac091accda224d52f2e67022c631","abstract_canon_sha256":"06ca702e41730120351c3ac3c72ca4ae62a30c02e322312aba6a8964c29e3e60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:24.034984Z","signature_b64":"xZWVL+hkesmH/eVwwm9Ugi0MNN12L5jpCYIsYfpusj83BJcqq622H3baHKhoy/vVGy8/rTKZlnapmEfhq13wDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"475fcb07a13d8cdaffd5894e69118985084e5554a8c5799d3dd8c91f733f3e65","last_reissued_at":"2026-07-05T11:32:24.034474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:24.034474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explainable AI for Mental Health Emergency Returns: Integrating LLMs with Predictive Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"Abdulaziz Ahmed, Ahmed Alhassan, Badari Birur, Bradley G Burk, Mohammad Saleem, Mohammed Ali Al-Garadi, Mohammed Alzeen, Rachel E Fargason","submitted_at":"2025-01-21T15:41:20Z","abstract_excerpt":"Importance: Emergency department (ED) returns for mental health conditions pose a major healthcare burden, with 24-27% of patients returning within 30 days. Traditional machine learning models for predicting these returns often lack interpretability for clinical use.\n  Objective: To assess whether integrating large language models (LLMs) with machine learning improves predictive accuracy and clinical interpretability of ED mental health return risk models.\n  Methods: This retrospective cohort study analyzed 42,464 ED visits for 27,904 unique mental health patients at an academic medical center"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00025","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/2502.00025/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":"2502.00025","created_at":"2026-07-05T11:32:24.034537+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00025v4","created_at":"2026-07-05T11:32:24.034537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00025","created_at":"2026-07-05T11:32:24.034537+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5P4WB5BHWGN","created_at":"2026-07-05T11:32:24.034537+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5P4WB5BHWGNV76V","created_at":"2026-07-05T11:32:24.034537+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5P4WB5B","created_at":"2026-07-05T11:32:24.034537+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17209","citing_title":"HypoChainer: A Collaborative System Combining LLMs and Knowledge Graphs for Hypothesis-Driven Scientific Discovery","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I5P4WB5BHWGNV76VRFHGSEMJQU","json":"https://pith.science/pith/I5P4WB5BHWGNV76VRFHGSEMJQU.json","graph_json":"https://pith.science/api/pith-number/I5P4WB5BHWGNV76VRFHGSEMJQU/graph.json","events_json":"https://pith.science/api/pith-number/I5P4WB5BHWGNV76VRFHGSEMJQU/events.json","paper":"https://pith.science/paper/I5P4WB5B"},"agent_actions":{"view_html":"https://pith.science/pith/I5P4WB5BHWGNV76VRFHGSEMJQU","download_json":"https://pith.science/pith/I5P4WB5BHWGNV76VRFHGSEMJQU.json","view_paper":"https://pith.science/paper/I5P4WB5B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00025&json=true","fetch_graph":"https://pith.science/api/pith-number/I5P4WB5BHWGNV76VRFHGSEMJQU/graph.json","fetch_events":"https://pith.science/api/pith-number/I5P4WB5BHWGNV76VRFHGSEMJQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5P4WB5BHWGNV76VRFHGSEMJQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5P4WB5BHWGNV76VRFHGSEMJQU/action/storage_attestation","attest_author":"https://pith.science/pith/I5P4WB5BHWGNV76VRFHGSEMJQU/action/author_attestation","sign_citation":"https://pith.science/pith/I5P4WB5BHWGNV76VRFHGSEMJQU/action/citation_signature","submit_replication":"https://pith.science/pith/I5P4WB5BHWGNV76VRFHGSEMJQU/action/replication_record"}},"created_at":"2026-07-05T11:32:24.034537+00:00","updated_at":"2026-07-05T11:32:24.034537+00:00"}