{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CPK5CJCYMCH37DWBKILA4LU5AS","short_pith_number":"pith:CPK5CJCY","schema_version":"1.0","canonical_sha256":"13d5d12458608fbf8ec152160e2e9d04afb19e72583c4b74d0ab952953ff45f6","source":{"kind":"arxiv","id":"2505.17380","version":1},"attestation_state":"computed","paper":{"title":"AI-Augmented LLMs Achieve Therapist-Level Responses in Motivational Interviewing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hui Liu, Weiqing Li, Xiangen Hu, Yinghui Huang, Yixin Cai, Yuxuan Jiang","submitted_at":"2025-05-23T01:33:04Z","abstract_excerpt":"Large language models (LLMs) like GPT-4 show potential for scaling motivational interviewing (MI) in addiction care, but require systematic evaluation of therapeutic capabilities. We present a computational framework assessing user-perceived quality (UPQ) through expected and unexpected MI behaviors. Analyzing human therapist and GPT-4 MI sessions via human-AI collaboration, we developed predictive models integrating deep learning and explainable AI to identify 17 MI-consistent (MICO) and MI-inconsistent (MIIN) behavioral metrics. A customized chain-of-thought prompt improved GPT-4's MI perfor"},"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":"2505.17380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T01:33:04Z","cross_cats_sorted":[],"title_canon_sha256":"509eab2db9c0b9e47dbb2b2f971e40d3856825cbfd068a5fbdf4a9c27f95d8cf","abstract_canon_sha256":"02e925cb9702453a2d1de6d076f27ad3e255463c429f74d4d69db1e1b56bb989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:25.041504Z","signature_b64":"4xb69dzMQc05gvFN4vkzCHO5co3+AxdGp7/HQQglYmmj6Wva9IH4YpHQhM3wMEsdDK/Ov6zKsvu7htIwXccGAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13d5d12458608fbf8ec152160e2e9d04afb19e72583c4b74d0ab952953ff45f6","last_reissued_at":"2026-07-05T11:08:25.041031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:25.041031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI-Augmented LLMs Achieve Therapist-Level Responses in Motivational Interviewing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hui Liu, Weiqing Li, Xiangen Hu, Yinghui Huang, Yixin Cai, Yuxuan Jiang","submitted_at":"2025-05-23T01:33:04Z","abstract_excerpt":"Large language models (LLMs) like GPT-4 show potential for scaling motivational interviewing (MI) in addiction care, but require systematic evaluation of therapeutic capabilities. We present a computational framework assessing user-perceived quality (UPQ) through expected and unexpected MI behaviors. Analyzing human therapist and GPT-4 MI sessions via human-AI collaboration, we developed predictive models integrating deep learning and explainable AI to identify 17 MI-consistent (MICO) and MI-inconsistent (MIIN) behavioral metrics. A customized chain-of-thought prompt improved GPT-4's MI perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17380","kind":"arxiv","version":1},"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/2505.17380/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":"2505.17380","created_at":"2026-07-05T11:08:25.041091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17380v1","created_at":"2026-07-05T11:08:25.041091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17380","created_at":"2026-07-05T11:08:25.041091+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPK5CJCYMCH3","created_at":"2026-07-05T11:08:25.041091+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPK5CJCYMCH37DWB","created_at":"2026-07-05T11:08:25.041091+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPK5CJCY","created_at":"2026-07-05T11:08:25.041091+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/CPK5CJCYMCH37DWBKILA4LU5AS","json":"https://pith.science/pith/CPK5CJCYMCH37DWBKILA4LU5AS.json","graph_json":"https://pith.science/api/pith-number/CPK5CJCYMCH37DWBKILA4LU5AS/graph.json","events_json":"https://pith.science/api/pith-number/CPK5CJCYMCH37DWBKILA4LU5AS/events.json","paper":"https://pith.science/paper/CPK5CJCY"},"agent_actions":{"view_html":"https://pith.science/pith/CPK5CJCYMCH37DWBKILA4LU5AS","download_json":"https://pith.science/pith/CPK5CJCYMCH37DWBKILA4LU5AS.json","view_paper":"https://pith.science/paper/CPK5CJCY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17380&json=true","fetch_graph":"https://pith.science/api/pith-number/CPK5CJCYMCH37DWBKILA4LU5AS/graph.json","fetch_events":"https://pith.science/api/pith-number/CPK5CJCYMCH37DWBKILA4LU5AS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPK5CJCYMCH37DWBKILA4LU5AS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPK5CJCYMCH37DWBKILA4LU5AS/action/storage_attestation","attest_author":"https://pith.science/pith/CPK5CJCYMCH37DWBKILA4LU5AS/action/author_attestation","sign_citation":"https://pith.science/pith/CPK5CJCYMCH37DWBKILA4LU5AS/action/citation_signature","submit_replication":"https://pith.science/pith/CPK5CJCYMCH37DWBKILA4LU5AS/action/replication_record"}},"created_at":"2026-07-05T11:08:25.041091+00:00","updated_at":"2026-07-05T11:08:25.041091+00:00"}