{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PRFSMRN3KT2ZYLPMCBPYAW5IDF","short_pith_number":"pith:PRFSMRN3","schema_version":"1.0","canonical_sha256":"7c4b2645bb54f59c2dec105f805ba8196b48f69a1b439917b29fba51f0279664","source":{"kind":"arxiv","id":"2507.02950","version":2},"attestation_state":"computed","paper":{"title":"Evaluating AI Counseling in Japanese: Counselor, Client, and Evaluator Roles Assessed by Motivational Interviewing Criteria","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Hideyuki Goto, Izumi Sezai, Keita Kiuchi, Makoto Nishimura, Tomonori Hosokawa, Yoshikazu Fujimoto, Yosuke Sato","submitted_at":"2025-06-28T21:50:29Z","abstract_excerpt":"This study provides the first comprehensive evaluation of large language model (LLM) performance across three counseling roles in Japanese-language therapeutic contexts. We simultaneously assessed counselor artificial intelligence (AI) systems (GPT-4-turbo with zeroshot prompting or Structured Multi-step Dialogue Prompts (SMDP), Claude-3-Opus-SMDP), client AI simulations, and evaluation AI systems (o3, Claude-3.7-Sonnet, Gemini-2.5-pro). Human experts (n = 15) with extensive counseling experience evaluated AI-generated dialogues using the Motivational Interviewing Treatment Integrity (MITI) Co"},"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":"2507.02950","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-28T21:50:29Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"b6742acfa841316a77f19a63b4661d49f0b47a8ac21bf83e921fc27011f13c85","abstract_canon_sha256":"cf933c615f52baeb3706880a85735fd6ef7d261cf1b193d91c029bf39f4a9395"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:26.037618Z","signature_b64":"1EKY1oOGy40CQBWDNkRjM/urU0CeOzNPaQuFHOvZ/RJLlsoHKhkYRU53TiJswEFuqIlQc9RetPPyed0yW2l7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c4b2645bb54f59c2dec105f805ba8196b48f69a1b439917b29fba51f0279664","last_reissued_at":"2026-07-05T11:33:26.037138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:26.037138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating AI Counseling in Japanese: Counselor, Client, and Evaluator Roles Assessed by Motivational Interviewing Criteria","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Hideyuki Goto, Izumi Sezai, Keita Kiuchi, Makoto Nishimura, Tomonori Hosokawa, Yoshikazu Fujimoto, Yosuke Sato","submitted_at":"2025-06-28T21:50:29Z","abstract_excerpt":"This study provides the first comprehensive evaluation of large language model (LLM) performance across three counseling roles in Japanese-language therapeutic contexts. We simultaneously assessed counselor artificial intelligence (AI) systems (GPT-4-turbo with zeroshot prompting or Structured Multi-step Dialogue Prompts (SMDP), Claude-3-Opus-SMDP), client AI simulations, and evaluation AI systems (o3, Claude-3.7-Sonnet, Gemini-2.5-pro). Human experts (n = 15) with extensive counseling experience evaluated AI-generated dialogues using the Motivational Interviewing Treatment Integrity (MITI) Co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02950","kind":"arxiv","version":2},"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/2507.02950/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":"2507.02950","created_at":"2026-07-05T11:33:26.037195+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02950v2","created_at":"2026-07-05T11:33:26.037195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02950","created_at":"2026-07-05T11:33:26.037195+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRFSMRN3KT2Z","created_at":"2026-07-05T11:33:26.037195+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRFSMRN3KT2ZYLPM","created_at":"2026-07-05T11:33:26.037195+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRFSMRN3","created_at":"2026-07-05T11:33:26.037195+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/PRFSMRN3KT2ZYLPMCBPYAW5IDF","json":"https://pith.science/pith/PRFSMRN3KT2ZYLPMCBPYAW5IDF.json","graph_json":"https://pith.science/api/pith-number/PRFSMRN3KT2ZYLPMCBPYAW5IDF/graph.json","events_json":"https://pith.science/api/pith-number/PRFSMRN3KT2ZYLPMCBPYAW5IDF/events.json","paper":"https://pith.science/paper/PRFSMRN3"},"agent_actions":{"view_html":"https://pith.science/pith/PRFSMRN3KT2ZYLPMCBPYAW5IDF","download_json":"https://pith.science/pith/PRFSMRN3KT2ZYLPMCBPYAW5IDF.json","view_paper":"https://pith.science/paper/PRFSMRN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02950&json=true","fetch_graph":"https://pith.science/api/pith-number/PRFSMRN3KT2ZYLPMCBPYAW5IDF/graph.json","fetch_events":"https://pith.science/api/pith-number/PRFSMRN3KT2ZYLPMCBPYAW5IDF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRFSMRN3KT2ZYLPMCBPYAW5IDF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRFSMRN3KT2ZYLPMCBPYAW5IDF/action/storage_attestation","attest_author":"https://pith.science/pith/PRFSMRN3KT2ZYLPMCBPYAW5IDF/action/author_attestation","sign_citation":"https://pith.science/pith/PRFSMRN3KT2ZYLPMCBPYAW5IDF/action/citation_signature","submit_replication":"https://pith.science/pith/PRFSMRN3KT2ZYLPMCBPYAW5IDF/action/replication_record"}},"created_at":"2026-07-05T11:33:26.037195+00:00","updated_at":"2026-07-05T11:33:26.037195+00:00"}