{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2JQNABLZE5KDXC7HBXM2Y42RJ5","short_pith_number":"pith:2JQNABLZ","schema_version":"1.0","canonical_sha256":"d260d0057927543b8be70dd9ac73514f635d793f4ba4f5457ce7c5299c84f03e","source":{"kind":"arxiv","id":"2505.03293","version":1},"attestation_state":"computed","paper":{"title":"{\\Psi}-Arena: Interactive Assessment and Optimization of LLM-based Psychological Counselors with Tripartite Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binghang Li, Dazhen Wan, Fangfang Li, Guanqun Bi, Libiao Peng, Minlie Huang, Rongsheng Zhang, Shijing Zhu, Tangjie Lv, Xiyao Xiao, Yaxi Deng, Zhipeng Hu, Zhuang Chen","submitted_at":"2025-05-06T08:22:51Z","abstract_excerpt":"Large language models (LLMs) have shown promise in providing scalable mental health support, while evaluating their counseling capability remains crucial to ensure both efficacy and safety. Existing evaluations are limited by the static assessment that focuses on knowledge tests, the single perspective that centers on user experience, and the open-loop framework that lacks actionable feedback. To address these issues, we propose {\\Psi}-Arena, an interactive framework for comprehensive assessment and optimization of LLM-based counselors, featuring three key characteristics: (1) Realistic arena "},"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":"2505.03293","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-06T08:22:51Z","cross_cats_sorted":[],"title_canon_sha256":"ed84957e97ad0658f6fa732ef6fa5f977dce7f80b1a48cfb8a8d128cb20d4d3f","abstract_canon_sha256":"fc274518a4694037b06a93e65c2beb383914d35f709a0ea06ff59fbe7c6a33c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:13.516842Z","signature_b64":"BDxws9HbdC/VO9MpC9Si9nmbYbmG2fW0PW6I03O0zdI76GT6NLbVTvcxVd7k+IrADJ7xpIhczNTi2l5cKkjiBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d260d0057927543b8be70dd9ac73514f635d793f4ba4f5457ce7c5299c84f03e","last_reissued_at":"2026-07-05T10:59:13.516361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:13.516361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"{\\Psi}-Arena: Interactive Assessment and Optimization of LLM-based Psychological Counselors with Tripartite Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binghang Li, Dazhen Wan, Fangfang Li, Guanqun Bi, Libiao Peng, Minlie Huang, Rongsheng Zhang, Shijing Zhu, Tangjie Lv, Xiyao Xiao, Yaxi Deng, Zhipeng Hu, Zhuang Chen","submitted_at":"2025-05-06T08:22:51Z","abstract_excerpt":"Large language models (LLMs) have shown promise in providing scalable mental health support, while evaluating their counseling capability remains crucial to ensure both efficacy and safety. Existing evaluations are limited by the static assessment that focuses on knowledge tests, the single perspective that centers on user experience, and the open-loop framework that lacks actionable feedback. To address these issues, we propose {\\Psi}-Arena, an interactive framework for comprehensive assessment and optimization of LLM-based counselors, featuring three key characteristics: (1) Realistic arena "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03293","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/2505.03293/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":"2505.03293","created_at":"2026-07-05T10:59:13.516422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03293v1","created_at":"2026-07-05T10:59:13.516422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03293","created_at":"2026-07-05T10:59:13.516422+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JQNABLZE5KD","created_at":"2026-07-05T10:59:13.516422+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JQNABLZE5KDXC7H","created_at":"2026-07-05T10:59:13.516422+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JQNABLZ","created_at":"2026-07-05T10:59:13.516422+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02713","citing_title":"Breakdowns in Conversational AI: Interactional Failures in Emotionally and Ethically Sensitive Contexts","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2JQNABLZE5KDXC7HBXM2Y42RJ5","json":"https://pith.science/pith/2JQNABLZE5KDXC7HBXM2Y42RJ5.json","graph_json":"https://pith.science/api/pith-number/2JQNABLZE5KDXC7HBXM2Y42RJ5/graph.json","events_json":"https://pith.science/api/pith-number/2JQNABLZE5KDXC7HBXM2Y42RJ5/events.json","paper":"https://pith.science/paper/2JQNABLZ"},"agent_actions":{"view_html":"https://pith.science/pith/2JQNABLZE5KDXC7HBXM2Y42RJ5","download_json":"https://pith.science/pith/2JQNABLZE5KDXC7HBXM2Y42RJ5.json","view_paper":"https://pith.science/paper/2JQNABLZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03293&json=true","fetch_graph":"https://pith.science/api/pith-number/2JQNABLZE5KDXC7HBXM2Y42RJ5/graph.json","fetch_events":"https://pith.science/api/pith-number/2JQNABLZE5KDXC7HBXM2Y42RJ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JQNABLZE5KDXC7HBXM2Y42RJ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JQNABLZE5KDXC7HBXM2Y42RJ5/action/storage_attestation","attest_author":"https://pith.science/pith/2JQNABLZE5KDXC7HBXM2Y42RJ5/action/author_attestation","sign_citation":"https://pith.science/pith/2JQNABLZE5KDXC7HBXM2Y42RJ5/action/citation_signature","submit_replication":"https://pith.science/pith/2JQNABLZE5KDXC7HBXM2Y42RJ5/action/replication_record"}},"created_at":"2026-07-05T10:59:13.516422+00:00","updated_at":"2026-07-05T10:59:13.516422+00:00"}