{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MDPN5MPYQOMHJFRYKKNXTJSXUZ","short_pith_number":"pith:MDPN5MPY","schema_version":"1.0","canonical_sha256":"60dedeb1f88398749638529b79a657a64b58f4147d9ffbbc51691ca3e910deea","source":{"kind":"arxiv","id":"2403.09705","version":1},"attestation_state":"computed","paper":{"title":"A Novel Nuanced Conversation Evaluation Framework for Large Language Models in Mental Health","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.ET"],"primary_cat":"cs.CL","authors_text":"Alexander Marrapese, Basem Suleiman, Imdad Ullah, Juno Kim","submitted_at":"2024-03-08T23:46:37Z","abstract_excerpt":"Understanding the conversation abilities of Large Language Models (LLMs) can help lead to its more cautious and appropriate deployment. This is especially important for safety-critical domains like mental health, where someone's life may depend on the exact wording of a response to an urgent question. In this paper, we propose a novel framework for evaluating the nuanced conversation abilities of LLMs. Within it, we develop a series of quantitative metrics developed from literature on using psychotherapy conversation analysis literature. While we ensure that our framework and metrics are trans"},"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":"2403.09705","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-08T23:46:37Z","cross_cats_sorted":["cs.AI","cs.ET"],"title_canon_sha256":"8f6b4b46350962c1ef54a77e932725b82c4431fdcac1eb1951acac5cbc690796","abstract_canon_sha256":"fa3b70d84774b9eee1489ab23bb6a2e0798482bb8600aa3f8b957bd6be43087c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:23.683559Z","signature_b64":"Hx3quz6cUBwPmbBM9mGO5is2AcD7QlfoBmqNOeyqL2U8iKbD4JYp6fQRJudAX+3/TNtUyy9CKV4xJYssH9k+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60dedeb1f88398749638529b79a657a64b58f4147d9ffbbc51691ca3e910deea","last_reissued_at":"2026-07-05T07:56:23.683169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:23.683169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Novel Nuanced Conversation Evaluation Framework for Large Language Models in Mental Health","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.ET"],"primary_cat":"cs.CL","authors_text":"Alexander Marrapese, Basem Suleiman, Imdad Ullah, Juno Kim","submitted_at":"2024-03-08T23:46:37Z","abstract_excerpt":"Understanding the conversation abilities of Large Language Models (LLMs) can help lead to its more cautious and appropriate deployment. This is especially important for safety-critical domains like mental health, where someone's life may depend on the exact wording of a response to an urgent question. In this paper, we propose a novel framework for evaluating the nuanced conversation abilities of LLMs. Within it, we develop a series of quantitative metrics developed from literature on using psychotherapy conversation analysis literature. While we ensure that our framework and metrics are trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09705","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/2403.09705/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":"2403.09705","created_at":"2026-07-05T07:56:23.683229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09705v1","created_at":"2026-07-05T07:56:23.683229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09705","created_at":"2026-07-05T07:56:23.683229+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDPN5MPYQOMH","created_at":"2026-07-05T07:56:23.683229+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDPN5MPYQOMHJFRY","created_at":"2026-07-05T07:56:23.683229+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDPN5MPY","created_at":"2026-07-05T07:56:23.683229+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/MDPN5MPYQOMHJFRYKKNXTJSXUZ","json":"https://pith.science/pith/MDPN5MPYQOMHJFRYKKNXTJSXUZ.json","graph_json":"https://pith.science/api/pith-number/MDPN5MPYQOMHJFRYKKNXTJSXUZ/graph.json","events_json":"https://pith.science/api/pith-number/MDPN5MPYQOMHJFRYKKNXTJSXUZ/events.json","paper":"https://pith.science/paper/MDPN5MPY"},"agent_actions":{"view_html":"https://pith.science/pith/MDPN5MPYQOMHJFRYKKNXTJSXUZ","download_json":"https://pith.science/pith/MDPN5MPYQOMHJFRYKKNXTJSXUZ.json","view_paper":"https://pith.science/paper/MDPN5MPY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09705&json=true","fetch_graph":"https://pith.science/api/pith-number/MDPN5MPYQOMHJFRYKKNXTJSXUZ/graph.json","fetch_events":"https://pith.science/api/pith-number/MDPN5MPYQOMHJFRYKKNXTJSXUZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDPN5MPYQOMHJFRYKKNXTJSXUZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDPN5MPYQOMHJFRYKKNXTJSXUZ/action/storage_attestation","attest_author":"https://pith.science/pith/MDPN5MPYQOMHJFRYKKNXTJSXUZ/action/author_attestation","sign_citation":"https://pith.science/pith/MDPN5MPYQOMHJFRYKKNXTJSXUZ/action/citation_signature","submit_replication":"https://pith.science/pith/MDPN5MPYQOMHJFRYKKNXTJSXUZ/action/replication_record"}},"created_at":"2026-07-05T07:56:23.683229+00:00","updated_at":"2026-07-05T07:56:23.683229+00:00"}