{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PP7GNQYM6WLG3ZHKMY2GRIK2HE","short_pith_number":"pith:PP7GNQYM","schema_version":"1.0","canonical_sha256":"7bfe66c30cf5966de4ea663468a15a3915abb2e20eb09567e654e9878eeb957a","source":{"kind":"arxiv","id":"2404.16160","version":2},"attestation_state":"computed","paper":{"title":"Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cheng Kang, Daniel Novak, Katerina Urbanova, Yong Hu, Yuqing Cheng","submitted_at":"2024-04-24T19:30:18Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive generalization capabilities on specific tasks with human-written instruction data. However, the limited quantity, diversity, and professional expertise of such instruction data raise concerns about the performance of LLMs in psychotherapy tasks when provided with domain-specific instructions. To address this, we firstly propose Domain-Specific Assistant Instructions based on AlexanderStreet therapy, and secondly, we use an adaption fine-tuning method and retrieval augmented generation method to improve pre-trained LLMs. Through quantita"},"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":"2404.16160","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-24T19:30:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af574e22538cb2ee338a203fc5370700903d29999fbc2311ece4167dd36d03ac","abstract_canon_sha256":"8f7e2d6294a4ed4dfc9abbd1bd69cba1a1c2fc47ab6162a8962ec52c7c3db383"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:18.692474Z","signature_b64":"ebpvJB4kE/EFg4GZnjADQt/wcqrS9/nZ6wi2kXXfVQUngCsLblBjRd/riyLibnlA7PfRwcFg0hq8gHsHVgUDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bfe66c30cf5966de4ea663468a15a3915abb2e20eb09567e654e9878eeb957a","last_reissued_at":"2026-07-05T09:02:18.692040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:18.692040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain-Specific Improvement on Psychotherapy Chatbot Using Assistant","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cheng Kang, Daniel Novak, Katerina Urbanova, Yong Hu, Yuqing Cheng","submitted_at":"2024-04-24T19:30:18Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive generalization capabilities on specific tasks with human-written instruction data. However, the limited quantity, diversity, and professional expertise of such instruction data raise concerns about the performance of LLMs in psychotherapy tasks when provided with domain-specific instructions. To address this, we firstly propose Domain-Specific Assistant Instructions based on AlexanderStreet therapy, and secondly, we use an adaption fine-tuning method and retrieval augmented generation method to improve pre-trained LLMs. Through quantita"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16160","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/2404.16160/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":"2404.16160","created_at":"2026-07-05T09:02:18.692096+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16160v2","created_at":"2026-07-05T09:02:18.692096+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16160","created_at":"2026-07-05T09:02:18.692096+00:00"},{"alias_kind":"pith_short_12","alias_value":"PP7GNQYM6WLG","created_at":"2026-07-05T09:02:18.692096+00:00"},{"alias_kind":"pith_short_16","alias_value":"PP7GNQYM6WLG3ZHK","created_at":"2026-07-05T09:02:18.692096+00:00"},{"alias_kind":"pith_short_8","alias_value":"PP7GNQYM","created_at":"2026-07-05T09:02:18.692096+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04666","citing_title":"Enhancing Health Information Retrieval with RAG by Prioritizing Topical Relevance and Factual Accuracy","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PP7GNQYM6WLG3ZHKMY2GRIK2HE","json":"https://pith.science/pith/PP7GNQYM6WLG3ZHKMY2GRIK2HE.json","graph_json":"https://pith.science/api/pith-number/PP7GNQYM6WLG3ZHKMY2GRIK2HE/graph.json","events_json":"https://pith.science/api/pith-number/PP7GNQYM6WLG3ZHKMY2GRIK2HE/events.json","paper":"https://pith.science/paper/PP7GNQYM"},"agent_actions":{"view_html":"https://pith.science/pith/PP7GNQYM6WLG3ZHKMY2GRIK2HE","download_json":"https://pith.science/pith/PP7GNQYM6WLG3ZHKMY2GRIK2HE.json","view_paper":"https://pith.science/paper/PP7GNQYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16160&json=true","fetch_graph":"https://pith.science/api/pith-number/PP7GNQYM6WLG3ZHKMY2GRIK2HE/graph.json","fetch_events":"https://pith.science/api/pith-number/PP7GNQYM6WLG3ZHKMY2GRIK2HE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PP7GNQYM6WLG3ZHKMY2GRIK2HE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PP7GNQYM6WLG3ZHKMY2GRIK2HE/action/storage_attestation","attest_author":"https://pith.science/pith/PP7GNQYM6WLG3ZHKMY2GRIK2HE/action/author_attestation","sign_citation":"https://pith.science/pith/PP7GNQYM6WLG3ZHKMY2GRIK2HE/action/citation_signature","submit_replication":"https://pith.science/pith/PP7GNQYM6WLG3ZHKMY2GRIK2HE/action/replication_record"}},"created_at":"2026-07-05T09:02:18.692096+00:00","updated_at":"2026-07-05T09:02:18.692096+00:00"}