{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SZR4SNABCNI67TGOJBGE4RETDY","short_pith_number":"pith:SZR4SNAB","schema_version":"1.0","canonical_sha256":"9663c934011351efccce484c4e44931e198ccce7a294552d58ff47118526f894","source":{"kind":"arxiv","id":"2404.04292","version":5},"attestation_state":"computed","paper":{"title":"Conversational Disease Diagnosis via External Planner-Controlled Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cheng Luo, Zhengxing Huang, Zhoujian Sun, Ziyi Liu","submitted_at":"2024-04-04T06:16:35Z","abstract_excerpt":"The development of large language models (LLMs) has brought unprecedented possibilities for artificial intelligence (AI) based medical diagnosis. However, the application perspective of LLMs in real diagnostic scenarios is still unclear because they are not adept at collecting patient data proactively. This study presents a LLM-based diagnostic system that enhances planning capabilities by emulating doctors. Our system involves two external planners to handle planning tasks. The first planner employs a reinforcement learning approach to formulate disease screening questions and conduct initial"},"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":"2404.04292","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-04T06:16:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"52a28239cf50739cc2449e65adc552470c497db37645baa2030db2d41e8c410b","abstract_canon_sha256":"ecb12b08738f40dc96988fc0b63195e49d04ec1ffa017f666ac222cbf7506082"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:28.923118Z","signature_b64":"UpME/psUCvLndYFO1u+4GaRzVn9V/m7W0suzh0mGWDhESx33b8U49EGpBBJ/306lmLDBG1lMW0uNFEtVJ0ciAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9663c934011351efccce484c4e44931e198ccce7a294552d58ff47118526f894","last_reissued_at":"2026-07-05T08:20:28.922663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:28.922663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conversational Disease Diagnosis via External Planner-Controlled Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cheng Luo, Zhengxing Huang, Zhoujian Sun, Ziyi Liu","submitted_at":"2024-04-04T06:16:35Z","abstract_excerpt":"The development of large language models (LLMs) has brought unprecedented possibilities for artificial intelligence (AI) based medical diagnosis. However, the application perspective of LLMs in real diagnostic scenarios is still unclear because they are not adept at collecting patient data proactively. This study presents a LLM-based diagnostic system that enhances planning capabilities by emulating doctors. Our system involves two external planners to handle planning tasks. The first planner employs a reinforcement learning approach to formulate disease screening questions and conduct initial"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04292","kind":"arxiv","version":5},"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/2404.04292/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":"2404.04292","created_at":"2026-07-05T08:20:28.922719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04292v5","created_at":"2026-07-05T08:20:28.922719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04292","created_at":"2026-07-05T08:20:28.922719+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZR4SNABCNI6","created_at":"2026-07-05T08:20:28.922719+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZR4SNABCNI67TGO","created_at":"2026-07-05T08:20:28.922719+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZR4SNAB","created_at":"2026-07-05T08:20:28.922719+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20022","citing_title":"MoBayes: A Modular Bayesian Framework for Separating Reasoning from Language in Conversational Clinical Decision Support","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20022","citing_title":"MoBayes: A Modular Bayesian Framework for Separating Reasoning from Language in Conversational Clinical Decision Support","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SZR4SNABCNI67TGOJBGE4RETDY","json":"https://pith.science/pith/SZR4SNABCNI67TGOJBGE4RETDY.json","graph_json":"https://pith.science/api/pith-number/SZR4SNABCNI67TGOJBGE4RETDY/graph.json","events_json":"https://pith.science/api/pith-number/SZR4SNABCNI67TGOJBGE4RETDY/events.json","paper":"https://pith.science/paper/SZR4SNAB"},"agent_actions":{"view_html":"https://pith.science/pith/SZR4SNABCNI67TGOJBGE4RETDY","download_json":"https://pith.science/pith/SZR4SNABCNI67TGOJBGE4RETDY.json","view_paper":"https://pith.science/paper/SZR4SNAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04292&json=true","fetch_graph":"https://pith.science/api/pith-number/SZR4SNABCNI67TGOJBGE4RETDY/graph.json","fetch_events":"https://pith.science/api/pith-number/SZR4SNABCNI67TGOJBGE4RETDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZR4SNABCNI67TGOJBGE4RETDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZR4SNABCNI67TGOJBGE4RETDY/action/storage_attestation","attest_author":"https://pith.science/pith/SZR4SNABCNI67TGOJBGE4RETDY/action/author_attestation","sign_citation":"https://pith.science/pith/SZR4SNABCNI67TGOJBGE4RETDY/action/citation_signature","submit_replication":"https://pith.science/pith/SZR4SNABCNI67TGOJBGE4RETDY/action/replication_record"}},"created_at":"2026-07-05T08:20:28.922719+00:00","updated_at":"2026-07-05T08:20:28.922719+00:00"}