{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N2EPR7ZGD3SJEH45DNKURSAUC4","short_pith_number":"pith:N2EPR7ZG","schema_version":"1.0","canonical_sha256":"6e88f8ff261ee4921f9d1b5548c81417039c4b6f40be3b6a5a22672bae168578","source":{"kind":"arxiv","id":"2605.00846","version":1},"attestation_state":"computed","paper":{"title":"ClinicBot: A Guideline-Grounded Clinical Chatbot with Prioritized Evidence RAG and Verifiable Citations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ClinicBot extracts clinical guidelines into semantic units and prioritizes evidence by significance to generate verifiable answers.","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Mayank Kejriwal, Navapat Nananukul","submitted_at":"2026-04-11T00:37:12Z","abstract_excerpt":"Clinical diagnosis requires answers that are accurate, verifiable, and explicitly grounded in official guidelines. While large language models excel at natural language processing, their tendency to hallucinate undermines their utility in high-stakes medical contexts where precision is essential. Existing retrieval-augmented generation (RAG) systems treat all evidence equally, producing noisy context and generic answers misaligned with clinical practice. We present ClinicBot, an AI system that translates guideline recommendations into trustworthy clinical support through three key advances: (1"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.00846","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-11T00:37:12Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"203138973bf4665a146255dbe886560222c603a6dd9f26f54c70eebc684e5424","abstract_canon_sha256":"b46ab15d2340a5591fcfe567de146274a332d3d826dbae7fee3a4a8162090a58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:11.162327Z","signature_b64":"/d5uvoZEhfxjT3uiGRNlUkJwZdy3VCBJ9nuIlvVAuPBe+5WJIL6f5Bt2ipcXK/8IeUFKgMp7xI9Uyvtaex7aCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e88f8ff261ee4921f9d1b5548c81417039c4b6f40be3b6a5a22672bae168578","last_reissued_at":"2026-05-29T01:05:11.161481Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:11.161481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ClinicBot: A Guideline-Grounded Clinical Chatbot with Prioritized Evidence RAG and Verifiable Citations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ClinicBot extracts clinical guidelines into semantic units and prioritizes evidence by significance to generate verifiable answers.","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Mayank Kejriwal, Navapat Nananukul","submitted_at":"2026-04-11T00:37:12Z","abstract_excerpt":"Clinical diagnosis requires answers that are accurate, verifiable, and explicitly grounded in official guidelines. While large language models excel at natural language processing, their tendency to hallucinate undermines their utility in high-stakes medical contexts where precision is essential. Existing retrieval-augmented generation (RAG) systems treat all evidence equally, producing noisy context and generic answers misaligned with clinical practice. We present ClinicBot, an AI system that translates guideline recommendations into trustworthy clinical support through three key advances: (1"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We present ClinicBot, an AI system that translates guideline recommendations into trustworthy clinical support through three key advances: (1) structured extraction of clinical guidelines into semantic units with explicit provenance, (2) evidence prioritization that ranks content by clinical significance and guideline structure rather than textual similarity, and (3) a web-based interface that presents concise, actionable answers with verifiable evidence.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That clinical significance and guideline structure can be defined and ranked objectively enough to produce reliable prioritization without introducing new errors or omitting critical context.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ClinicBot is a clinical chatbot that uses structured guideline extraction and prioritized RAG to deliver verifiable, guideline-grounded answers for diabetes care.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ClinicBot extracts clinical guidelines into semantic units and prioritizes evidence by significance to generate verifiable answers.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"317cff562a54bc88fca9addc2f2aec192cdcf1a349d0373b61957479d4633729"},"source":{"id":"2605.00846","kind":"arxiv","version":1},"verdict":{"id":"bf6ccf96-b5fe-4cf3-88d1-7937339fd626","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T16:55:27.684715Z","strongest_claim":"We present ClinicBot, an AI system that translates guideline recommendations into trustworthy clinical support through three key advances: (1) structured extraction of clinical guidelines into semantic units with explicit provenance, (2) evidence prioritization that ranks content by clinical significance and guideline structure rather than textual similarity, and (3) a web-based interface that presents concise, actionable answers with verifiable evidence.","one_line_summary":"ClinicBot is a clinical chatbot that uses structured guideline extraction and prioritized RAG to deliver verifiable, guideline-grounded answers for diabetes care.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That clinical significance and guideline structure can be defined and ranked objectively enough to produce reliable prioritization without introducing new errors or omitting critical context.","pith_extraction_headline":"ClinicBot extracts clinical guidelines into semantic units and prioritizes evidence by significance to generate verifiable answers."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.00846/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":22,"sample":[{"doi":"","year":2025,"title":"Manar Aljohani, Jun Hou, Sindhura Kommu, and Xuan Wang. 2025. A compre- hensive survey on the trustworthiness of large language models in healthcare. npj Digital Medicine8 (2025), 1–18","work_id":"1e4a9a8e-bb62-496f-8d3f-bae72cf4731a","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"American Diabetes Association. 2025. Standards of Care in Diabetes.Diabetes Care48, Suppl. 1 (2025), S1–S387","work_id":"843305bb-6b69-448c-a727-c149dbf3b433","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Z Chen et al. 2023. Harnessing the power of clinical decision support systems: challenges and opportunities.Open Heart10, 1 (2023), e001878","work_id":"7886df7d-9423-4d01-be74-920f5f775258","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Kristof Coussement, Mohammad Zoynul Abedin, Mathias Kraus, Sebastián Mal- donado, and Kazim Topuz. 2024. Explainable AI for enhanced decision-making. Decision Support Systems184 (2024), 114276","work_id":"7a8e8128-b0c8-4201-bceb-60f7e8e18d45","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"Gordon Guyatt, Andrew D Oxman, Gunn E Vist, Regina Kunz, Yngve Falck-Ytter, Pablo Alonso-Coello, and Holger J Schünemann. 2011. GRADE: an emerging consensus on rating quality of evidence and strength ","work_id":"7cc906ba-2e61-4827-9013-1b0c84582c28","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":22,"snapshot_sha256":"6ddaa53ff9bc74adc239e4af1ccd523a7cda68bf693783617efec0156c6462ef","internal_anchors":1},"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":"2605.00846","created_at":"2026-05-29T01:05:11.161592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.00846v1","created_at":"2026-05-29T01:05:11.161592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.00846","created_at":"2026-05-29T01:05:11.161592+00:00"},{"alias_kind":"pith_short_12","alias_value":"N2EPR7ZGD3SJ","created_at":"2026-05-29T01:05:11.161592+00:00"},{"alias_kind":"pith_short_16","alias_value":"N2EPR7ZGD3SJEH45","created_at":"2026-05-29T01:05:11.161592+00:00"},{"alias_kind":"pith_short_8","alias_value":"N2EPR7ZG","created_at":"2026-05-29T01:05:11.161592+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.29473","citing_title":"Inform, Coach, Relate, Listen: Auditing LLM Caregiving Support Roles","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N2EPR7ZGD3SJEH45DNKURSAUC4","json":"https://pith.science/pith/N2EPR7ZGD3SJEH45DNKURSAUC4.json","graph_json":"https://pith.science/api/pith-number/N2EPR7ZGD3SJEH45DNKURSAUC4/graph.json","events_json":"https://pith.science/api/pith-number/N2EPR7ZGD3SJEH45DNKURSAUC4/events.json","paper":"https://pith.science/paper/N2EPR7ZG"},"agent_actions":{"view_html":"https://pith.science/pith/N2EPR7ZGD3SJEH45DNKURSAUC4","download_json":"https://pith.science/pith/N2EPR7ZGD3SJEH45DNKURSAUC4.json","view_paper":"https://pith.science/paper/N2EPR7ZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.00846&json=true","fetch_graph":"https://pith.science/api/pith-number/N2EPR7ZGD3SJEH45DNKURSAUC4/graph.json","fetch_events":"https://pith.science/api/pith-number/N2EPR7ZGD3SJEH45DNKURSAUC4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N2EPR7ZGD3SJEH45DNKURSAUC4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N2EPR7ZGD3SJEH45DNKURSAUC4/action/storage_attestation","attest_author":"https://pith.science/pith/N2EPR7ZGD3SJEH45DNKURSAUC4/action/author_attestation","sign_citation":"https://pith.science/pith/N2EPR7ZGD3SJEH45DNKURSAUC4/action/citation_signature","submit_replication":"https://pith.science/pith/N2EPR7ZGD3SJEH45DNKURSAUC4/action/replication_record"}},"created_at":"2026-05-29T01:05:11.161592+00:00","updated_at":"2026-05-29T01:05:11.161592+00:00"}