{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GPSOCFLAFEZ423PAC6LVSZZRVO","short_pith_number":"pith:GPSOCFLA","schema_version":"1.0","canonical_sha256":"33e4e115602933cd6de01797596731abb5d8ff2cc4df9cb5256a4b4609af94c6","source":{"kind":"arxiv","id":"2607.22555","version":1},"attestation_state":"computed","paper":{"title":"DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"David Talby, Mahmood Bayeshi, Muhammed Ali Naqvi, Veysel Kocaman, Yigit Gul","submitted_at":"2026-05-19T12:55:39Z","abstract_excerpt":"Medical diagnosis is a multi-stage process: extract facts, consult knowledge, generate a differential analysis, and select the best diagnosis with explanations. Frontier LLMs are strong generalists, but single-shot prompting often yields brittle diagnostic reasoning. We present the DeepLens Diagnosis Agent, a five-stage harnessing pipeline (combining model capabilities with disciplined process constraints) centered on a small medical reasoning model (JSL Medical Small 7B v2) and retrieval-augmented generation (RAG). The pipeline enforces structured clinical extraction, disciplined retrieval, c"},"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":"2607.22555","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T12:55:39Z","cross_cats_sorted":[],"title_canon_sha256":"40e25740dc3adb8d4ea434e2a601ff0f07843ca3755ffee1f6bf2386420751c6","abstract_canon_sha256":"2576e1ddba5b2f93a3bdbe42dc254974e5623dd60572e26c0509d85081eae2da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:21:41.965964Z","signature_b64":"/bCik7GVInMSVP6g5b+qOUwDbPYSExWeJfQ0P6azsQzwry9x+4RfXNUR8sxGf2llDxGk0mtOBKNV8zCXDJIPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33e4e115602933cd6de01797596731abb5d8ff2cc4df9cb5256a4b4609af94c6","last_reissued_at":"2026-07-28T00:21:41.965085Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:21:41.965085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepLens Diagnosis Agent: Agentic Workflow Design Lets a Small Reasoning Model Compete with Frontier LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"David Talby, Mahmood Bayeshi, Muhammed Ali Naqvi, Veysel Kocaman, Yigit Gul","submitted_at":"2026-05-19T12:55:39Z","abstract_excerpt":"Medical diagnosis is a multi-stage process: extract facts, consult knowledge, generate a differential analysis, and select the best diagnosis with explanations. Frontier LLMs are strong generalists, but single-shot prompting often yields brittle diagnostic reasoning. We present the DeepLens Diagnosis Agent, a five-stage harnessing pipeline (combining model capabilities with disciplined process constraints) centered on a small medical reasoning model (JSL Medical Small 7B v2) and retrieval-augmented generation (RAG). The pipeline enforces structured clinical extraction, disciplined retrieval, c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22555","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/2607.22555/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":"2607.22555","created_at":"2026-07-28T00:21:41.965531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22555v1","created_at":"2026-07-28T00:21:41.965531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22555","created_at":"2026-07-28T00:21:41.965531+00:00"},{"alias_kind":"pith_short_12","alias_value":"GPSOCFLAFEZ4","created_at":"2026-07-28T00:21:41.965531+00:00"},{"alias_kind":"pith_short_16","alias_value":"GPSOCFLAFEZ423PA","created_at":"2026-07-28T00:21:41.965531+00:00"},{"alias_kind":"pith_short_8","alias_value":"GPSOCFLA","created_at":"2026-07-28T00:21:41.965531+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/GPSOCFLAFEZ423PAC6LVSZZRVO","json":"https://pith.science/pith/GPSOCFLAFEZ423PAC6LVSZZRVO.json","graph_json":"https://pith.science/api/pith-number/GPSOCFLAFEZ423PAC6LVSZZRVO/graph.json","events_json":"https://pith.science/api/pith-number/GPSOCFLAFEZ423PAC6LVSZZRVO/events.json","paper":"https://pith.science/paper/GPSOCFLA"},"agent_actions":{"view_html":"https://pith.science/pith/GPSOCFLAFEZ423PAC6LVSZZRVO","download_json":"https://pith.science/pith/GPSOCFLAFEZ423PAC6LVSZZRVO.json","view_paper":"https://pith.science/paper/GPSOCFLA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22555&json=true","fetch_graph":"https://pith.science/api/pith-number/GPSOCFLAFEZ423PAC6LVSZZRVO/graph.json","fetch_events":"https://pith.science/api/pith-number/GPSOCFLAFEZ423PAC6LVSZZRVO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GPSOCFLAFEZ423PAC6LVSZZRVO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GPSOCFLAFEZ423PAC6LVSZZRVO/action/storage_attestation","attest_author":"https://pith.science/pith/GPSOCFLAFEZ423PAC6LVSZZRVO/action/author_attestation","sign_citation":"https://pith.science/pith/GPSOCFLAFEZ423PAC6LVSZZRVO/action/citation_signature","submit_replication":"https://pith.science/pith/GPSOCFLAFEZ423PAC6LVSZZRVO/action/replication_record"}},"created_at":"2026-07-28T00:21:41.965531+00:00","updated_at":"2026-07-28T00:21:41.965531+00:00"}