{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PRN3SSP3B6SZYDTOEEEMUF62K7","short_pith_number":"pith:PRN3SSP3","schema_version":"1.0","canonical_sha256":"7c5bb949fb0fa59c0e6e2108ca17da57e07ad4e52a2d427feeae4cfa7a0d3c74","source":{"kind":"arxiv","id":"2506.01841","version":1},"attestation_state":"computed","paper":{"title":"Beyond Pixel Agreement: Large Language Models as Clinical Guardrails for Reliable Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Haoyue Li, Jiaxi Sheng, Leyi Yu, Xin Gao, Yifan Gao","submitted_at":"2025-06-02T16:28:03Z","abstract_excerpt":"Evaluating AI-generated medical image segmentations for clinical acceptability poses a significant challenge, as traditional pixelagreement metrics often fail to capture true diagnostic utility. This paper introduces Hierarchical Clinical Reasoner (HCR), a novel framework that leverages Large Language Models (LLMs) as clinical guardrails for reliable, zero-shot quality assessment. HCR employs a structured, multistage prompting strategy that guides LLMs through a detailed reasoning process, encompassing knowledge recall, visual feature analysis, anatomical inference, and clinical synthesis, to "},"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":"2506.01841","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-06-02T16:28:03Z","cross_cats_sorted":[],"title_canon_sha256":"938826af7c4db3f89c4460e1f0ec065e04071987df149dfdae395178c2edd88d","abstract_canon_sha256":"e8df619d160fa0c09853893533cc9eec3bf43de75dc182c8b410b42ee48f1aef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:20.240585Z","signature_b64":"nSOVpne97TDE1SMs6hS9I3sEkzNcZQBB7i6F3iLVlZP1K+BzhLEuv5xq89/TkB3uWdr9k3P1F6pOvRRQzT5BAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c5bb949fb0fa59c0e6e2108ca17da57e07ad4e52a2d427feeae4cfa7a0d3c74","last_reissued_at":"2026-07-05T11:14:20.240082Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:20.240082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Pixel Agreement: Large Language Models as Clinical Guardrails for Reliable Medical Image Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Haoyue Li, Jiaxi Sheng, Leyi Yu, Xin Gao, Yifan Gao","submitted_at":"2025-06-02T16:28:03Z","abstract_excerpt":"Evaluating AI-generated medical image segmentations for clinical acceptability poses a significant challenge, as traditional pixelagreement metrics often fail to capture true diagnostic utility. This paper introduces Hierarchical Clinical Reasoner (HCR), a novel framework that leverages Large Language Models (LLMs) as clinical guardrails for reliable, zero-shot quality assessment. HCR employs a structured, multistage prompting strategy that guides LLMs through a detailed reasoning process, encompassing knowledge recall, visual feature analysis, anatomical inference, and clinical synthesis, to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01841","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/2506.01841/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":"2506.01841","created_at":"2026-07-05T11:14:20.240146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01841v1","created_at":"2026-07-05T11:14:20.240146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01841","created_at":"2026-07-05T11:14:20.240146+00:00"},{"alias_kind":"pith_short_12","alias_value":"PRN3SSP3B6SZ","created_at":"2026-07-05T11:14:20.240146+00:00"},{"alias_kind":"pith_short_16","alias_value":"PRN3SSP3B6SZYDTO","created_at":"2026-07-05T11:14:20.240146+00:00"},{"alias_kind":"pith_short_8","alias_value":"PRN3SSP3","created_at":"2026-07-05T11:14:20.240146+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/PRN3SSP3B6SZYDTOEEEMUF62K7","json":"https://pith.science/pith/PRN3SSP3B6SZYDTOEEEMUF62K7.json","graph_json":"https://pith.science/api/pith-number/PRN3SSP3B6SZYDTOEEEMUF62K7/graph.json","events_json":"https://pith.science/api/pith-number/PRN3SSP3B6SZYDTOEEEMUF62K7/events.json","paper":"https://pith.science/paper/PRN3SSP3"},"agent_actions":{"view_html":"https://pith.science/pith/PRN3SSP3B6SZYDTOEEEMUF62K7","download_json":"https://pith.science/pith/PRN3SSP3B6SZYDTOEEEMUF62K7.json","view_paper":"https://pith.science/paper/PRN3SSP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01841&json=true","fetch_graph":"https://pith.science/api/pith-number/PRN3SSP3B6SZYDTOEEEMUF62K7/graph.json","fetch_events":"https://pith.science/api/pith-number/PRN3SSP3B6SZYDTOEEEMUF62K7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PRN3SSP3B6SZYDTOEEEMUF62K7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PRN3SSP3B6SZYDTOEEEMUF62K7/action/storage_attestation","attest_author":"https://pith.science/pith/PRN3SSP3B6SZYDTOEEEMUF62K7/action/author_attestation","sign_citation":"https://pith.science/pith/PRN3SSP3B6SZYDTOEEEMUF62K7/action/citation_signature","submit_replication":"https://pith.science/pith/PRN3SSP3B6SZYDTOEEEMUF62K7/action/replication_record"}},"created_at":"2026-07-05T11:14:20.240146+00:00","updated_at":"2026-07-05T11:14:20.240146+00:00"}