{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5Y3SJDFTMBVBFSCVB2NIS52JP5","short_pith_number":"pith:5Y3SJDFT","schema_version":"1.0","canonical_sha256":"ee37248cb3606a12c8550e9a8977497f517057729ac25619c945223dbc6a4a75","source":{"kind":"arxiv","id":"2606.22382","version":1},"attestation_state":"computed","paper":{"title":"Large Language Model-Assisted Cleaning of Report-Derived Labels in a Large-Scale Chest CT Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"eess.IV","authors_text":"Atsushi Takamatsu, Mototsugu Sato, Osamu Abe, Shouhei Hanaoka, Takeharu Yoshikawa, Tomohiro Kikuchi, Yosuke Yamagishi","submitted_at":"2026-06-21T08:01:06Z","abstract_excerpt":"Purpose: To evaluate whether large language model (LLM)-assisted label cleaning can identify label-report discordance in CT-RATE, a large-scale public chest CT dataset.\n  Materials and Methods: After report-level deduplication, 24,446 unique radiology reports were identified. Twelve reports were excluded from the primary GPT-5.4 analysis because of Microsoft Azure AI Foundry content-safety filtering, leaving 24,434 reports and 439,812 label instances across 18 abnormality categories. GPT-5.4-derived binary labels were generated from report text using structured JSON output and compared with ex"},"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":"2606.22382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-06-21T08:01:06Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"5233e914dbfbe3148b1bae27761f3c1dc83d3efc5e71c314ebeba28b41b39492","abstract_canon_sha256":"42bc87c947052774909ab9fad278f71628ba4f1b6c42d62e9e0e3a6cb50dd92b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:36.948311Z","signature_b64":"xOuTo4WHCYydMg9QCpDbllDVB9vC8JsSpLJJ0vjE1rQQVzJkf9WbHYlp6jKNKoodsTBXuNtzQujBRgKFMKvcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee37248cb3606a12c8550e9a8977497f517057729ac25619c945223dbc6a4a75","last_reissued_at":"2026-06-23T02:13:36.947800Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:36.947800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Model-Assisted Cleaning of Report-Derived Labels in a Large-Scale Chest CT Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"eess.IV","authors_text":"Atsushi Takamatsu, Mototsugu Sato, Osamu Abe, Shouhei Hanaoka, Takeharu Yoshikawa, Tomohiro Kikuchi, Yosuke Yamagishi","submitted_at":"2026-06-21T08:01:06Z","abstract_excerpt":"Purpose: To evaluate whether large language model (LLM)-assisted label cleaning can identify label-report discordance in CT-RATE, a large-scale public chest CT dataset.\n  Materials and Methods: After report-level deduplication, 24,446 unique radiology reports were identified. Twelve reports were excluded from the primary GPT-5.4 analysis because of Microsoft Azure AI Foundry content-safety filtering, leaving 24,434 reports and 439,812 label instances across 18 abnormality categories. GPT-5.4-derived binary labels were generated from report text using structured JSON output and compared with ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22382","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/2606.22382/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":"2606.22382","created_at":"2026-06-23T02:13:36.947864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22382v1","created_at":"2026-06-23T02:13:36.947864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22382","created_at":"2026-06-23T02:13:36.947864+00:00"},{"alias_kind":"pith_short_12","alias_value":"5Y3SJDFTMBVB","created_at":"2026-06-23T02:13:36.947864+00:00"},{"alias_kind":"pith_short_16","alias_value":"5Y3SJDFTMBVBFSCV","created_at":"2026-06-23T02:13:36.947864+00:00"},{"alias_kind":"pith_short_8","alias_value":"5Y3SJDFT","created_at":"2026-06-23T02:13:36.947864+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/5Y3SJDFTMBVBFSCVB2NIS52JP5","json":"https://pith.science/pith/5Y3SJDFTMBVBFSCVB2NIS52JP5.json","graph_json":"https://pith.science/api/pith-number/5Y3SJDFTMBVBFSCVB2NIS52JP5/graph.json","events_json":"https://pith.science/api/pith-number/5Y3SJDFTMBVBFSCVB2NIS52JP5/events.json","paper":"https://pith.science/paper/5Y3SJDFT"},"agent_actions":{"view_html":"https://pith.science/pith/5Y3SJDFTMBVBFSCVB2NIS52JP5","download_json":"https://pith.science/pith/5Y3SJDFTMBVBFSCVB2NIS52JP5.json","view_paper":"https://pith.science/paper/5Y3SJDFT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22382&json=true","fetch_graph":"https://pith.science/api/pith-number/5Y3SJDFTMBVBFSCVB2NIS52JP5/graph.json","fetch_events":"https://pith.science/api/pith-number/5Y3SJDFTMBVBFSCVB2NIS52JP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5Y3SJDFTMBVBFSCVB2NIS52JP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5Y3SJDFTMBVBFSCVB2NIS52JP5/action/storage_attestation","attest_author":"https://pith.science/pith/5Y3SJDFTMBVBFSCVB2NIS52JP5/action/author_attestation","sign_citation":"https://pith.science/pith/5Y3SJDFTMBVBFSCVB2NIS52JP5/action/citation_signature","submit_replication":"https://pith.science/pith/5Y3SJDFTMBVBFSCVB2NIS52JP5/action/replication_record"}},"created_at":"2026-06-23T02:13:36.947864+00:00","updated_at":"2026-06-23T02:13:36.947864+00:00"}