{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2FPD7ZZXH7GCO4IGAPCFNL6GII","short_pith_number":"pith:2FPD7ZZX","schema_version":"1.0","canonical_sha256":"d15e3fe7373fcc27710603c456afc6422a8a1868bf4f4a127625a31be12161b4","source":{"kind":"arxiv","id":"2508.21777","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking GPT-5 in Radiation Oncology: Measurable Gains, but Persistent Need for Expert Oversight","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ahmed Gomaa, Andre Karius, Annette Schwarz, Benjamin Frey, Bernd-Niklas Axer, Christoph Bert, Florian Putz, Ishita Sheth, Jibak Sarkar, Johann Brand, Philipp Schubert, Pluvio Stephan, Rainer Fietkau, Sabine Semrau, Sogand Beirami, Stefanie Corradini, Thomas Weissmann, Udo Gaipl, Ugur Dinc","submitted_at":"2025-08-29T16:55:25Z","abstract_excerpt":"Introduction: Large language models (LLM) have shown great potential in clinical decision support. GPT-5 is a novel LLM system that has been specifically marketed towards oncology use.\n  Methods: Performance was assessed using two complementary benchmarks: (i) the ACR Radiation Oncology In-Training Examination (TXIT, 2021), comprising 300 multiple-choice items, and (ii) a curated set of 60 authentic radiation oncologic vignettes representing diverse disease sites and treatment indications. For the vignette evaluation, GPT-5 was instructed to generate concise therapeutic plans. Four board-certi"},"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":"2508.21777","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T16:55:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b8e7f2041ed70f6c1a4e644c9c095d96193c4a7fcb3e4fc9281e7d9931206928","abstract_canon_sha256":"69243437ac29478b6e16c80ceff20653475796b1762e8c4062ba2795e0c98c9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:49.601742Z","signature_b64":"dyAUKPmb2TEHAv5L+ThgQgHrdvXCqZm3qaPyV6NrKO8t9LjUDo5M5ECrVsihrngNNZXVtZmer8uHOU9EEihkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d15e3fe7373fcc27710603c456afc6422a8a1868bf4f4a127625a31be12161b4","last_reissued_at":"2026-07-05T12:01:49.601185Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:49.601185Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking GPT-5 in Radiation Oncology: Measurable Gains, but Persistent Need for Expert Oversight","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ahmed Gomaa, Andre Karius, Annette Schwarz, Benjamin Frey, Bernd-Niklas Axer, Christoph Bert, Florian Putz, Ishita Sheth, Jibak Sarkar, Johann Brand, Philipp Schubert, Pluvio Stephan, Rainer Fietkau, Sabine Semrau, Sogand Beirami, Stefanie Corradini, Thomas Weissmann, Udo Gaipl, Ugur Dinc","submitted_at":"2025-08-29T16:55:25Z","abstract_excerpt":"Introduction: Large language models (LLM) have shown great potential in clinical decision support. GPT-5 is a novel LLM system that has been specifically marketed towards oncology use.\n  Methods: Performance was assessed using two complementary benchmarks: (i) the ACR Radiation Oncology In-Training Examination (TXIT, 2021), comprising 300 multiple-choice items, and (ii) a curated set of 60 authentic radiation oncologic vignettes representing diverse disease sites and treatment indications. For the vignette evaluation, GPT-5 was instructed to generate concise therapeutic plans. Four board-certi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.21777","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/2508.21777/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":"2508.21777","created_at":"2026-07-05T12:01:49.601256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.21777v1","created_at":"2026-07-05T12:01:49.601256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.21777","created_at":"2026-07-05T12:01:49.601256+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FPD7ZZXH7GC","created_at":"2026-07-05T12:01:49.601256+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FPD7ZZXH7GCO4IG","created_at":"2026-07-05T12:01:49.601256+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FPD7ZZX","created_at":"2026-07-05T12:01:49.601256+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/2FPD7ZZXH7GCO4IGAPCFNL6GII","json":"https://pith.science/pith/2FPD7ZZXH7GCO4IGAPCFNL6GII.json","graph_json":"https://pith.science/api/pith-number/2FPD7ZZXH7GCO4IGAPCFNL6GII/graph.json","events_json":"https://pith.science/api/pith-number/2FPD7ZZXH7GCO4IGAPCFNL6GII/events.json","paper":"https://pith.science/paper/2FPD7ZZX"},"agent_actions":{"view_html":"https://pith.science/pith/2FPD7ZZXH7GCO4IGAPCFNL6GII","download_json":"https://pith.science/pith/2FPD7ZZXH7GCO4IGAPCFNL6GII.json","view_paper":"https://pith.science/paper/2FPD7ZZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.21777&json=true","fetch_graph":"https://pith.science/api/pith-number/2FPD7ZZXH7GCO4IGAPCFNL6GII/graph.json","fetch_events":"https://pith.science/api/pith-number/2FPD7ZZXH7GCO4IGAPCFNL6GII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FPD7ZZXH7GCO4IGAPCFNL6GII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FPD7ZZXH7GCO4IGAPCFNL6GII/action/storage_attestation","attest_author":"https://pith.science/pith/2FPD7ZZXH7GCO4IGAPCFNL6GII/action/author_attestation","sign_citation":"https://pith.science/pith/2FPD7ZZXH7GCO4IGAPCFNL6GII/action/citation_signature","submit_replication":"https://pith.science/pith/2FPD7ZZXH7GCO4IGAPCFNL6GII/action/replication_record"}},"created_at":"2026-07-05T12:01:49.601256+00:00","updated_at":"2026-07-05T12:01:49.601256+00:00"}