{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:I6IXKOTHMBRJR6CJN7FJ7IIWID","short_pith_number":"pith:I6IXKOTH","canonical_record":{"source":{"id":"2608.00817","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-01T18:48:51Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"aa97bf7fd2b54d7aef9dc77da7c2f100d7dff547ada64a585c246ee20d0225ac","abstract_canon_sha256":"3020560f25661430053f64014e8f999234f34127612f297abf2526d8b7fa28b8"},"schema_version":"1.0"},"canonical_sha256":"4791753a67606298f8496fca9fa11640f2139f046eccf854cd631d4d58a72b73","source":{"kind":"arxiv","id":"2608.00817","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00817","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00817v1","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00817","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"pith_short_12","alias_value":"I6IXKOTHMBRJ","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"pith_short_16","alias_value":"I6IXKOTHMBRJR6CJ","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"pith_short_8","alias_value":"I6IXKOTH","created_at":"2026-08-04T01:55:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:I6IXKOTHMBRJR6CJN7FJ7IIWID","target":"record","payload":{"canonical_record":{"source":{"id":"2608.00817","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-01T18:48:51Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"aa97bf7fd2b54d7aef9dc77da7c2f100d7dff547ada64a585c246ee20d0225ac","abstract_canon_sha256":"3020560f25661430053f64014e8f999234f34127612f297abf2526d8b7fa28b8"},"schema_version":"1.0"},"canonical_sha256":"4791753a67606298f8496fca9fa11640f2139f046eccf854cd631d4d58a72b73","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:55:12.116558Z","signature_b64":"/DJ9oTB53sCj59sOgFLZCvuX9fjDt0aV3fnY+YewcsSuVlv44gGT13yQC5wzHNF19vT7SgNHEJTpK5rrxjJJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4791753a67606298f8496fca9fa11640f2139f046eccf854cd631d4d58a72b73","last_reissued_at":"2026-08-04T01:55:12.115037Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:55:12.115037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.00817","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T01:55:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qxxReDYxcbz60falcLc1UXI7zs4NsrgYSGwyVLNKGg5d51fjE708/SFng/QDRHtlvxsZGg4W9ZGlGCtEsQDVBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:35:35.824845Z"},"content_sha256":"e843027ba5787b08064f32a5563bb3cd31c97e01eece7525dab074cec47134f3","schema_version":"1.0","event_id":"sha256:e843027ba5787b08064f32a5563bb3cd31c97e01eece7525dab074cec47134f3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:I6IXKOTHMBRJR6CJN7FJ7IIWID","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large language models improve physician accuracy but lead to false reliance","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"cs.AI","authors_text":"Alexander Thiem, Carina Nogueira Garcia, Christoph Wies, Consortium, Cristian Navarrete-Dechent, Franziska Schramm, Jakob N. Kather, Jochen S. Utikal, Martin J. Hetz, Nicolas B. Merl, Phillip Tschandl, Tirtha Chanda, Titus J. Brinker","submitted_at":"2026-08-01T18:48:51Z","abstract_excerpt":"Retrieval-augmented large language models (LLMs) promise source-linked clinical support, but their value depends on whether displayed evidence guides rather than distorts physician reliance. We developed CORA, an agentic retrieval-augmented LLM, to investigate how source-linked assistance affects physician decision-making. CORA maintained benchmark performance and achieved larger gains on cases published after the models' training-data cutoffs. In a study of 46 physicians, accuracy increased from 70.8% unaided to 82.6% with CORA. Supporting citations predicted correct answers (87.7% vs 65.5%),"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00817","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/2608.00817/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T01:55:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7QYGiIIQ+Br4ZvlAu8eWhm1gN7D8DTAp+WjLcHBdNmYNiy+3/fSDNMgcrtu/ks5M65YGFjVDQPuQ4Kls8XPXCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:35:35.825337Z"},"content_sha256":"f8923f2e3ac8cf8d1592d5de0925604d8485215e7e086f67203014cc392cff58","schema_version":"1.0","event_id":"sha256:f8923f2e3ac8cf8d1592d5de0925604d8485215e7e086f67203014cc392cff58"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I6IXKOTHMBRJR6CJN7FJ7IIWID/bundle.json","state_url":"https://pith.science/pith/I6IXKOTHMBRJR6CJN7FJ7IIWID/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I6IXKOTHMBRJR6CJN7FJ7IIWID/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T08:35:35Z","links":{"resolver":"https://pith.science/pith/I6IXKOTHMBRJR6CJN7FJ7IIWID","bundle":"https://pith.science/pith/I6IXKOTHMBRJR6CJN7FJ7IIWID/bundle.json","state":"https://pith.science/pith/I6IXKOTHMBRJR6CJN7FJ7IIWID/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I6IXKOTHMBRJR6CJN7FJ7IIWID/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I6IXKOTHMBRJR6CJN7FJ7IIWID","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3020560f25661430053f64014e8f999234f34127612f297abf2526d8b7fa28b8","cross_cats_sorted":["stat.AP"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-01T18:48:51Z","title_canon_sha256":"aa97bf7fd2b54d7aef9dc77da7c2f100d7dff547ada64a585c246ee20d0225ac"},"schema_version":"1.0","source":{"id":"2608.00817","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00817","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00817v1","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00817","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"pith_short_12","alias_value":"I6IXKOTHMBRJ","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"pith_short_16","alias_value":"I6IXKOTHMBRJR6CJ","created_at":"2026-08-04T01:55:12Z"},{"alias_kind":"pith_short_8","alias_value":"I6IXKOTH","created_at":"2026-08-04T01:55:12Z"}],"graph_snapshots":[{"event_id":"sha256:f8923f2e3ac8cf8d1592d5de0925604d8485215e7e086f67203014cc392cff58","target":"graph","created_at":"2026-08-04T01:55:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.00817/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented large language models (LLMs) promise source-linked clinical support, but their value depends on whether displayed evidence guides rather than distorts physician reliance. We developed CORA, an agentic retrieval-augmented LLM, to investigate how source-linked assistance affects physician decision-making. CORA maintained benchmark performance and achieved larger gains on cases published after the models' training-data cutoffs. In a study of 46 physicians, accuracy increased from 70.8% unaided to 82.6% with CORA. Supporting citations predicted correct answers (87.7% vs 65.5%),","authors_text":"Alexander Thiem, Carina Nogueira Garcia, Christoph Wies, Consortium, Cristian Navarrete-Dechent, Franziska Schramm, Jakob N. Kather, Jochen S. Utikal, Martin J. Hetz, Nicolas B. Merl, Phillip Tschandl, Tirtha Chanda, Titus J. Brinker","cross_cats":["stat.AP"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-01T18:48:51Z","title":"Large language models improve physician accuracy but lead to false reliance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00817","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e843027ba5787b08064f32a5563bb3cd31c97e01eece7525dab074cec47134f3","target":"record","created_at":"2026-08-04T01:55:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3020560f25661430053f64014e8f999234f34127612f297abf2526d8b7fa28b8","cross_cats_sorted":["stat.AP"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-01T18:48:51Z","title_canon_sha256":"aa97bf7fd2b54d7aef9dc77da7c2f100d7dff547ada64a585c246ee20d0225ac"},"schema_version":"1.0","source":{"id":"2608.00817","kind":"arxiv","version":1}},"canonical_sha256":"4791753a67606298f8496fca9fa11640f2139f046eccf854cd631d4d58a72b73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4791753a67606298f8496fca9fa11640f2139f046eccf854cd631d4d58a72b73","first_computed_at":"2026-08-04T01:55:12.115037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T01:55:12.115037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/DJ9oTB53sCj59sOgFLZCvuX9fjDt0aV3fnY+YewcsSuVlv44gGT13yQC5wzHNF19vT7SgNHEJTpK5rrxjJJAA==","signature_status":"signed_v1","signed_at":"2026-08-04T01:55:12.116558Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00817","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e843027ba5787b08064f32a5563bb3cd31c97e01eece7525dab074cec47134f3","sha256:f8923f2e3ac8cf8d1592d5de0925604d8485215e7e086f67203014cc392cff58"],"state_sha256":"c4fb0d4fb75cc073edfc413cc765002ada19659631c78dbca8d3d1bdbd0d7542"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RnBYjE/gtDXxcGKYDbqp3wwp3QHzB1CdaTtGfyhIEnBjTEnayfwJO/9cELb63gwxMBA2itsztMVnyG6TFYEABQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:35:35.830273Z","bundle_sha256":"00146df8e82b097a5c95246f0c96a552e67974a8ec234fb88fe8fb94b40ffc4d"}}