{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RK6JCOPDKQKQJ6L4A43VJ2R6D5","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":"9a320228c84b6cbf56a5cef0e0e0cbc8581cca3dd017fef43a78ff2c25d265bf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T09:45:45Z","title_canon_sha256":"0852ffb5a072e4a446fc97422e53c0537b910004686b7e9255d8f5809d0cf8ae"},"schema_version":"1.0","source":{"id":"2606.08071","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08071","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08071v1","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08071","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"RK6JCOPDKQKQ","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"RK6JCOPDKQKQJ6L4","created_at":"2026-06-09T01:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"RK6JCOPD","created_at":"2026-06-09T01:05:25Z"}],"graph_snapshots":[{"event_id":"sha256:c4ca767135dd12f58425e158dd4808010aba0b00376a16800c743fc826445d6f","target":"graph","created_at":"2026-06-09T01:05:25Z","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/2606.08071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reliable evaluation of large language models in surgery remains underdeveloped. Broad medical benchmarks test clinical knowledge, while surgery requires procedural reasoning, management trade-offs, negation handling, and selection among plausible operative decisions. We present SurgiQ, a text-only, source-grounded benchmark of 13,055 four-option multiple-choice questions spanning six surgical domains and four question formats: case-based, reasoning, best-option, and negative. SurgiQ is constructed from surgical textbooks, open-access papers, and examination material using a multi-stage generat","authors_text":"Ayah Al-Naji, Cesare Stefanini, Edoardo Fazzari, Hamdan Alhadhrami, Preslav Nakov, Saif AlKindi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T09:45:45Z","title":"SurgiQ: A Large-Scale Multi-Domain Benchmark for Evaluating Surgical Understanding in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08071","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:b2578ec6d29bc5a0cfb7504e827fc161fcb359c4391da4f2ae28efe36de08f4a","target":"record","created_at":"2026-06-09T01:05:25Z","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":"9a320228c84b6cbf56a5cef0e0e0cbc8581cca3dd017fef43a78ff2c25d265bf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-06T09:45:45Z","title_canon_sha256":"0852ffb5a072e4a446fc97422e53c0537b910004686b7e9255d8f5809d0cf8ae"},"schema_version":"1.0","source":{"id":"2606.08071","kind":"arxiv","version":1}},"canonical_sha256":"8abc9139e3541504f97c073754ea3e1f78718516bcae47b81790f6552e4ecb24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8abc9139e3541504f97c073754ea3e1f78718516bcae47b81790f6552e4ecb24","first_computed_at":"2026-06-09T01:05:25.368855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:25.368855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nMIMNpfYYgmlfIuUwkl56zWrtc+wMUcSS9mIHW51J4ky3QnP2UFZlIxo49SvMlMJ2f28zXpUznTmPcGQUGptAA==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:25.369359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08071","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2578ec6d29bc5a0cfb7504e827fc161fcb359c4391da4f2ae28efe36de08f4a","sha256:c4ca767135dd12f58425e158dd4808010aba0b00376a16800c743fc826445d6f"],"state_sha256":"c8bbbc3427f28579dccc7b5ee40c7efb33ff6357313a6b192732ce08f97cc26d"}