{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OB77MC6SQ6WBDVDI66YJJLDJBU","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":"608df2f16312b2bea03bb7409f3a1771c1b02eda9aaee23c23b612a2eace5200","cross_cats_sorted":["cs.SC"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T09:43:14Z","title_canon_sha256":"6d93785dc45a05318874671351a81abe95f6bac6ca1a316108bf9633cf01d41c"},"schema_version":"1.0","source":{"id":"2608.10725","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.10725","created_at":"2026-08-12T01:23:08Z"},{"alias_kind":"arxiv_version","alias_value":"2608.10725v1","created_at":"2026-08-12T01:23:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10725","created_at":"2026-08-12T01:23:08Z"},{"alias_kind":"pith_short_12","alias_value":"OB77MC6SQ6WB","created_at":"2026-08-12T01:23:08Z"},{"alias_kind":"pith_short_16","alias_value":"OB77MC6SQ6WBDVDI","created_at":"2026-08-12T01:23:08Z"},{"alias_kind":"pith_short_8","alias_value":"OB77MC6S","created_at":"2026-08-12T01:23:08Z"}],"graph_snapshots":[{"event_id":"sha256:d5a8a30af165a0fd61dac290782f0cd54867c61f4260d4f959090122312a7d42","target":"graph","created_at":"2026-08-12T01:23:08Z","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/2608.10725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) often rely on shortcuts rather than systematic reasoning, raising safety concerns in medical applications. Allowing models to abstain when uncertain improves reliability but introduces a coverage accuracy tradeoff. We propose a two-stage framework for medical hypothesis verification in multiple-choice settings that manages this tradeoff through targeted ontology grounding, applied only when the model abstains. We show that abstention is not random but reflects genuine uncertainty, with abstained predictions associated with lower confidence. Across two frontier mode","authors_text":"Aditya Koul, Ajo Babu George, Amit Sharma, Anurag Mahipal, Dashpreet Singh, Hriday Rana, Kunal Tilaganji, Manan Jain, Nagarajan Natarajan, Sidharth Gupta, Uma Ranjan, Vineeth Balasubramanian","cross_cats":["cs.SC"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T09:43:14Z","title":"Rethinking LLM Verification: Evidence Structure, Uncertainty, and Selective Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10725","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:e0b81f1d81d048df2cea49a468dd1ae9d1c9f6ca35762c7559e17dac92e3dd85","target":"record","created_at":"2026-08-12T01:23:08Z","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":"608df2f16312b2bea03bb7409f3a1771c1b02eda9aaee23c23b612a2eace5200","cross_cats_sorted":["cs.SC"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-11T09:43:14Z","title_canon_sha256":"6d93785dc45a05318874671351a81abe95f6bac6ca1a316108bf9633cf01d41c"},"schema_version":"1.0","source":{"id":"2608.10725","kind":"arxiv","version":1}},"canonical_sha256":"707ff60bd287ac11d468f7b094ac690d0ccda13cc9d5494672f730d7b4f5a445","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"707ff60bd287ac11d468f7b094ac690d0ccda13cc9d5494672f730d7b4f5a445","first_computed_at":"2026-08-12T01:23:08.558963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T01:23:08.558963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KuAb1TFIvad7SSNAa8kRqTBvCYGqFZYC9lBYCYxc7NaQEiR6Mz2FVtbSdFn7+vMPqh7p5XKHAnkXQpZUvr5HBQ==","signature_status":"signed_v1","signed_at":"2026-08-12T01:23:08.560672Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.10725","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0b81f1d81d048df2cea49a468dd1ae9d1c9f6ca35762c7559e17dac92e3dd85","sha256:d5a8a30af165a0fd61dac290782f0cd54867c61f4260d4f959090122312a7d42"],"state_sha256":"8012bbc3bdccc2202b8ef025f3bf0a6110c6e6e7b9ffb77b92984bb540aaa497"}