{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YG6HTKLGBU2EBMTSIBUDQ6X7IB","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":"a063c85b1b8d1c730a60434798280be46a13fb70034053aba03b70153acfa2b5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-10T21:44:20Z","title_canon_sha256":"fa2322b0146ab055df6dbc9a717e914742a14262fb0fa551a43f96bf456c62ba"},"schema_version":"1.0","source":{"id":"2606.12702","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12702","created_at":"2026-06-12T01:08:46Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12702v1","created_at":"2026-06-12T01:08:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12702","created_at":"2026-06-12T01:08:46Z"},{"alias_kind":"pith_short_12","alias_value":"YG6HTKLGBU2E","created_at":"2026-06-12T01:08:46Z"},{"alias_kind":"pith_short_16","alias_value":"YG6HTKLGBU2EBMTS","created_at":"2026-06-12T01:08:46Z"},{"alias_kind":"pith_short_8","alias_value":"YG6HTKLG","created_at":"2026-06-12T01:08:46Z"}],"graph_snapshots":[{"event_id":"sha256:a4f31f3121310971b4518fd2307fc470dce8dc27022bd38630da4853051a103e","target":"graph","created_at":"2026-06-12T01:08:46Z","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/2606.12702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly integrated into clinical systems, making it essential to evaluate the real-world utility of these systems. However, static benchmarks tend to measure correctness rather than user acceptance, aggregate performance across queries, and require densely annotated datasets -- leading to major blind spots for evaluating clinical systems. In this work, we perform a deployment-centered evaluation of an LLM system embedded within electronic health records at an academic medical center, where user feedback is sparse but closely reflects the deployment conditi","authors_text":"Alyssa Unell, Brenna Li, Bridget Lin, Meena Jagadeesan, Miguel Fuentes, Nigam Shah, Sanmi Koyejo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-10T21:44:20Z","title":"Deployment-Centered Evaluation: Predicting Query-Level Rejection Risk in a Clinical LLM System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12702","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:aaf6df5d6cfec49bcd44778e64e8d713ce0cf55c7b3c39ca3e9eca890d21cb17","target":"record","created_at":"2026-06-12T01:08:46Z","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":"a063c85b1b8d1c730a60434798280be46a13fb70034053aba03b70153acfa2b5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-10T21:44:20Z","title_canon_sha256":"fa2322b0146ab055df6dbc9a717e914742a14262fb0fa551a43f96bf456c62ba"},"schema_version":"1.0","source":{"id":"2606.12702","kind":"arxiv","version":1}},"canonical_sha256":"c1bc79a9660d3440b2724068387aff404cc357f590790fd960060909d4df115d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1bc79a9660d3440b2724068387aff404cc357f590790fd960060909d4df115d","first_computed_at":"2026-06-12T01:08:46.273477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:08:46.273477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q2JpcxrfMx9auGjQH/NI369y6xqOkuChKDhh2HnXRTZegLmh76KddmGpn0gKXpWLtGycz7VfYVR0pPlR4GY1CA==","signature_status":"signed_v1","signed_at":"2026-06-12T01:08:46.274283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12702","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aaf6df5d6cfec49bcd44778e64e8d713ce0cf55c7b3c39ca3e9eca890d21cb17","sha256:a4f31f3121310971b4518fd2307fc470dce8dc27022bd38630da4853051a103e"],"state_sha256":"1301caf4cd9aaf18528980bbc58cef748f1a4efe2221d5b167e47fcfb1cf8d1b"}