{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FXDB3IQK4SUODOHY3N7HS7MWPF","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":"9946eb343488b13f07a55377279bc6eef44715772d5a30eaf1a5d9406f1ff09b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-06T08:52:45Z","title_canon_sha256":"0cd1ee7b893306a376bd3ba109a9f04df8445bbd1249599d2fdcd91bd7582db0"},"schema_version":"1.0","source":{"id":"2607.13036","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13036","created_at":"2026-07-16T00:21:53Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13036v1","created_at":"2026-07-16T00:21:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13036","created_at":"2026-07-16T00:21:53Z"},{"alias_kind":"pith_short_12","alias_value":"FXDB3IQK4SUO","created_at":"2026-07-16T00:21:53Z"},{"alias_kind":"pith_short_16","alias_value":"FXDB3IQK4SUODOHY","created_at":"2026-07-16T00:21:53Z"},{"alias_kind":"pith_short_8","alias_value":"FXDB3IQK","created_at":"2026-07-16T00:21:53Z"}],"graph_snapshots":[{"event_id":"sha256:86cc92e877182e65755b7e25e75a95802bf7ce488afe6c1e66bfe8be5a8c76dd","target":"graph","created_at":"2026-07-16T00:21:53Z","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/2607.13036/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used for decision support in healthcare, but clinical evidence is often incomplete or evolving. When the available information is insufficient to support a reliable answer, models should request clarification or abstain rather than provide unsupported responses. Existing medical benchmarks, however, typically assume that complete information is available upfront. We introduce Safe-Psych, a sequential benchmark for evaluating how LLMs handle evolving diagnostic uncertainty in clinical psychiatry. Safe-Psych contains over 1,000 real-world psychiatric","authors_text":"Alireza Nik, Andreea Grama, Bogdan Ionescu, Ciprian I. B\\u{a}cil\\u{a}, Jaya Ojha, Larisa Irimin\\u{a}, Michael A. Riegler, Oriana Presacan, Vajira Thambawita","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-06T08:52:45Z","title":"Ask Before You Diagnose: Safe-Psych, a Sequential Evaluation Benchmark for LLMs in Psychiatry"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13036","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":"sha256:2e39426330b5ab59e6040284b148ed56930ecb2997e670f0216cc1da0ce9a593","target":"record","created_at":"2026-07-16T00:21:53Z","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":"9946eb343488b13f07a55377279bc6eef44715772d5a30eaf1a5d9406f1ff09b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-06T08:52:45Z","title_canon_sha256":"0cd1ee7b893306a376bd3ba109a9f04df8445bbd1249599d2fdcd91bd7582db0"},"schema_version":"1.0","source":{"id":"2607.13036","kind":"arxiv","version":1}},"canonical_sha256":"2dc61da20ae4a8e1b8f8db7e797d96797cfd94a374ffd0bd9f5ca7d6593164f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2dc61da20ae4a8e1b8f8db7e797d96797cfd94a374ffd0bd9f5ca7d6593164f5","first_computed_at":"2026-07-16T00:21:53.081117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T00:21:53.081117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M7up/I7pAxO73NIkcuxDtbzAiHGi2rE6sgTLEWieee41T5XVXkjHXsAP82S+cW6ORTfmq1Pa/3czlnqclVqcCQ==","signature_status":"signed_v1","signed_at":"2026-07-16T00:21:53.081958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.13036","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e39426330b5ab59e6040284b148ed56930ecb2997e670f0216cc1da0ce9a593","sha256:86cc92e877182e65755b7e25e75a95802bf7ce488afe6c1e66bfe8be5a8c76dd"],"state_sha256":"cdca201db0ca66d2299841bf76e54b6005d4db12cb017f70760b5ae404b2b09d"}