{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WDSPFUSFQH7Y5XEH6RPADPOC26","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":"1a35ce80d586f43fc9ccd641ad2758efbfb88e81c0a7297b461cc9affa41cfc6","cross_cats_sorted":["cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-25T20:11:04Z","title_canon_sha256":"01d268539b0e572a7d31bb0a7764a6046450b4e2e924c71e052f86bec7f4b7e4"},"schema_version":"1.0","source":{"id":"2401.14493","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.14493","created_at":"2026-07-05T07:37:57Z"},{"alias_kind":"arxiv_version","alias_value":"2401.14493v1","created_at":"2026-07-05T07:37:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14493","created_at":"2026-07-05T07:37:57Z"},{"alias_kind":"pith_short_12","alias_value":"WDSPFUSFQH7Y","created_at":"2026-07-05T07:37:57Z"},{"alias_kind":"pith_short_16","alias_value":"WDSPFUSFQH7Y5XEH","created_at":"2026-07-05T07:37:57Z"},{"alias_kind":"pith_short_8","alias_value":"WDSPFUSF","created_at":"2026-07-05T07:37:57Z"}],"graph_snapshots":[{"event_id":"sha256:5e74eeafbe9ef3b36d26037cd2c78e4d7851cb85b33c81f8570bf6e17dc29989","target":"graph","created_at":"2026-07-05T07:37:57Z","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/2401.14493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensuring the accuracy of responses provided by large language models (LLMs) is crucial, particularly in clinical settings where incorrect information may directly impact patient health. To address this challenge, we construct K-QA, a dataset containing 1,212 patient questions originating from real-world conversations held on K Health (an AI-driven clinical platform). We employ a panel of in-house physicians to answer and manually decompose a subset of K-QA into self-contained statements. Additionally, we formulate two NLI-based evaluation metrics approximating recall and precision: (1) compreh","authors_text":"David Cohen, Gabriel Stanovsky, Itay Manes, Naama Ronn, Ran Ilan Ber, Zehavi Horowitz-Kugler","cross_cats":["cs.HC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-25T20:11:04Z","title":"K-QA: A Real-World Medical Q&A Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14493","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":"sha256:5f0b296e3f6e68b373f84143d7d734afca238fddbe0ea5fee6eecd0b7be410fe","target":"record","created_at":"2026-07-05T07:37:57Z","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":"1a35ce80d586f43fc9ccd641ad2758efbfb88e81c0a7297b461cc9affa41cfc6","cross_cats_sorted":["cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-25T20:11:04Z","title_canon_sha256":"01d268539b0e572a7d31bb0a7764a6046450b4e2e924c71e052f86bec7f4b7e4"},"schema_version":"1.0","source":{"id":"2401.14493","kind":"arxiv","version":1}},"canonical_sha256":"b0e4f2d24581ff8edc87f45e01bdc2d78f1d565a9d1a78ef678f030904be55ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0e4f2d24581ff8edc87f45e01bdc2d78f1d565a9d1a78ef678f030904be55ed","first_computed_at":"2026-07-05T07:37:57.591739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:37:57.591739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EK508iMT9qGCwK+w6ejUcaE4hShXqQFKrXcPnyeeQnbZ3OkX6bHGjjKPx/sLjDKWTmfXpnhPRxIUiLYD+8wQDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:37:57.592172Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.14493","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f0b296e3f6e68b373f84143d7d734afca238fddbe0ea5fee6eecd0b7be410fe","sha256:5e74eeafbe9ef3b36d26037cd2c78e4d7851cb85b33c81f8570bf6e17dc29989"],"state_sha256":"3c26eca42887ef683e0b748518834863fee8352d34072890264ede2b51231b30"}