{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:II3HDDAFS5OPCFRX66XXLHLRFQ","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":"03c76abc153a1fce67c13f3229b927f24c4a50f610417a2f338737cb8b77a31f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T06:39:39Z","title_canon_sha256":"a8cd475e65277bab5ed7c44892ded28bc3cd9e1826dfdbfc7827df6fed7703b3"},"schema_version":"1.0","source":{"id":"2507.02983","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02983","created_at":"2026-06-02T01:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02983v3","created_at":"2026-06-02T01:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02983","created_at":"2026-06-02T01:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"II3HDDAFS5OP","created_at":"2026-06-02T01:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"II3HDDAFS5OPCFRX","created_at":"2026-06-02T01:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"II3HDDAF","created_at":"2026-06-02T01:04:14Z"}],"graph_snapshots":[{"event_id":"sha256:32263d851e6c7020575e504a0b2dba9a8c6a18ee6f1049d36db3fce9695c3fcc","target":"graph","created_at":"2026-06-02T01:04:14Z","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/2507.02983/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) hold significant promise for transforming digital health by enabling automated medical question answering. However, ensuring these models meet critical industry standards for factual accuracy, usefulness, and safety remains a challenge, especially for open-source solutions. We present a rigorous benchmarking framework using a dataset of over 1,000 health questions. We assess model performance across honesty, helpfulness, and harmlessness. Our results highlight trade-offs between factual reliability and safety among evaluated models -- Mistral-7B, BioMistral-7B-DARE","authors_text":"Ebad Shabbir, Gautam Siddharth Kashyap, Jiechao Gao, Mohammad Anas Azeez, Rafiq Ali, Usman Naseem, Zohaib Hasan Siddiqui","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T06:39:39Z","title":"Truth, Trust, and Trouble: Medical AI on the Edge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02983","kind":"arxiv","version":3},"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:a13208965b6ee59810300e042147f037ead4f9646f4c6713f2069cd6c19456a0","target":"record","created_at":"2026-06-02T01:04:14Z","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":"03c76abc153a1fce67c13f3229b927f24c4a50f610417a2f338737cb8b77a31f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T06:39:39Z","title_canon_sha256":"a8cd475e65277bab5ed7c44892ded28bc3cd9e1826dfdbfc7827df6fed7703b3"},"schema_version":"1.0","source":{"id":"2507.02983","kind":"arxiv","version":3}},"canonical_sha256":"4236718c05975cf11637f7af759d712c300078c5a0d18a3373414ad6bcaf44f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4236718c05975cf11637f7af759d712c300078c5a0d18a3373414ad6bcaf44f4","first_computed_at":"2026-06-02T01:04:14.796086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:14.796086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CJxSaAMoLG4AtxtzdBocZHRg4v3eC82K1uxg5qHNCeJkNoXDY1SFIvPlaBJI+VHEvqz6m3SNcDy9AZJtMI3HAA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:14.796569Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02983","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a13208965b6ee59810300e042147f037ead4f9646f4c6713f2069cd6c19456a0","sha256:32263d851e6c7020575e504a0b2dba9a8c6a18ee6f1049d36db3fce9695c3fcc"],"state_sha256":"d652cb766417450b5c7734cbfff8d52626af308fa96b92f3ace64ec0e1d9cc1c"}