{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:T4CU7WA7CXW5V2CAP2LXPAWFME","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":"abc4fdbda7eed34c27f0bbae3f11c6f1b550f084f11ad630d47e47e0293fd957","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-12-16T20:19:23Z","title_canon_sha256":"2243ad55059d1b6244ff2819e81be3cae2f277c97e0405112f62f6d0027c6ef4"},"schema_version":"1.0","source":{"id":"2512.14896","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.14896","created_at":"2026-05-21T01:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2512.14896v2","created_at":"2026-05-21T01:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.14896","created_at":"2026-05-21T01:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"T4CU7WA7CXW5","created_at":"2026-05-21T01:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"T4CU7WA7CXW5V2CA","created_at":"2026-05-21T01:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"T4CU7WA7","created_at":"2026-05-21T01:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:8fa6a13c352b7c4fb606aa00ee4fda5a000d23cdd7d90dcdde6615e9a7e81c30","target":"graph","created_at":"2026-05-21T01:05:13Z","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/2512.14896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In our study, we evaluated large language model (LLM) performance on pharmacy licensure-style question-answering tasks and developed an external knowledge integration method to improve accuracy. We benchmarked ten LLMs with varying parameter sizes (8 billion to 70+ billion) using a 141-question pharmacy dataset, measuring baseline accuracy without modification. Baseline performance ranged from 46% to 92%, with GPT-5 (92%) and o3 (89%) achieving the highest scores, while smaller open-source models showed substantially lower performance. We then developed DrugRAG, a three-step retrieval-augmente","authors_text":"Ali Sabzi, Armin Khosravi, Babak Khalaj, Farbod Davoodi, Fatemeh Latifi, Glolamali Aminian, Houman Kazemzadeh, Kiarash Mokhtari Dizaji, Mohammad Hossein Rohban, MohammadReza KarimiNejad, Parham Abed Azad, Seyed Reza Tavakoli, Siavash Ahmadi, Tahereh Javaheri, Zohreh Amoozgar","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-12-16T20:19:23Z","title":"DrugRAG: Enhancing Pharmacy LLM Performance Through A Novel Retrieval-Augmented Generation Pipeline"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.14896","kind":"arxiv","version":2},"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:bbd035e5dfd990ab8f9855c2e3b01fab07a907785b8857b72d7828fa913cad8e","target":"record","created_at":"2026-05-21T01:05:13Z","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":"abc4fdbda7eed34c27f0bbae3f11c6f1b550f084f11ad630d47e47e0293fd957","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-12-16T20:19:23Z","title_canon_sha256":"2243ad55059d1b6244ff2819e81be3cae2f277c97e0405112f62f6d0027c6ef4"},"schema_version":"1.0","source":{"id":"2512.14896","kind":"arxiv","version":2}},"canonical_sha256":"9f054fd81f15eddae8407e977782c561038eb1d583af964a35405a2415fa3e70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f054fd81f15eddae8407e977782c561038eb1d583af964a35405a2415fa3e70","first_computed_at":"2026-05-21T01:05:13.631908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:13.631908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TVGedejDoTKY9jA4UqKx+HIzKc1cZZUnAGwOarBZSnOEYKRkdo+prs4gx/8yhuQ7LyX5flnSj/4Ykvmk0wZlDg==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:13.633074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.14896","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbd035e5dfd990ab8f9855c2e3b01fab07a907785b8857b72d7828fa913cad8e","sha256:8fa6a13c352b7c4fb606aa00ee4fda5a000d23cdd7d90dcdde6615e9a7e81c30"],"state_sha256":"ed3b642393a51794c1b021b36544c75d2e0dcf65cf45c9b132a2becfd17dfd17"}