{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NAQNS6QXWGTGTEYYJKNZPIBJ4M","short_pith_number":"pith:NAQNS6QX","schema_version":"1.0","canonical_sha256":"6820d97a17b1a66993184a9b97a029e32e43087fb409be11636523f85d4775c5","source":{"kind":"arxiv","id":"2607.22067","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Fine-tuning and Retrieval Strategies for a Multimodal Language Model on the NRC Reactor Operator Licensing Examination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Isak Hwang, Yoon Pyo Lee","submitted_at":"2026-07-24T08:10:21Z","abstract_excerpt":"The integration of large language models (LLMs) into the nuclear power industry requires outputs grounded in domain-specific knowledge. This study evaluates a 31-billion-parameter open-weight multimodal model (Gemma 4 31B-IT) on its capacity to apply nuclear knowledge by benchmarking eight model-retrieval configurations against the U.S. Nuclear Regulatory Commission (NRC) Reactor Operator licensing examination. We evaluate 14 Generic Fundamentals Examinations (GFE) from the 2015-2021 March sittings (seven pressurized and seven boiling water reactor exams) using the standard 80% human passing c"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.22067","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-24T08:10:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7484f33a78d83fa65460e21fdab90774a292bb5d41197e079c6d1e9cd8358edc","abstract_canon_sha256":"134839887add6073a23acb2e28b1775f141b4abfea9a8e099841d30164bc3285"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:20:46.226453Z","signature_b64":"Cl2zHXnlFt4Ej1yvicEjfnBfQU7MJghIeRnAjeRLdlA5vPrv3ESUrwEbsGiImAG/t+jfywJ19SddN8UwqzYVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6820d97a17b1a66993184a9b97a029e32e43087fb409be11636523f85d4775c5","last_reissued_at":"2026-07-27T01:20:46.225572Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:20:46.225572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Fine-tuning and Retrieval Strategies for a Multimodal Language Model on the NRC Reactor Operator Licensing Examination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Isak Hwang, Yoon Pyo Lee","submitted_at":"2026-07-24T08:10:21Z","abstract_excerpt":"The integration of large language models (LLMs) into the nuclear power industry requires outputs grounded in domain-specific knowledge. This study evaluates a 31-billion-parameter open-weight multimodal model (Gemma 4 31B-IT) on its capacity to apply nuclear knowledge by benchmarking eight model-retrieval configurations against the U.S. Nuclear Regulatory Commission (NRC) Reactor Operator licensing examination. We evaluate 14 Generic Fundamentals Examinations (GFE) from the 2015-2021 March sittings (seven pressurized and seven boiling water reactor exams) using the standard 80% human passing c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22067","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.22067/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.22067","created_at":"2026-07-27T01:20:46.226032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22067v1","created_at":"2026-07-27T01:20:46.226032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22067","created_at":"2026-07-27T01:20:46.226032+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAQNS6QXWGTG","created_at":"2026-07-27T01:20:46.226032+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAQNS6QXWGTGTEYY","created_at":"2026-07-27T01:20:46.226032+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAQNS6QX","created_at":"2026-07-27T01:20:46.226032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NAQNS6QXWGTGTEYYJKNZPIBJ4M","json":"https://pith.science/pith/NAQNS6QXWGTGTEYYJKNZPIBJ4M.json","graph_json":"https://pith.science/api/pith-number/NAQNS6QXWGTGTEYYJKNZPIBJ4M/graph.json","events_json":"https://pith.science/api/pith-number/NAQNS6QXWGTGTEYYJKNZPIBJ4M/events.json","paper":"https://pith.science/paper/NAQNS6QX"},"agent_actions":{"view_html":"https://pith.science/pith/NAQNS6QXWGTGTEYYJKNZPIBJ4M","download_json":"https://pith.science/pith/NAQNS6QXWGTGTEYYJKNZPIBJ4M.json","view_paper":"https://pith.science/paper/NAQNS6QX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22067&json=true","fetch_graph":"https://pith.science/api/pith-number/NAQNS6QXWGTGTEYYJKNZPIBJ4M/graph.json","fetch_events":"https://pith.science/api/pith-number/NAQNS6QXWGTGTEYYJKNZPIBJ4M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAQNS6QXWGTGTEYYJKNZPIBJ4M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAQNS6QXWGTGTEYYJKNZPIBJ4M/action/storage_attestation","attest_author":"https://pith.science/pith/NAQNS6QXWGTGTEYYJKNZPIBJ4M/action/author_attestation","sign_citation":"https://pith.science/pith/NAQNS6QXWGTGTEYYJKNZPIBJ4M/action/citation_signature","submit_replication":"https://pith.science/pith/NAQNS6QXWGTGTEYYJKNZPIBJ4M/action/replication_record"}},"created_at":"2026-07-27T01:20:46.226032+00:00","updated_at":"2026-07-27T01:20:46.226032+00:00"}