{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YI6C52JS5N66JDO2WCK73D4KMU","short_pith_number":"pith:YI6C52JS","schema_version":"1.0","canonical_sha256":"c23c2ee932eb7de48ddab095fd8f8a653f4739bbccf1a59ed90283df16920b22","source":{"kind":"arxiv","id":"2605.31478","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Boundary Probing and Demand-Guided Intervention for LLM-Based Power System Code Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.SY","eess.SY"],"primary_cat":"cs.SE","authors_text":"Hui Wu, Xiaoyang Wang, Zhong Fan","submitted_at":"2026-05-29T16:06:34Z","abstract_excerpt":"Large language models (LLMs) are increasingly used to automate power-system analysis, but many utilities and energy-research labs require on-premise serving for confidentiality, regulatory, reproducibility, and cost reasons. This makes the reliability of open-weight models a deployment issue. We show that first-pass failures in power-system code generation are dominated not by reasoning alone, but by structured API-knowledge boundary errors: hallucinated function names, misused parameters, and mishandled result tables in versioned simulation libraries.\n  We introduce PowerCodeBench, an executi"},"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":"2605.31478","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-29T16:06:34Z","cross_cats_sorted":["cs.CL","cs.SY","eess.SY"],"title_canon_sha256":"0b153243706d15ccff9542a874db8944649860edae0665bf0996494aa2e29d32","abstract_canon_sha256":"961d57cc07df87236e5fe7f8b1c71137deb556fd871675f0e7c8da08760f640d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:04:08.159044Z","signature_b64":"zSLkm3LHiK7zGlvElTI2aDqI5LUJF1gufx3PVc592n9IA9ooH4ASneEbXRJXQdK0TPGZKychnVSh2KItvn1PDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c23c2ee932eb7de48ddab095fd8f8a653f4739bbccf1a59ed90283df16920b22","last_reissued_at":"2026-06-01T02:04:08.158307Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:04:08.158307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Boundary Probing and Demand-Guided Intervention for LLM-Based Power System Code Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.SY","eess.SY"],"primary_cat":"cs.SE","authors_text":"Hui Wu, Xiaoyang Wang, Zhong Fan","submitted_at":"2026-05-29T16:06:34Z","abstract_excerpt":"Large language models (LLMs) are increasingly used to automate power-system analysis, but many utilities and energy-research labs require on-premise serving for confidentiality, regulatory, reproducibility, and cost reasons. This makes the reliability of open-weight models a deployment issue. We show that first-pass failures in power-system code generation are dominated not by reasoning alone, but by structured API-knowledge boundary errors: hallucinated function names, misused parameters, and mishandled result tables in versioned simulation libraries.\n  We introduce PowerCodeBench, an executi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.31478","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/2605.31478/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":"2605.31478","created_at":"2026-06-01T02:04:08.158421+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.31478v1","created_at":"2026-06-01T02:04:08.158421+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.31478","created_at":"2026-06-01T02:04:08.158421+00:00"},{"alias_kind":"pith_short_12","alias_value":"YI6C52JS5N66","created_at":"2026-06-01T02:04:08.158421+00:00"},{"alias_kind":"pith_short_16","alias_value":"YI6C52JS5N66JDO2","created_at":"2026-06-01T02:04:08.158421+00:00"},{"alias_kind":"pith_short_8","alias_value":"YI6C52JS","created_at":"2026-06-01T02:04:08.158421+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/YI6C52JS5N66JDO2WCK73D4KMU","json":"https://pith.science/pith/YI6C52JS5N66JDO2WCK73D4KMU.json","graph_json":"https://pith.science/api/pith-number/YI6C52JS5N66JDO2WCK73D4KMU/graph.json","events_json":"https://pith.science/api/pith-number/YI6C52JS5N66JDO2WCK73D4KMU/events.json","paper":"https://pith.science/paper/YI6C52JS"},"agent_actions":{"view_html":"https://pith.science/pith/YI6C52JS5N66JDO2WCK73D4KMU","download_json":"https://pith.science/pith/YI6C52JS5N66JDO2WCK73D4KMU.json","view_paper":"https://pith.science/paper/YI6C52JS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.31478&json=true","fetch_graph":"https://pith.science/api/pith-number/YI6C52JS5N66JDO2WCK73D4KMU/graph.json","fetch_events":"https://pith.science/api/pith-number/YI6C52JS5N66JDO2WCK73D4KMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YI6C52JS5N66JDO2WCK73D4KMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YI6C52JS5N66JDO2WCK73D4KMU/action/storage_attestation","attest_author":"https://pith.science/pith/YI6C52JS5N66JDO2WCK73D4KMU/action/author_attestation","sign_citation":"https://pith.science/pith/YI6C52JS5N66JDO2WCK73D4KMU/action/citation_signature","submit_replication":"https://pith.science/pith/YI6C52JS5N66JDO2WCK73D4KMU/action/replication_record"}},"created_at":"2026-06-01T02:04:08.158421+00:00","updated_at":"2026-06-01T02:04:08.158421+00:00"}