{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6GBIU4GGVC3RNEKN7S4GHD2RWA","short_pith_number":"pith:6GBIU4GG","schema_version":"1.0","canonical_sha256":"f1828a70c6a8b716914dfcb8638f51b011e67e096021bc17324858294740d544","source":{"kind":"arxiv","id":"2407.05365","version":2},"attestation_state":"computed","paper":{"title":"ElecBench: a Power Dispatch Evaluation Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gaoqi Liang, Guolong Liu, Huan Zhao, Junhua Zhao, Wenxuan Liu, Xiyuan Zhou, Yan Xu, Yuheng Cheng, Yuji Cao","submitted_at":"2024-07-07T13:38:05Z","abstract_excerpt":"In response to the urgent demand for grid stability and the complex challenges posed by renewable energy integration and electricity market dynamics, the power sector increasingly seeks innovative technological solutions. In this context, large language models (LLMs) have become a key technology to improve efficiency and promote intelligent progress in the power sector with their excellent natural language processing, logical reasoning, and generalization capabilities. Despite their potential, the absence of a performance evaluation benchmark for LLM in the power sector has limited the effecti"},"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":"2407.05365","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-07T13:38:05Z","cross_cats_sorted":[],"title_canon_sha256":"ea98cea7a24e654f0a04f88b470f8f8fb4f415cd482b49746285e7ebae7d7c5d","abstract_canon_sha256":"bd7c64d1d7788e852fa935d280db4322877c11a8f06aca599274b3189f7bdc1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:15.295293Z","signature_b64":"EKFTEqgX4vPYEqFg4bRL2lt0Jf/vl0w+r3EgqGho84eoEiHirQbOog2rY8dHcJxsnij1sskjHgKHOZSAAmpWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1828a70c6a8b716914dfcb8638f51b011e67e096021bc17324858294740d544","last_reissued_at":"2026-07-05T08:54:15.294818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:15.294818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ElecBench: a Power Dispatch Evaluation Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gaoqi Liang, Guolong Liu, Huan Zhao, Junhua Zhao, Wenxuan Liu, Xiyuan Zhou, Yan Xu, Yuheng Cheng, Yuji Cao","submitted_at":"2024-07-07T13:38:05Z","abstract_excerpt":"In response to the urgent demand for grid stability and the complex challenges posed by renewable energy integration and electricity market dynamics, the power sector increasingly seeks innovative technological solutions. In this context, large language models (LLMs) have become a key technology to improve efficiency and promote intelligent progress in the power sector with their excellent natural language processing, logical reasoning, and generalization capabilities. Despite their potential, the absence of a performance evaluation benchmark for LLM in the power sector has limited the effecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05365","kind":"arxiv","version":2},"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/2407.05365/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":"2407.05365","created_at":"2026-07-05T08:54:15.294875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05365v2","created_at":"2026-07-05T08:54:15.294875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05365","created_at":"2026-07-05T08:54:15.294875+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GBIU4GGVC3R","created_at":"2026-07-05T08:54:15.294875+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GBIU4GGVC3RNEKN","created_at":"2026-07-05T08:54:15.294875+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GBIU4GG","created_at":"2026-07-05T08:54:15.294875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26346","citing_title":"How Do Tool-Augmented LLM Agents Perform on Real-World Energy Analytics Tasks?","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20950","citing_title":"Power Systems Agent Benchmark: Executable Evaluation of AI Agents in Electric Power Engineering","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20950","citing_title":"Power Systems Agent Benchmark: Executable Evaluation of AI Agents in Electric Power Engineering","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31478","citing_title":"Knowledge Boundary Probing and Demand-Guided Intervention for LLM-Based Power System Code Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2509.17677","citing_title":"EngiBench: A Benchmark for Evaluating Large Language Models on Engineering Problem Solving","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10159","citing_title":"Enhancing Large Language Model-Based Systems for End-to-End Circuit Analysis Problem Solving","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GBIU4GGVC3RNEKN7S4GHD2RWA","json":"https://pith.science/pith/6GBIU4GGVC3RNEKN7S4GHD2RWA.json","graph_json":"https://pith.science/api/pith-number/6GBIU4GGVC3RNEKN7S4GHD2RWA/graph.json","events_json":"https://pith.science/api/pith-number/6GBIU4GGVC3RNEKN7S4GHD2RWA/events.json","paper":"https://pith.science/paper/6GBIU4GG"},"agent_actions":{"view_html":"https://pith.science/pith/6GBIU4GGVC3RNEKN7S4GHD2RWA","download_json":"https://pith.science/pith/6GBIU4GGVC3RNEKN7S4GHD2RWA.json","view_paper":"https://pith.science/paper/6GBIU4GG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05365&json=true","fetch_graph":"https://pith.science/api/pith-number/6GBIU4GGVC3RNEKN7S4GHD2RWA/graph.json","fetch_events":"https://pith.science/api/pith-number/6GBIU4GGVC3RNEKN7S4GHD2RWA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GBIU4GGVC3RNEKN7S4GHD2RWA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GBIU4GGVC3RNEKN7S4GHD2RWA/action/storage_attestation","attest_author":"https://pith.science/pith/6GBIU4GGVC3RNEKN7S4GHD2RWA/action/author_attestation","sign_citation":"https://pith.science/pith/6GBIU4GGVC3RNEKN7S4GHD2RWA/action/citation_signature","submit_replication":"https://pith.science/pith/6GBIU4GGVC3RNEKN7S4GHD2RWA/action/replication_record"}},"created_at":"2026-07-05T08:54:15.294875+00:00","updated_at":"2026-07-05T08:54:15.294875+00:00"}