{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TDSA7HRATNQ72VJY7YBKFKLY7P","short_pith_number":"pith:TDSA7HRA","schema_version":"1.0","canonical_sha256":"98e40f9e209b61fd5538fe02a2a978fbefaaa234c7e28a44a81773393f1794eb","source":{"kind":"arxiv","id":"2606.18789","version":1},"attestation_state":"computed","paper":{"title":"PowerAgentBench-SS: A Benchmark for Agentic AI in Power System Steady-State Studies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Andrea Pomarico, Costas Mylonas, Emmanouel Varvarigos, Magda Foti, Matheus Duarte, Qian Zhang","submitted_at":"2026-06-17T08:04:12Z","abstract_excerpt":"Power system benchmarks usually evaluate numerical solvers, prediction models, or sequential controllers. These benchmarks are necessary, but they do not directly test whether a Large Language Model (LLM) agent can execute an engineering workflow: inspect a grid case, select tools, call simulators, screen contingencies, propose admissible mitigations, validate results, and produce an auditable evidence trail. This paper introduces PowerAgentBench-SS, a steady-state benchmark framework for evaluating tool-using agents in power system operation and planning studies. The benchmark exposes public "},"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":"2606.18789","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2026-06-17T08:04:12Z","cross_cats_sorted":["cs.SY"],"title_canon_sha256":"01dd8a70f6ed4d93591ab5054bda9633bad88da17ce75b9ef74e57ef22865ddb","abstract_canon_sha256":"fa2fb199f2cd10f2cfdf03495697ae5e1f9739657f9256a8dd5a749895765ffc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:47.311167Z","signature_b64":"CUcchBO2J1LSt0z2BSsQYDNsrtxSbdTrU22Q1ZQQHPTpQAwd4L93XYwdHGv15l1c6/KFOdsOOZ2sc/9VZosdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98e40f9e209b61fd5538fe02a2a978fbefaaa234c7e28a44a81773393f1794eb","last_reissued_at":"2026-06-19T16:11:47.310820Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:47.310820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PowerAgentBench-SS: A Benchmark for Agentic AI in Power System Steady-State Studies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY"],"primary_cat":"eess.SY","authors_text":"Andrea Pomarico, Costas Mylonas, Emmanouel Varvarigos, Magda Foti, Matheus Duarte, Qian Zhang","submitted_at":"2026-06-17T08:04:12Z","abstract_excerpt":"Power system benchmarks usually evaluate numerical solvers, prediction models, or sequential controllers. These benchmarks are necessary, but they do not directly test whether a Large Language Model (LLM) agent can execute an engineering workflow: inspect a grid case, select tools, call simulators, screen contingencies, propose admissible mitigations, validate results, and produce an auditable evidence trail. This paper introduces PowerAgentBench-SS, a steady-state benchmark framework for evaluating tool-using agents in power system operation and planning studies. The benchmark exposes public "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18789","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/2606.18789/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":"2606.18789","created_at":"2026-06-19T16:11:47.310880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18789v1","created_at":"2026-06-19T16:11:47.310880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18789","created_at":"2026-06-19T16:11:47.310880+00:00"},{"alias_kind":"pith_short_12","alias_value":"TDSA7HRATNQ7","created_at":"2026-06-19T16:11:47.310880+00:00"},{"alias_kind":"pith_short_16","alias_value":"TDSA7HRATNQ72VJY","created_at":"2026-06-19T16:11:47.310880+00:00"},{"alias_kind":"pith_short_8","alias_value":"TDSA7HRA","created_at":"2026-06-19T16:11:47.310880+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/TDSA7HRATNQ72VJY7YBKFKLY7P","json":"https://pith.science/pith/TDSA7HRATNQ72VJY7YBKFKLY7P.json","graph_json":"https://pith.science/api/pith-number/TDSA7HRATNQ72VJY7YBKFKLY7P/graph.json","events_json":"https://pith.science/api/pith-number/TDSA7HRATNQ72VJY7YBKFKLY7P/events.json","paper":"https://pith.science/paper/TDSA7HRA"},"agent_actions":{"view_html":"https://pith.science/pith/TDSA7HRATNQ72VJY7YBKFKLY7P","download_json":"https://pith.science/pith/TDSA7HRATNQ72VJY7YBKFKLY7P.json","view_paper":"https://pith.science/paper/TDSA7HRA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18789&json=true","fetch_graph":"https://pith.science/api/pith-number/TDSA7HRATNQ72VJY7YBKFKLY7P/graph.json","fetch_events":"https://pith.science/api/pith-number/TDSA7HRATNQ72VJY7YBKFKLY7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TDSA7HRATNQ72VJY7YBKFKLY7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TDSA7HRATNQ72VJY7YBKFKLY7P/action/storage_attestation","attest_author":"https://pith.science/pith/TDSA7HRATNQ72VJY7YBKFKLY7P/action/author_attestation","sign_citation":"https://pith.science/pith/TDSA7HRATNQ72VJY7YBKFKLY7P/action/citation_signature","submit_replication":"https://pith.science/pith/TDSA7HRATNQ72VJY7YBKFKLY7P/action/replication_record"}},"created_at":"2026-06-19T16:11:47.310880+00:00","updated_at":"2026-06-19T16:11:47.310880+00:00"}