{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IRZJNQUQOCMSJJTN5P463PCUV6","short_pith_number":"pith:IRZJNQUQ","schema_version":"1.0","canonical_sha256":"447296c290709924a66debf9edbc54afaa9fcb17f5fdc116f4bbafd495e246e3","source":{"kind":"arxiv","id":"2606.26346","version":1},"attestation_state":"computed","paper":{"title":"How Do Tool-Augmented LLM Agents Perform on Real-World Energy Analytics Tasks?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Akintonde Abbas, Ayodeji Lana, David Akinpelu, Rereloluwa Alimi","submitted_at":"2026-06-24T19:38:21Z","abstract_excerpt":"Agentic benchmarks have emerged across general-purpose and domain-specific settings, including finance, coding, law, and drug discovery, yet energy-domain evaluations remain largely limited to static knowledge recall. This is a critical gap for a sector that requires live data retrieval, specialized regulatory and market knowledge, and multi-step quantitative reasoning under real-world constraints.\n  We present an empirical study of tool-augmented LLM agents on real-world energy market analytics tasks. Our evaluation environment includes 243 expert-curated problems across three categories: (1)"},"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":"2606.26346","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-24T19:38:21Z","cross_cats_sorted":[],"title_canon_sha256":"36758ae2cb6f5f5f3a939e8e3e5052118763dde88c7cde9b4ceec7326fe81876","abstract_canon_sha256":"d71638e2f81a4c5d89ba63704a9d36544b6e8c14532a9ad62ecb9d869bff89ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T00:15:37.405105Z","signature_b64":"CZNPnsqCjo8cRIhaxFS1BpdEGwj8R/r87pr2sHr1DVzM1FxNFrF6mHk71iW3i0vy1xW3ds7+I374LZThId4vAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"447296c290709924a66debf9edbc54afaa9fcb17f5fdc116f4bbafd495e246e3","last_reissued_at":"2026-06-26T00:15:37.404540Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T00:15:37.404540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Do Tool-Augmented LLM Agents Perform on Real-World Energy Analytics Tasks?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Akintonde Abbas, Ayodeji Lana, David Akinpelu, Rereloluwa Alimi","submitted_at":"2026-06-24T19:38:21Z","abstract_excerpt":"Agentic benchmarks have emerged across general-purpose and domain-specific settings, including finance, coding, law, and drug discovery, yet energy-domain evaluations remain largely limited to static knowledge recall. This is a critical gap for a sector that requires live data retrieval, specialized regulatory and market knowledge, and multi-step quantitative reasoning under real-world constraints.\n  We present an empirical study of tool-augmented LLM agents on real-world energy market analytics tasks. Our evaluation environment includes 243 expert-curated problems across three categories: (1)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26346","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/2606.26346/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":"2606.26346","created_at":"2026-06-26T00:15:37.404630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26346v1","created_at":"2026-06-26T00:15:37.404630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26346","created_at":"2026-06-26T00:15:37.404630+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRZJNQUQOCMS","created_at":"2026-06-26T00:15:37.404630+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRZJNQUQOCMSJJTN","created_at":"2026-06-26T00:15:37.404630+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRZJNQUQ","created_at":"2026-06-26T00:15:37.404630+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/IRZJNQUQOCMSJJTN5P463PCUV6","json":"https://pith.science/pith/IRZJNQUQOCMSJJTN5P463PCUV6.json","graph_json":"https://pith.science/api/pith-number/IRZJNQUQOCMSJJTN5P463PCUV6/graph.json","events_json":"https://pith.science/api/pith-number/IRZJNQUQOCMSJJTN5P463PCUV6/events.json","paper":"https://pith.science/paper/IRZJNQUQ"},"agent_actions":{"view_html":"https://pith.science/pith/IRZJNQUQOCMSJJTN5P463PCUV6","download_json":"https://pith.science/pith/IRZJNQUQOCMSJJTN5P463PCUV6.json","view_paper":"https://pith.science/paper/IRZJNQUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26346&json=true","fetch_graph":"https://pith.science/api/pith-number/IRZJNQUQOCMSJJTN5P463PCUV6/graph.json","fetch_events":"https://pith.science/api/pith-number/IRZJNQUQOCMSJJTN5P463PCUV6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRZJNQUQOCMSJJTN5P463PCUV6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRZJNQUQOCMSJJTN5P463PCUV6/action/storage_attestation","attest_author":"https://pith.science/pith/IRZJNQUQOCMSJJTN5P463PCUV6/action/author_attestation","sign_citation":"https://pith.science/pith/IRZJNQUQOCMSJJTN5P463PCUV6/action/citation_signature","submit_replication":"https://pith.science/pith/IRZJNQUQOCMSJJTN5P463PCUV6/action/replication_record"}},"created_at":"2026-06-26T00:15:37.404630+00:00","updated_at":"2026-06-26T00:15:37.404630+00:00"}