{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KGQPO5CCPSRWAILVWXUHCVXNXU","short_pith_number":"pith:KGQPO5CC","schema_version":"1.0","canonical_sha256":"51a0f774427ca3602175b5e87156edbd1689402a842b720b617fb619c4f53684","source":{"kind":"arxiv","id":"2407.03469","version":1},"attestation_state":"computed","paper":{"title":"Scaling Data-Driven Building Energy Modelling using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Liang Zhang, Sunil Khadka","submitted_at":"2024-07-03T19:34:24Z","abstract_excerpt":"Building Management System (BMS) through a data-driven method always faces data and model scalability issues. We propose a methodology to tackle the scalability challenges associated with the development of data-driven models for BMS by using Large Language Models (LLMs). LLMs' code generation adaptability can enable broader adoption of BMS by \"automating the automation,\" particularly the data handling and data-driven modeling processes. In this paper, we use LLMs to generate code that processes structured data from BMS and build data-driven models for BMS's specific requirements. This elimina"},"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":"2407.03469","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-07-03T19:34:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e3015fcfc1715533385f600f3a319ae3f32e9a0b017d9c9269d54abf481071df","abstract_canon_sha256":"462e397732df4d9fd860f361efdb2a99b3dc0d9dffa5799abc4e81dc1ab5d34f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:55.385653Z","signature_b64":"2XfWTXhEbZaxuEDKhCEqH//9eRTH3c1XkWGgzU+x3HVj6BPdzH2eoQNrlp4TinaWLALWpM9Pmn58JPLQqP86DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51a0f774427ca3602175b5e87156edbd1689402a842b720b617fb619c4f53684","last_reissued_at":"2026-07-05T08:39:55.385258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:55.385258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Data-Driven Building Energy Modelling using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Liang Zhang, Sunil Khadka","submitted_at":"2024-07-03T19:34:24Z","abstract_excerpt":"Building Management System (BMS) through a data-driven method always faces data and model scalability issues. We propose a methodology to tackle the scalability challenges associated with the development of data-driven models for BMS by using Large Language Models (LLMs). LLMs' code generation adaptability can enable broader adoption of BMS by \"automating the automation,\" particularly the data handling and data-driven modeling processes. In this paper, we use LLMs to generate code that processes structured data from BMS and build data-driven models for BMS's specific requirements. This elimina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03469","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/2407.03469/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":"2407.03469","created_at":"2026-07-05T08:39:55.385320+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03469v1","created_at":"2026-07-05T08:39:55.385320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03469","created_at":"2026-07-05T08:39:55.385320+00:00"},{"alias_kind":"pith_short_12","alias_value":"KGQPO5CCPSRW","created_at":"2026-07-05T08:39:55.385320+00:00"},{"alias_kind":"pith_short_16","alias_value":"KGQPO5CCPSRWAILV","created_at":"2026-07-05T08:39:55.385320+00:00"},{"alias_kind":"pith_short_8","alias_value":"KGQPO5CC","created_at":"2026-07-05T08:39:55.385320+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.11698","citing_title":"Large Language Models in the Data Science Lifecycle: A Systematic Mapping Study","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KGQPO5CCPSRWAILVWXUHCVXNXU","json":"https://pith.science/pith/KGQPO5CCPSRWAILVWXUHCVXNXU.json","graph_json":"https://pith.science/api/pith-number/KGQPO5CCPSRWAILVWXUHCVXNXU/graph.json","events_json":"https://pith.science/api/pith-number/KGQPO5CCPSRWAILVWXUHCVXNXU/events.json","paper":"https://pith.science/paper/KGQPO5CC"},"agent_actions":{"view_html":"https://pith.science/pith/KGQPO5CCPSRWAILVWXUHCVXNXU","download_json":"https://pith.science/pith/KGQPO5CCPSRWAILVWXUHCVXNXU.json","view_paper":"https://pith.science/paper/KGQPO5CC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03469&json=true","fetch_graph":"https://pith.science/api/pith-number/KGQPO5CCPSRWAILVWXUHCVXNXU/graph.json","fetch_events":"https://pith.science/api/pith-number/KGQPO5CCPSRWAILVWXUHCVXNXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KGQPO5CCPSRWAILVWXUHCVXNXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KGQPO5CCPSRWAILVWXUHCVXNXU/action/storage_attestation","attest_author":"https://pith.science/pith/KGQPO5CCPSRWAILVWXUHCVXNXU/action/author_attestation","sign_citation":"https://pith.science/pith/KGQPO5CCPSRWAILVWXUHCVXNXU/action/citation_signature","submit_replication":"https://pith.science/pith/KGQPO5CCPSRWAILVWXUHCVXNXU/action/replication_record"}},"created_at":"2026-07-05T08:39:55.385320+00:00","updated_at":"2026-07-05T08:39:55.385320+00:00"}