{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:27K2IW4OLVEAQMLACV27QB4WAB","short_pith_number":"pith:27K2IW4O","schema_version":"1.0","canonical_sha256":"d7d5a45b8e5d480831601575f807960067d3f81a5c3effb111cf804e73746f7f","source":{"kind":"arxiv","id":"2411.10599","version":2},"attestation_state":"computed","paper":{"title":"Generating Energy-efficient code with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Ana Oprescu, Pepijn de Reus, Tom Cappendijk","submitted_at":"2024-11-15T21:45:58Z","abstract_excerpt":"The increasing electricity demands of personal computers, communication networks, and data centers contribute to higher atmospheric greenhouse gas emissions, which in turn lead to global warming and climate change. Therefore the energy consumption of code must be minimized. Code can be generated by large language models. We look at the influence of prompt modification on the energy consumption of the code generated. We use three different Python code problems of varying difficulty levels. Prompt modification is done by adding the sentence ``Give me an energy-optimized solution for this problem"},"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":"2411.10599","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-15T21:45:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f242e6080ea7137c4d029f3f02a0641e99f43d8211962205c77ef78e80c157cf","abstract_canon_sha256":"e85c6d45b48a8fa668dcacf7e91beda6b17b869e79e54b5ddeb0047ac4883806"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:05.463234Z","signature_b64":"Vot7qDRmY692Dbye4uSSKTO7/WPIIR4c97ascLH56dE8RYL6kNkYZMflvGME49d3DJYShK3E0qoMXTnj4LOFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7d5a45b8e5d480831601575f807960067d3f81a5c3effb111cf804e73746f7f","last_reissued_at":"2026-07-05T11:25:05.462729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:05.462729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Energy-efficient code with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Ana Oprescu, Pepijn de Reus, Tom Cappendijk","submitted_at":"2024-11-15T21:45:58Z","abstract_excerpt":"The increasing electricity demands of personal computers, communication networks, and data centers contribute to higher atmospheric greenhouse gas emissions, which in turn lead to global warming and climate change. Therefore the energy consumption of code must be minimized. Code can be generated by large language models. We look at the influence of prompt modification on the energy consumption of the code generated. We use three different Python code problems of varying difficulty levels. Prompt modification is done by adding the sentence ``Give me an energy-optimized solution for this problem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10599","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/2411.10599/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":"2411.10599","created_at":"2026-07-05T11:25:05.462790+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10599v2","created_at":"2026-07-05T11:25:05.462790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10599","created_at":"2026-07-05T11:25:05.462790+00:00"},{"alias_kind":"pith_short_12","alias_value":"27K2IW4OLVEA","created_at":"2026-07-05T11:25:05.462790+00:00"},{"alias_kind":"pith_short_16","alias_value":"27K2IW4OLVEAQMLA","created_at":"2026-07-05T11:25:05.462790+00:00"},{"alias_kind":"pith_short_8","alias_value":"27K2IW4O","created_at":"2026-07-05T11:25:05.462790+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06826","citing_title":"SkelDPO: A Skeleton-Guided Direct Preference Optimization Framework for Efficient Code Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06821","citing_title":"Chiseling Out Efficiency: Structured Skeleton Supervision for Efficient Code Generation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02352","citing_title":"An Initial Exploration of Contrastive Prompt Tuning to Generate Energy-Efficient Code","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/27K2IW4OLVEAQMLACV27QB4WAB","json":"https://pith.science/pith/27K2IW4OLVEAQMLACV27QB4WAB.json","graph_json":"https://pith.science/api/pith-number/27K2IW4OLVEAQMLACV27QB4WAB/graph.json","events_json":"https://pith.science/api/pith-number/27K2IW4OLVEAQMLACV27QB4WAB/events.json","paper":"https://pith.science/paper/27K2IW4O"},"agent_actions":{"view_html":"https://pith.science/pith/27K2IW4OLVEAQMLACV27QB4WAB","download_json":"https://pith.science/pith/27K2IW4OLVEAQMLACV27QB4WAB.json","view_paper":"https://pith.science/paper/27K2IW4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10599&json=true","fetch_graph":"https://pith.science/api/pith-number/27K2IW4OLVEAQMLACV27QB4WAB/graph.json","fetch_events":"https://pith.science/api/pith-number/27K2IW4OLVEAQMLACV27QB4WAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/27K2IW4OLVEAQMLACV27QB4WAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/27K2IW4OLVEAQMLACV27QB4WAB/action/storage_attestation","attest_author":"https://pith.science/pith/27K2IW4OLVEAQMLACV27QB4WAB/action/author_attestation","sign_citation":"https://pith.science/pith/27K2IW4OLVEAQMLACV27QB4WAB/action/citation_signature","submit_replication":"https://pith.science/pith/27K2IW4OLVEAQMLACV27QB4WAB/action/replication_record"}},"created_at":"2026-07-05T11:25:05.462790+00:00","updated_at":"2026-07-05T11:25:05.462790+00:00"}