{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AGX6555ONDXCAAYMOPBMBMKFCF","short_pith_number":"pith:AGX6555O","schema_version":"1.0","canonical_sha256":"01afeef7ae68ee20030c73c2c0b145114dad0bf9a66cc5f40104ef01ea551c93","source":{"kind":"arxiv","id":"2412.00329","version":2},"attestation_state":"computed","paper":{"title":"Language Models in Software Development Tasks: An Experimental Analysis of Energy and Accuracy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Boris Belchev, Fernando Castor, Negar Alizadeh, Nishant Saurabh, Patricia Kelbert","submitted_at":"2024-11-30T03:02:50Z","abstract_excerpt":"The use of generative AI-based coding assistants like ChatGPT and Github Copilot is a reality in contemporary software development. Many of these tools are provided as remote APIs. Using third-party APIs raises data privacy and security concerns for client companies, which motivates the use of locally-deployed language models. In this study, we explore the trade-off between model accuracy and energy consumption, aiming to provide valuable insights to help developers make informed decisions when selecting a language model. We investigate the performance of 18 families of LLMs in typical softwar"},"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":"2412.00329","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-30T03:02:50Z","cross_cats_sorted":[],"title_canon_sha256":"2dddbb6dead2096ab136e9d27b3da29cc6ed810b7452e49b735490de48999b02","abstract_canon_sha256":"441edb63f861941ef69ec805e59e3e927f30d30191b816341919f794e34e9862"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:08.163257Z","signature_b64":"eUIQXlSHJLkNhcKf87bSMs+SFgvYOpCkJRNv13qMNAxKCC4iwbYvkiIMAF/eWFflgIVm1L9Lm0OIDHDTswzrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01afeef7ae68ee20030c73c2c0b145114dad0bf9a66cc5f40104ef01ea551c93","last_reissued_at":"2026-07-05T10:02:08.162793Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:08.162793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Models in Software Development Tasks: An Experimental Analysis of Energy and Accuracy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Boris Belchev, Fernando Castor, Negar Alizadeh, Nishant Saurabh, Patricia Kelbert","submitted_at":"2024-11-30T03:02:50Z","abstract_excerpt":"The use of generative AI-based coding assistants like ChatGPT and Github Copilot is a reality in contemporary software development. Many of these tools are provided as remote APIs. Using third-party APIs raises data privacy and security concerns for client companies, which motivates the use of locally-deployed language models. In this study, we explore the trade-off between model accuracy and energy consumption, aiming to provide valuable insights to help developers make informed decisions when selecting a language model. We investigate the performance of 18 families of LLMs in typical softwar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00329","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/2412.00329/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":"2412.00329","created_at":"2026-07-05T10:02:08.162857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00329v2","created_at":"2026-07-05T10:02:08.162857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00329","created_at":"2026-07-05T10:02:08.162857+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGX6555ONDXC","created_at":"2026-07-05T10:02:08.162857+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGX6555ONDXCAAYM","created_at":"2026-07-05T10:02:08.162857+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGX6555O","created_at":"2026-07-05T10:02:08.162857+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27205","citing_title":"Smaller Models, Unexpected Costs: Trade-offs in LLM Quantization for Automated Program Repair","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AGX6555ONDXCAAYMOPBMBMKFCF","json":"https://pith.science/pith/AGX6555ONDXCAAYMOPBMBMKFCF.json","graph_json":"https://pith.science/api/pith-number/AGX6555ONDXCAAYMOPBMBMKFCF/graph.json","events_json":"https://pith.science/api/pith-number/AGX6555ONDXCAAYMOPBMBMKFCF/events.json","paper":"https://pith.science/paper/AGX6555O"},"agent_actions":{"view_html":"https://pith.science/pith/AGX6555ONDXCAAYMOPBMBMKFCF","download_json":"https://pith.science/pith/AGX6555ONDXCAAYMOPBMBMKFCF.json","view_paper":"https://pith.science/paper/AGX6555O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00329&json=true","fetch_graph":"https://pith.science/api/pith-number/AGX6555ONDXCAAYMOPBMBMKFCF/graph.json","fetch_events":"https://pith.science/api/pith-number/AGX6555ONDXCAAYMOPBMBMKFCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGX6555ONDXCAAYMOPBMBMKFCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGX6555ONDXCAAYMOPBMBMKFCF/action/storage_attestation","attest_author":"https://pith.science/pith/AGX6555ONDXCAAYMOPBMBMKFCF/action/author_attestation","sign_citation":"https://pith.science/pith/AGX6555ONDXCAAYMOPBMBMKFCF/action/citation_signature","submit_replication":"https://pith.science/pith/AGX6555ONDXCAAYMOPBMBMKFCF/action/replication_record"}},"created_at":"2026-07-05T10:02:08.162857+00:00","updated_at":"2026-07-05T10:02:08.162857+00:00"}