{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PTDAMWO7NKUHV7QTA2ZGMPFUAX","short_pith_number":"pith:PTDAMWO7","schema_version":"1.0","canonical_sha256":"7cc60659df6aa87afe1306b2663cb405dcbfc20f31b1e719c4b7031b3868db66","source":{"kind":"arxiv","id":"2303.05378","version":1},"attestation_state":"computed","paper":{"title":"Greener yet Powerful: Taming Large Code Generation Models with Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Baishakhi Ray, Ben Athiwaratkun, Bing Xiang, Haifeng Qian, Mingyue Shang, Murali Krishna Ramanathan, Parminder Bhatia, Qing Sun, Shiqi Wang, Sujan Gonugondla, Varun Kumar, Wasi Ahmad, Xiaokai Wei, Xiaopeng Li, Yuchen Tian, Zijian Wang","submitted_at":"2023-03-09T16:25:51Z","abstract_excerpt":"ML-powered code generation aims to assist developers to write code in a more productive manner, by intelligently generating code blocks based on natural language prompts. Recently, large pretrained deep learning models have substantially pushed the boundary of code generation and achieved impressive performance. Despite their great power, the huge number of model parameters poses a significant threat to adapting them in a regular software development environment, where a developer might use a standard laptop or mid-size server to develop her code. Such large models incur significant resource u"},"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":"2303.05378","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-09T16:25:51Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"f8b80eb663e18e7765ae8cb8e7631e962ad2b014d552118fdca65e7719697f37","abstract_canon_sha256":"05b3ab48332b42aababee112a03e83a0118cfd197b95db4dc3a01ee312adfffd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:40.115301Z","signature_b64":"3hTtriS9WqULpgzEZnsUfUl4ao3lkT2QqpiSxruyGssDFaszE9v4hdz6vmNFqecRGjERPfIQ6rUVzvp5Oc1ODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cc60659df6aa87afe1306b2663cb405dcbfc20f31b1e719c4b7031b3868db66","last_reissued_at":"2026-07-05T05:49:40.114851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:40.114851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Greener yet Powerful: Taming Large Code Generation Models with Quantization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Baishakhi Ray, Ben Athiwaratkun, Bing Xiang, Haifeng Qian, Mingyue Shang, Murali Krishna Ramanathan, Parminder Bhatia, Qing Sun, Shiqi Wang, Sujan Gonugondla, Varun Kumar, Wasi Ahmad, Xiaokai Wei, Xiaopeng Li, Yuchen Tian, Zijian Wang","submitted_at":"2023-03-09T16:25:51Z","abstract_excerpt":"ML-powered code generation aims to assist developers to write code in a more productive manner, by intelligently generating code blocks based on natural language prompts. Recently, large pretrained deep learning models have substantially pushed the boundary of code generation and achieved impressive performance. Despite their great power, the huge number of model parameters poses a significant threat to adapting them in a regular software development environment, where a developer might use a standard laptop or mid-size server to develop her code. Such large models incur significant resource u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05378","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/2303.05378/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":"2303.05378","created_at":"2026-07-05T05:49:40.114912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.05378v1","created_at":"2026-07-05T05:49:40.114912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05378","created_at":"2026-07-05T05:49:40.114912+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTDAMWO7NKUH","created_at":"2026-07-05T05:49:40.114912+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTDAMWO7NKUHV7QT","created_at":"2026-07-05T05:49:40.114912+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTDAMWO7","created_at":"2026-07-05T05:49:40.114912+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/PTDAMWO7NKUHV7QTA2ZGMPFUAX","json":"https://pith.science/pith/PTDAMWO7NKUHV7QTA2ZGMPFUAX.json","graph_json":"https://pith.science/api/pith-number/PTDAMWO7NKUHV7QTA2ZGMPFUAX/graph.json","events_json":"https://pith.science/api/pith-number/PTDAMWO7NKUHV7QTA2ZGMPFUAX/events.json","paper":"https://pith.science/paper/PTDAMWO7"},"agent_actions":{"view_html":"https://pith.science/pith/PTDAMWO7NKUHV7QTA2ZGMPFUAX","download_json":"https://pith.science/pith/PTDAMWO7NKUHV7QTA2ZGMPFUAX.json","view_paper":"https://pith.science/paper/PTDAMWO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.05378&json=true","fetch_graph":"https://pith.science/api/pith-number/PTDAMWO7NKUHV7QTA2ZGMPFUAX/graph.json","fetch_events":"https://pith.science/api/pith-number/PTDAMWO7NKUHV7QTA2ZGMPFUAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTDAMWO7NKUHV7QTA2ZGMPFUAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTDAMWO7NKUHV7QTA2ZGMPFUAX/action/storage_attestation","attest_author":"https://pith.science/pith/PTDAMWO7NKUHV7QTA2ZGMPFUAX/action/author_attestation","sign_citation":"https://pith.science/pith/PTDAMWO7NKUHV7QTA2ZGMPFUAX/action/citation_signature","submit_replication":"https://pith.science/pith/PTDAMWO7NKUHV7QTA2ZGMPFUAX/action/replication_record"}},"created_at":"2026-07-05T05:49:40.114912+00:00","updated_at":"2026-07-05T05:49:40.114912+00:00"}