{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:POPNEWBUA7NYAJ52LNLCFMMCSU","short_pith_number":"pith:POPNEWBU","schema_version":"1.0","canonical_sha256":"7b9ed2583407db8027ba5b5622b182953774036f2736d7ebb2d2726c68aad447","source":{"kind":"arxiv","id":"2310.17680","version":3},"attestation_state":"computed","paper":{"title":"CodeFusion: A Pre-trained Diffusion Model for Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.PL"],"primary_cat":"cs.SE","authors_text":"Carina Negreanu, Gust Verbruggen, Jos\\'e Cambronero, Mukul Singh, Sumit Gulwani, Vu Le","submitted_at":"2023-10-26T11:06:15Z","abstract_excerpt":"Imagine a developer who can only change their last line of code, how often would they have to start writing a function from scratch before it is correct? Auto-regressive models for code generation from natural language have a similar limitation: they do not easily allow reconsidering earlier tokens generated. We introduce CodeFusion, a pre-trained diffusion code generation model that addresses this limitation by iteratively denoising a complete program conditioned on the encoded natural language. We evaluate CodeFusion on the task of natural language to code generation for Bash, Python, and Mi"},"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":"2310.17680","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-10-26T11:06:15Z","cross_cats_sorted":["cs.AI","cs.CL","cs.PL"],"title_canon_sha256":"68c094330eddca45c0ffdef9068b179828239b74da905f5932515bf0f520b58f","abstract_canon_sha256":"a7a3f24e0b73d5d0fa12fd8b667692417bfbac0f7d6c493de34079f500310cb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:55.859785Z","signature_b64":"fw1IEED+dSyRoO7HxHcMw9Ml97GpjL2YQeu2lskxlxWOzSAHdPMOykpF31cy4u6HmbgxEM9GduGr78cLp9I5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b9ed2583407db8027ba5b5622b182953774036f2736d7ebb2d2726c68aad447","last_reissued_at":"2026-07-05T07:07:55.859200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:55.859200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeFusion: A Pre-trained Diffusion Model for Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.PL"],"primary_cat":"cs.SE","authors_text":"Carina Negreanu, Gust Verbruggen, Jos\\'e Cambronero, Mukul Singh, Sumit Gulwani, Vu Le","submitted_at":"2023-10-26T11:06:15Z","abstract_excerpt":"Imagine a developer who can only change their last line of code, how often would they have to start writing a function from scratch before it is correct? Auto-regressive models for code generation from natural language have a similar limitation: they do not easily allow reconsidering earlier tokens generated. We introduce CodeFusion, a pre-trained diffusion code generation model that addresses this limitation by iteratively denoising a complete program conditioned on the encoded natural language. We evaluate CodeFusion on the task of natural language to code generation for Bash, Python, and Mi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17680","kind":"arxiv","version":3},"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/2310.17680/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":"2310.17680","created_at":"2026-07-05T07:07:55.859265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17680v3","created_at":"2026-07-05T07:07:55.859265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17680","created_at":"2026-07-05T07:07:55.859265+00:00"},{"alias_kind":"pith_short_12","alias_value":"POPNEWBUA7NY","created_at":"2026-07-05T07:07:55.859265+00:00"},{"alias_kind":"pith_short_16","alias_value":"POPNEWBUA7NYAJ52","created_at":"2026-07-05T07:07:55.859265+00:00"},{"alias_kind":"pith_short_8","alias_value":"POPNEWBU","created_at":"2026-07-05T07:07:55.859265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":246,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POPNEWBUA7NYAJ52LNLCFMMCSU","json":"https://pith.science/pith/POPNEWBUA7NYAJ52LNLCFMMCSU.json","graph_json":"https://pith.science/api/pith-number/POPNEWBUA7NYAJ52LNLCFMMCSU/graph.json","events_json":"https://pith.science/api/pith-number/POPNEWBUA7NYAJ52LNLCFMMCSU/events.json","paper":"https://pith.science/paper/POPNEWBU"},"agent_actions":{"view_html":"https://pith.science/pith/POPNEWBUA7NYAJ52LNLCFMMCSU","download_json":"https://pith.science/pith/POPNEWBUA7NYAJ52LNLCFMMCSU.json","view_paper":"https://pith.science/paper/POPNEWBU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17680&json=true","fetch_graph":"https://pith.science/api/pith-number/POPNEWBUA7NYAJ52LNLCFMMCSU/graph.json","fetch_events":"https://pith.science/api/pith-number/POPNEWBUA7NYAJ52LNLCFMMCSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POPNEWBUA7NYAJ52LNLCFMMCSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POPNEWBUA7NYAJ52LNLCFMMCSU/action/storage_attestation","attest_author":"https://pith.science/pith/POPNEWBUA7NYAJ52LNLCFMMCSU/action/author_attestation","sign_citation":"https://pith.science/pith/POPNEWBUA7NYAJ52LNLCFMMCSU/action/citation_signature","submit_replication":"https://pith.science/pith/POPNEWBUA7NYAJ52LNLCFMMCSU/action/replication_record"}},"created_at":"2026-07-05T07:07:55.859265+00:00","updated_at":"2026-07-05T07:07:55.859265+00:00"}