{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SLP3SD4PWRZL26FNRFB6UMM2FC","short_pith_number":"pith:SLP3SD4P","schema_version":"1.0","canonical_sha256":"92dfb90f8fb472bd78ad8943ea319a28a7b7136f42cea8ac967a335819029e98","source":{"kind":"arxiv","id":"2305.00909","version":4},"attestation_state":"computed","paper":{"title":"Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.PL","authors_text":"Ajay Kumar Jaiswal, Dejia Xu, Kevin Wang, S P Sharan, Wenqing Zheng, Yihan Xi, Zhangyang Wang","submitted_at":"2023-04-28T01:47:09Z","abstract_excerpt":"For a complicated algorithm, its implementation by a human programmer usually starts with outlining a rough control flow followed by iterative enrichments, eventually yielding carefully generated syntactic structures and variables in a hierarchy. However, state-of-the-art large language models generate codes in a single pass, without intermediate warm-ups to reflect the structured thought process of \"outline-then-detail\". Inspired by the recent success of chain-of-thought prompting, we propose ChainCoder, a program synthesis language model that generates Python code progressively, i.e. from co"},"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":"2305.00909","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PL","submitted_at":"2023-04-28T01:47:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3dbcbf01b545d9b8a04b862c037815cda7450eb268718ba28a9a84f0cc78ebf6","abstract_canon_sha256":"72527234e9f233386c96136f1b976bb4a1542ea08e42f25de758899dcb036521"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:32:38.810325Z","signature_b64":"Ak+poISlo60adLBvbQeH8d6WpsOA6G6b4OjORr52R55+r/FSp31pyGVBM9GNT0zL81EAvdGp7uAgfQr9CXnfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92dfb90f8fb472bd78ad8943ea319a28a7b7136f42cea8ac967a335819029e98","last_reissued_at":"2026-07-05T06:32:38.809837Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:32:38.809837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.PL","authors_text":"Ajay Kumar Jaiswal, Dejia Xu, Kevin Wang, S P Sharan, Wenqing Zheng, Yihan Xi, Zhangyang Wang","submitted_at":"2023-04-28T01:47:09Z","abstract_excerpt":"For a complicated algorithm, its implementation by a human programmer usually starts with outlining a rough control flow followed by iterative enrichments, eventually yielding carefully generated syntactic structures and variables in a hierarchy. However, state-of-the-art large language models generate codes in a single pass, without intermediate warm-ups to reflect the structured thought process of \"outline-then-detail\". Inspired by the recent success of chain-of-thought prompting, we propose ChainCoder, a program synthesis language model that generates Python code progressively, i.e. from co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.00909","kind":"arxiv","version":4},"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/2305.00909/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":"2305.00909","created_at":"2026-07-05T06:32:38.809912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.00909v4","created_at":"2026-07-05T06:32:38.809912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.00909","created_at":"2026-07-05T06:32:38.809912+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLP3SD4PWRZL","created_at":"2026-07-05T06:32:38.809912+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLP3SD4PWRZL26FN","created_at":"2026-07-05T06:32:38.809912+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLP3SD4P","created_at":"2026-07-05T06:32:38.809912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05150","citing_title":"CodeSCM: Causal Analysis for Multi-Modal Code Generation","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SLP3SD4PWRZL26FNRFB6UMM2FC","json":"https://pith.science/pith/SLP3SD4PWRZL26FNRFB6UMM2FC.json","graph_json":"https://pith.science/api/pith-number/SLP3SD4PWRZL26FNRFB6UMM2FC/graph.json","events_json":"https://pith.science/api/pith-number/SLP3SD4PWRZL26FNRFB6UMM2FC/events.json","paper":"https://pith.science/paper/SLP3SD4P"},"agent_actions":{"view_html":"https://pith.science/pith/SLP3SD4PWRZL26FNRFB6UMM2FC","download_json":"https://pith.science/pith/SLP3SD4PWRZL26FNRFB6UMM2FC.json","view_paper":"https://pith.science/paper/SLP3SD4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.00909&json=true","fetch_graph":"https://pith.science/api/pith-number/SLP3SD4PWRZL26FNRFB6UMM2FC/graph.json","fetch_events":"https://pith.science/api/pith-number/SLP3SD4PWRZL26FNRFB6UMM2FC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLP3SD4PWRZL26FNRFB6UMM2FC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLP3SD4PWRZL26FNRFB6UMM2FC/action/storage_attestation","attest_author":"https://pith.science/pith/SLP3SD4PWRZL26FNRFB6UMM2FC/action/author_attestation","sign_citation":"https://pith.science/pith/SLP3SD4PWRZL26FNRFB6UMM2FC/action/citation_signature","submit_replication":"https://pith.science/pith/SLP3SD4PWRZL26FNRFB6UMM2FC/action/replication_record"}},"created_at":"2026-07-05T06:32:38.809912+00:00","updated_at":"2026-07-05T06:32:38.809912+00:00"}