{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5TPXTKBXGVNVGITANMYTEWQXYX","short_pith_number":"pith:5TPXTKBX","schema_version":"1.0","canonical_sha256":"ecdf79a837355b5322606b31325a17c5ee1389377740c436059f504964a9f74c","source":{"kind":"arxiv","id":"2309.16120","version":3},"attestation_state":"computed","paper":{"title":"Fixing Large Language Models' Specification Misunderstanding for Better Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Junjie Chen, Xiangyu Zhang, Zhao Tian","submitted_at":"2023-09-28T02:58:07Z","abstract_excerpt":"Code generation is to automatically generate source code conforming to a given programming specification, which has received extensive attention especially with the development of large language models (LLMs). Due to the inherent difficulty of code generation, the code generated by LLMs may not be aligned with the specification. Although thought-eliciting prompting techniques have been proposed to enhance the code generation performance of LLMs, producing correct understanding for complicated programming problems remains challenging, resulting in unsatisfactory performance. Also, some feedback"},"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":"2309.16120","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-09-28T02:58:07Z","cross_cats_sorted":[],"title_canon_sha256":"e0e63050da4c4a6a9ad9eb6cd1fc4e94c6d3697776dfd83827a9992d52b70537","abstract_canon_sha256":"8e097133a83a41f644cf17d6f0e95bd0ce3ea432561551535f68b94416e0b7de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:29.069863Z","signature_b64":"3PzzyxFizaB2f5iDUG/DfwIJEFlAnLGk7x8Jb6eGX+TxGUu15j6PtbWQM5fPh71D44yVFF7D4PYFzw2wuhUJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecdf79a837355b5322606b31325a17c5ee1389377740c436059f504964a9f74c","last_reissued_at":"2026-07-05T09:51:29.069458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:29.069458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fixing Large Language Models' Specification Misunderstanding for Better Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Junjie Chen, Xiangyu Zhang, Zhao Tian","submitted_at":"2023-09-28T02:58:07Z","abstract_excerpt":"Code generation is to automatically generate source code conforming to a given programming specification, which has received extensive attention especially with the development of large language models (LLMs). Due to the inherent difficulty of code generation, the code generated by LLMs may not be aligned with the specification. Although thought-eliciting prompting techniques have been proposed to enhance the code generation performance of LLMs, producing correct understanding for complicated programming problems remains challenging, resulting in unsatisfactory performance. Also, some feedback"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16120","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/2309.16120/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":"2309.16120","created_at":"2026-07-05T09:51:29.069513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.16120v3","created_at":"2026-07-05T09:51:29.069513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16120","created_at":"2026-07-05T09:51:29.069513+00:00"},{"alias_kind":"pith_short_12","alias_value":"5TPXTKBXGVNV","created_at":"2026-07-05T09:51:29.069513+00:00"},{"alias_kind":"pith_short_16","alias_value":"5TPXTKBXGVNVGITA","created_at":"2026-07-05T09:51:29.069513+00:00"},{"alias_kind":"pith_short_8","alias_value":"5TPXTKBX","created_at":"2026-07-05T09:51:29.069513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00511","citing_title":"Large Language Models for Multi-Lingual Equivalent Mutant Detection: An Extended Empirical Study","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2503.13549","citing_title":"A Showdown of ChatGPT vs DeepSeek in Solving Programming Tasks","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08980","citing_title":"AdaDec: A Uncertainty-Guided Lookahead Decoding Framework for LLM-Based Code Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2512.00380","citing_title":"Knowledge-Graph-Driven Data Synthesis for Low-Resource Software Development: A HarmonyOS Case Study","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2401.03065","citing_title":"CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2403.07974","citing_title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5TPXTKBXGVNVGITANMYTEWQXYX","json":"https://pith.science/pith/5TPXTKBXGVNVGITANMYTEWQXYX.json","graph_json":"https://pith.science/api/pith-number/5TPXTKBXGVNVGITANMYTEWQXYX/graph.json","events_json":"https://pith.science/api/pith-number/5TPXTKBXGVNVGITANMYTEWQXYX/events.json","paper":"https://pith.science/paper/5TPXTKBX"},"agent_actions":{"view_html":"https://pith.science/pith/5TPXTKBXGVNVGITANMYTEWQXYX","download_json":"https://pith.science/pith/5TPXTKBXGVNVGITANMYTEWQXYX.json","view_paper":"https://pith.science/paper/5TPXTKBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.16120&json=true","fetch_graph":"https://pith.science/api/pith-number/5TPXTKBXGVNVGITANMYTEWQXYX/graph.json","fetch_events":"https://pith.science/api/pith-number/5TPXTKBXGVNVGITANMYTEWQXYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5TPXTKBXGVNVGITANMYTEWQXYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5TPXTKBXGVNVGITANMYTEWQXYX/action/storage_attestation","attest_author":"https://pith.science/pith/5TPXTKBXGVNVGITANMYTEWQXYX/action/author_attestation","sign_citation":"https://pith.science/pith/5TPXTKBXGVNVGITANMYTEWQXYX/action/citation_signature","submit_replication":"https://pith.science/pith/5TPXTKBXGVNVGITANMYTEWQXYX/action/replication_record"}},"created_at":"2026-07-05T09:51:29.069513+00:00","updated_at":"2026-07-05T09:51:29.069513+00:00"}