{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FAL4JNNFGADJ252EXPWX3ECZKQ","short_pith_number":"pith:FAL4JNNF","schema_version":"1.0","canonical_sha256":"2817c4b5a530069d7744bbed7d905954374e394adc098726acb9656241cd5447","source":{"kind":"arxiv","id":"2207.10397","version":2},"attestation_state":"computed","paper":{"title":"CodeT: Code Generation with Generated Tests","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CodeT generates test cases with the same model to select correct code samples via dual execution agreement.","cross_cats":["cs.AI","cs.PL","cs.SE"],"primary_cat":"cs.CL","authors_text":"Anh Nguyen, Bei Chen, Daoguang Zan, Fengji Zhang, Jian-Guang Lou, Weizhu Chen, Zeqi Lin","submitted_at":"2022-07-21T10:18:37Z","abstract_excerpt":"The task of generating code solutions for a given programming problem can benefit from the use of pre-trained language models such as Codex, which can produce multiple diverse samples. However, a major challenge for this task is to select the most appropriate solution from the multiple samples generated by the pre-trained language models. A natural way to evaluate the quality and correctness of a code solution is to run it against a set of test cases, but the manual creation of such test cases is often costly and time-consuming. In this paper, we propose a novel method, CodeT, that leverages t"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2207.10397","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-21T10:18:37Z","cross_cats_sorted":["cs.AI","cs.PL","cs.SE"],"title_canon_sha256":"9f454b5fd5666f3fd6b9b1f77c86081aef821f4aef5eae5e56439466fc5afe5f","abstract_canon_sha256":"18964b1cece2710bd0d5489f437f4f7246a382cc6eab0a23b0b624827c6804ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:49.699762Z","signature_b64":"NeEAjfKZoxQ3kYphp37Hfmn7BamgbFImalAkI5QblZoplH2SLQbJ+S9mfQkTFnETrodP/KPuNv21nYnLmNtkBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2817c4b5a530069d7744bbed7d905954374e394adc098726acb9656241cd5447","last_reissued_at":"2026-05-17T23:38:49.699265Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:49.699265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeT: Code Generation with Generated Tests","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CodeT generates test cases with the same model to select correct code samples via dual execution agreement.","cross_cats":["cs.AI","cs.PL","cs.SE"],"primary_cat":"cs.CL","authors_text":"Anh Nguyen, Bei Chen, Daoguang Zan, Fengji Zhang, Jian-Guang Lou, Weizhu Chen, Zeqi Lin","submitted_at":"2022-07-21T10:18:37Z","abstract_excerpt":"The task of generating code solutions for a given programming problem can benefit from the use of pre-trained language models such as Codex, which can produce multiple diverse samples. However, a major challenge for this task is to select the most appropriate solution from the multiple samples generated by the pre-trained language models. A natural way to evaluate the quality and correctness of a code solution is to run it against a set of test cases, but the manual creation of such test cases is often costly and time-consuming. In this paper, we propose a novel method, CodeT, that leverages t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"CodeT improves the pass@1 metric on HumanEval to 65.8%, an absolute improvement of 18.8% over the code-davinci-002 model and more than 20% over previous state-of-the-art results.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That agreement between independently generated code samples on independently generated tests reliably indicates functional correctness rather than shared bugs or test weaknesses.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CodeT improves code generation accuracy by using the same model to create test cases and then selecting solutions via output agreement on those tests, raising HumanEval pass@1 from 47% to 65.8%.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CodeT generates test cases with the same model to select correct code samples via dual execution agreement.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c0b39ab2ff4903c5967a93fb2485db4b52184e302c306e58cded605d5fbb8151"},"source":{"id":"2207.10397","kind":"arxiv","version":2},"verdict":{"id":"e21bdbb2-d0be-44ec-976c-a1954b6c04ea","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T23:51:28.385332Z","strongest_claim":"CodeT improves the pass@1 metric on HumanEval to 65.8%, an absolute improvement of 18.8% over the code-davinci-002 model and more than 20% over previous state-of-the-art results.","one_line_summary":"CodeT improves code generation accuracy by using the same model to create test cases and then selecting solutions via output agreement on those tests, raising HumanEval pass@1 from 47% to 65.8%.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That agreement between independently generated code samples on independently generated tests reliably indicates functional correctness rather than shared bugs or test weaknesses.","pith_extraction_headline":"CodeT generates test cases with the same model to select correct code samples via dual execution agreement."},"references":{"count":17,"sample":[{"doi":"","year":null,"title":"Program Synthesis with Large Language Models","work_id":"fd241a05-03b9-4de2-9588-9d77ce176125","ref_index":1,"cited_arxiv_id":"2108.07732","is_internal_anchor":true},{"doi":"","year":1901,"title":"Language models are few-shot learners","work_id":"f93ff324-f230-4a46-97b9-6b103c35585d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","ref_index":3,"cited_arxiv_id":"2107.03374","is_internal_anchor":true},{"doi":"","year":null,"title":"Training Verifiers to Solve Math Word Problems","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","ref_index":4,"cited_arxiv_id":"2110.14168","is_internal_anchor":true},{"doi":"","year":null,"title":"InCoder: A Generative Model for Code Infilling and Synthesis","work_id":"e98a5559-529d-48b1-833c-b85b662f190c","ref_index":5,"cited_arxiv_id":"2204.05999","is_internal_anchor":true}],"resolved_work":17,"snapshot_sha256":"0ae46256bda4d7fa4217c296ab130a7ddb6b28ef879e79fcf162e163703d5246","internal_anchors":6},"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":"2207.10397","created_at":"2026-05-17T23:38:49.699361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.10397v2","created_at":"2026-05-17T23:38:49.699361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10397","created_at":"2026-05-17T23:38:49.699361+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAL4JNNFGADJ","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAL4JNNFGADJ252E","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAL4JNNF","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":26,"sample":[{"citing_arxiv_id":"2402.01411","citing_title":"CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09730","citing_title":"RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17029","citing_title":"Task Abstention for Large Language Models in Code Generation","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15248","citing_title":"Probing Privacy Leaks in LLM-based Code Generation via Test Generation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2510.08804","citing_title":"MOSAIC: Multi-agent Orchestration for Task-Intelligent Scientific Coding","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2510.15494","citing_title":"Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2512.00127","citing_title":"Generating Verifiable Chain of Thoughts from Exection-Traces","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2512.18470","citing_title":"SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09730","citing_title":"RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2603.27098","citing_title":"Ensemble-Based Uncertainty Estimation for Code Correctness Estimation","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2603.28653","citing_title":"BACE: LLM-based Code Generation through Bayesian Anchored Co-Evolution of Code and Test Populations","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12201","citing_title":"Uncertainty Quantification for LLM-based Code Generation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03356","citing_title":"POSTCONDBENCH: Benchmarking Correctness and Completeness in Formal Postcondition Inference","ref_index":124,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24222","citing_title":"MEMCoder: Multi-dimensional Evolving Memory for Private-Library-Oriented Code Generation","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00628","citing_title":"EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19826","citing_title":"Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10449","citing_title":"AdverMCTS: Combating Pseudo-Correctness in Code Generation via Adversarial Monte Carlo Tree Search","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07248","citing_title":"PaT: Planning-after-Trial for Efficient Test-Time Code Generation","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06253","citing_title":"FLeX: Fourier-based Low-rank EXpansion for multilingual transfer","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2403.07974","citing_title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","ref_index":248,"is_internal_anchor":true},{"citing_arxiv_id":"2303.11366","citing_title":"Reflexion: Language Agents with Verbal Reinforcement Learning","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13559","citing_title":"WebMAC: A Multi-Agent Collaborative Framework for Scenario Testing of Web Systems","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16198","citing_title":"Bridging the Gap between User Intent and LLM: A Requirement Alignment Approach for Code Generation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17433","citing_title":"Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAL4JNNFGADJ252EXPWX3ECZKQ","json":"https://pith.science/pith/FAL4JNNFGADJ252EXPWX3ECZKQ.json","graph_json":"https://pith.science/api/pith-number/FAL4JNNFGADJ252EXPWX3ECZKQ/graph.json","events_json":"https://pith.science/api/pith-number/FAL4JNNFGADJ252EXPWX3ECZKQ/events.json","paper":"https://pith.science/paper/FAL4JNNF"},"agent_actions":{"view_html":"https://pith.science/pith/FAL4JNNFGADJ252EXPWX3ECZKQ","download_json":"https://pith.science/pith/FAL4JNNFGADJ252EXPWX3ECZKQ.json","view_paper":"https://pith.science/paper/FAL4JNNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.10397&json=true","fetch_graph":"https://pith.science/api/pith-number/FAL4JNNFGADJ252EXPWX3ECZKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/FAL4JNNFGADJ252EXPWX3ECZKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAL4JNNFGADJ252EXPWX3ECZKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAL4JNNFGADJ252EXPWX3ECZKQ/action/storage_attestation","attest_author":"https://pith.science/pith/FAL4JNNFGADJ252EXPWX3ECZKQ/action/author_attestation","sign_citation":"https://pith.science/pith/FAL4JNNFGADJ252EXPWX3ECZKQ/action/citation_signature","submit_replication":"https://pith.science/pith/FAL4JNNFGADJ252EXPWX3ECZKQ/action/replication_record"}},"created_at":"2026-05-17T23:38:49.699361+00:00","updated_at":"2026-05-17T23:38:49.699361+00:00"}