{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UY7PUD3DTNGSRT3PBEILDB27HR","short_pith_number":"pith:UY7PUD3D","schema_version":"1.0","canonical_sha256":"a63efa0f639b4d28cf6f0910b1875f3c58cd7bebc4ac5a8c2832d86797dada6d","source":{"kind":"arxiv","id":"2402.14852","version":1},"attestation_state":"computed","paper":{"title":"HumanEval on Latest GPT Models -- 2024","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel Li, Lincoln Murr","submitted_at":"2024-02-20T04:17:21Z","abstract_excerpt":"In 2023, we are using the latest models of GPT-4 to advance program synthesis. The large language models have significantly improved the state-of-the-art for this purpose. To make these advancements more accessible, we have created a repository that connects these models to Huamn Eval. This dataset was initally developed to be used with a language model called CODEGEN on natural and programming language data. The utility of these trained models is showcased by demonstrating their competitive performance in zero-shot Python code generation on HumanEval tasks compared to previous state-of-the-ar"},"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":"2402.14852","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T04:17:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e613f3e34fbf0dd05d75bbeb5c7b6c09b9179ee9ec56159a4c6ee1177134e9ad","abstract_canon_sha256":"62abc09a04d2a334eb9db5669d330ef7d8434045424b39aed71f3f5b35708574"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:18.868531Z","signature_b64":"Vb+jkKWCywFukmVUPiqZeOju5MAO2p+lbgXVYpAa2pZhiSzmBc9YUrN5rJHVKCxkpkAn8tV8Xgqndt+Q/o/IBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a63efa0f639b4d28cf6f0910b1875f3c58cd7bebc4ac5a8c2832d86797dada6d","last_reissued_at":"2026-07-05T07:48:18.868045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:18.868045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HumanEval on Latest GPT Models -- 2024","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel Li, Lincoln Murr","submitted_at":"2024-02-20T04:17:21Z","abstract_excerpt":"In 2023, we are using the latest models of GPT-4 to advance program synthesis. The large language models have significantly improved the state-of-the-art for this purpose. To make these advancements more accessible, we have created a repository that connects these models to Huamn Eval. This dataset was initally developed to be used with a language model called CODEGEN on natural and programming language data. The utility of these trained models is showcased by demonstrating their competitive performance in zero-shot Python code generation on HumanEval tasks compared to previous state-of-the-ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14852","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/2402.14852/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":"2402.14852","created_at":"2026-07-05T07:48:18.868104+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14852v1","created_at":"2026-07-05T07:48:18.868104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14852","created_at":"2026-07-05T07:48:18.868104+00:00"},{"alias_kind":"pith_short_12","alias_value":"UY7PUD3DTNGS","created_at":"2026-07-05T07:48:18.868104+00:00"},{"alias_kind":"pith_short_16","alias_value":"UY7PUD3DTNGSRT3P","created_at":"2026-07-05T07:48:18.868104+00:00"},{"alias_kind":"pith_short_8","alias_value":"UY7PUD3D","created_at":"2026-07-05T07:48:18.868104+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18073","citing_title":"A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10332","citing_title":"From GPT-3 to GPT-5: Mapping their capabilities, scope, limitations, and consequences","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10449","citing_title":"AdverMCTS: Combating Pseudo-Correctness in Code Generation via Adversarial Monte Carlo Tree Search","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UY7PUD3DTNGSRT3PBEILDB27HR","json":"https://pith.science/pith/UY7PUD3DTNGSRT3PBEILDB27HR.json","graph_json":"https://pith.science/api/pith-number/UY7PUD3DTNGSRT3PBEILDB27HR/graph.json","events_json":"https://pith.science/api/pith-number/UY7PUD3DTNGSRT3PBEILDB27HR/events.json","paper":"https://pith.science/paper/UY7PUD3D"},"agent_actions":{"view_html":"https://pith.science/pith/UY7PUD3DTNGSRT3PBEILDB27HR","download_json":"https://pith.science/pith/UY7PUD3DTNGSRT3PBEILDB27HR.json","view_paper":"https://pith.science/paper/UY7PUD3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14852&json=true","fetch_graph":"https://pith.science/api/pith-number/UY7PUD3DTNGSRT3PBEILDB27HR/graph.json","fetch_events":"https://pith.science/api/pith-number/UY7PUD3DTNGSRT3PBEILDB27HR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UY7PUD3DTNGSRT3PBEILDB27HR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UY7PUD3DTNGSRT3PBEILDB27HR/action/storage_attestation","attest_author":"https://pith.science/pith/UY7PUD3DTNGSRT3PBEILDB27HR/action/author_attestation","sign_citation":"https://pith.science/pith/UY7PUD3DTNGSRT3PBEILDB27HR/action/citation_signature","submit_replication":"https://pith.science/pith/UY7PUD3DTNGSRT3PBEILDB27HR/action/replication_record"}},"created_at":"2026-07-05T07:48:18.868104+00:00","updated_at":"2026-07-05T07:48:18.868104+00:00"}