{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M4POQYTBNALD6ZH6UYHFXM3PBM","short_pith_number":"pith:M4POQYTB","schema_version":"1.0","canonical_sha256":"671ee8626168163f64fea60e5bb36f0b133374c147e4c0647876a3725ebe5e1f","source":{"kind":"arxiv","id":"2407.14118","version":1},"attestation_state":"computed","paper":{"title":"Beyond Code Generation: Assessing Code LLM Maturity with Postconditions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Fusen He, Juan Zhai, Minxue Pan","submitted_at":"2024-07-19T08:34:30Z","abstract_excerpt":"Most existing code Large Language Model (LLM) benchmarks, e.g., EvalPlus, focus on the code generation tasks. Namely, they contain a natural language description of a problem and ask the LLM to write code to solve the problem. We argue that they do not capture all capabilities needed to assess the quality of a code LLM. In this paper, we propose a code LLM maturity model, based on the postcondition generation problem, to access a more complete set of code LLM capabilities. We choose the postcondition generation problem as it requires the code LLM to understand the code including semantics, nat"},"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":"2407.14118","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-07-19T08:34:30Z","cross_cats_sorted":[],"title_canon_sha256":"14540327d4ccacc50e1db970d233756bb011c41ab4d2bffab8814408c5f1f5f2","abstract_canon_sha256":"065c81e9641dfb5712d9cd19edcfca75228fb5354a5e50a944dfe6fd28c8184a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:58.671705Z","signature_b64":"3lcJlM/IwLx1JDoT59Hui7KdqNO7wcyXUqnqm2RBhuvuGmdlE76XpBHO8ec1sWOPxGprV4JZpJq4XcAm/9a9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"671ee8626168163f64fea60e5bb36f0b133374c147e4c0647876a3725ebe5e1f","last_reissued_at":"2026-07-05T08:45:58.671063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:58.671063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Code Generation: Assessing Code LLM Maturity with Postconditions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Fusen He, Juan Zhai, Minxue Pan","submitted_at":"2024-07-19T08:34:30Z","abstract_excerpt":"Most existing code Large Language Model (LLM) benchmarks, e.g., EvalPlus, focus on the code generation tasks. Namely, they contain a natural language description of a problem and ask the LLM to write code to solve the problem. We argue that they do not capture all capabilities needed to assess the quality of a code LLM. In this paper, we propose a code LLM maturity model, based on the postcondition generation problem, to access a more complete set of code LLM capabilities. We choose the postcondition generation problem as it requires the code LLM to understand the code including semantics, nat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14118","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/2407.14118/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":"2407.14118","created_at":"2026-07-05T08:45:58.671205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14118v1","created_at":"2026-07-05T08:45:58.671205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14118","created_at":"2026-07-05T08:45:58.671205+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4POQYTBNALD","created_at":"2026-07-05T08:45:58.671205+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4POQYTBNALD6ZH6","created_at":"2026-07-05T08:45:58.671205+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4POQYTB","created_at":"2026-07-05T08:45:58.671205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.16771","citing_title":"EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03245","citing_title":"FVRuleLearner: Operator-Level Reasoning Tree (Op-Tree)-Based Rules Learning for Formal Verification","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M4POQYTBNALD6ZH6UYHFXM3PBM","json":"https://pith.science/pith/M4POQYTBNALD6ZH6UYHFXM3PBM.json","graph_json":"https://pith.science/api/pith-number/M4POQYTBNALD6ZH6UYHFXM3PBM/graph.json","events_json":"https://pith.science/api/pith-number/M4POQYTBNALD6ZH6UYHFXM3PBM/events.json","paper":"https://pith.science/paper/M4POQYTB"},"agent_actions":{"view_html":"https://pith.science/pith/M4POQYTBNALD6ZH6UYHFXM3PBM","download_json":"https://pith.science/pith/M4POQYTBNALD6ZH6UYHFXM3PBM.json","view_paper":"https://pith.science/paper/M4POQYTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14118&json=true","fetch_graph":"https://pith.science/api/pith-number/M4POQYTBNALD6ZH6UYHFXM3PBM/graph.json","fetch_events":"https://pith.science/api/pith-number/M4POQYTBNALD6ZH6UYHFXM3PBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4POQYTBNALD6ZH6UYHFXM3PBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4POQYTBNALD6ZH6UYHFXM3PBM/action/storage_attestation","attest_author":"https://pith.science/pith/M4POQYTBNALD6ZH6UYHFXM3PBM/action/author_attestation","sign_citation":"https://pith.science/pith/M4POQYTBNALD6ZH6UYHFXM3PBM/action/citation_signature","submit_replication":"https://pith.science/pith/M4POQYTBNALD6ZH6UYHFXM3PBM/action/replication_record"}},"created_at":"2026-07-05T08:45:58.671205+00:00","updated_at":"2026-07-05T08:45:58.671205+00:00"}