{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A4QWSBWXH37XVM66P2YT4JMH4V","short_pith_number":"pith:A4QWSBWX","schema_version":"1.0","canonical_sha256":"07216906d73eff7ab3de7eb13e2587e554e23a66224088f1c1540da7382a71b4","source":{"kind":"arxiv","id":"2408.14504","version":1},"attestation_state":"computed","paper":{"title":"Is Functional Correctness Enough to Evaluate Code Language Models? Exploring Diversity of Generated Codes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.SE","authors_text":"Dongha Lee, Heejae Chon, Jinyoung Yeo, Seonghyeon Lee","submitted_at":"2024-08-24T07:40:22Z","abstract_excerpt":"Language models (LMs) have exhibited impressive abilities in generating codes from natural language requirements. In this work, we highlight the diversity of code generated by LMs as a critical criterion for evaluating their code generation capabilities, in addition to functional correctness. Despite its practical implications, there is a lack of studies focused on assessing the diversity of generated code, which overlooks its importance in the development of code LMs. We propose a systematic approach to evaluate the diversity of generated code, utilizing various metrics for inter-code similar"},"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":"2408.14504","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-08-24T07:40:22Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"e61e2ea67933325c9d45eb0cd79c8e5355b9c7d3c32478306d72a4a53923bd67","abstract_canon_sha256":"f35eccf7bd73902a1fd3e29093a5776e1c4f28656a74804bb18da101551bb86f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:54.425584Z","signature_b64":"erv6AWN7Hi5FJ1jMGWOfOEt4o991oBbyWLEXvkeXowO3tcKQKSwLf4MQht49qyChyD4RqaD3dzZ1H8Ebxlp8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07216906d73eff7ab3de7eb13e2587e554e23a66224088f1c1540da7382a71b4","last_reissued_at":"2026-07-05T08:59:54.425149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:54.425149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Functional Correctness Enough to Evaluate Code Language Models? Exploring Diversity of Generated Codes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.SE","authors_text":"Dongha Lee, Heejae Chon, Jinyoung Yeo, Seonghyeon Lee","submitted_at":"2024-08-24T07:40:22Z","abstract_excerpt":"Language models (LMs) have exhibited impressive abilities in generating codes from natural language requirements. In this work, we highlight the diversity of code generated by LMs as a critical criterion for evaluating their code generation capabilities, in addition to functional correctness. Despite its practical implications, there is a lack of studies focused on assessing the diversity of generated code, which overlooks its importance in the development of code LMs. We propose a systematic approach to evaluate the diversity of generated code, utilizing various metrics for inter-code similar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14504","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/2408.14504/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":"2408.14504","created_at":"2026-07-05T08:59:54.425208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.14504v1","created_at":"2026-07-05T08:59:54.425208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14504","created_at":"2026-07-05T08:59:54.425208+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4QWSBWXH37X","created_at":"2026-07-05T08:59:54.425208+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4QWSBWXH37XVM66","created_at":"2026-07-05T08:59:54.425208+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4QWSBWX","created_at":"2026-07-05T08:59:54.425208+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07619","citing_title":"Rethinking Code Performance Benchmarks for LLMs","ref_index":95,"is_internal_anchor":true},{"citing_arxiv_id":"2606.13097","citing_title":"Functional Cache Grafting: Robust and Rapid Code-Policy Synthesis for Embodied Agents","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05267","citing_title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19965","citing_title":"Insights into Security-Related AI-Generated Pull Requests","ref_index":77,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A4QWSBWXH37XVM66P2YT4JMH4V","json":"https://pith.science/pith/A4QWSBWXH37XVM66P2YT4JMH4V.json","graph_json":"https://pith.science/api/pith-number/A4QWSBWXH37XVM66P2YT4JMH4V/graph.json","events_json":"https://pith.science/api/pith-number/A4QWSBWXH37XVM66P2YT4JMH4V/events.json","paper":"https://pith.science/paper/A4QWSBWX"},"agent_actions":{"view_html":"https://pith.science/pith/A4QWSBWXH37XVM66P2YT4JMH4V","download_json":"https://pith.science/pith/A4QWSBWXH37XVM66P2YT4JMH4V.json","view_paper":"https://pith.science/paper/A4QWSBWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.14504&json=true","fetch_graph":"https://pith.science/api/pith-number/A4QWSBWXH37XVM66P2YT4JMH4V/graph.json","fetch_events":"https://pith.science/api/pith-number/A4QWSBWXH37XVM66P2YT4JMH4V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4QWSBWXH37XVM66P2YT4JMH4V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4QWSBWXH37XVM66P2YT4JMH4V/action/storage_attestation","attest_author":"https://pith.science/pith/A4QWSBWXH37XVM66P2YT4JMH4V/action/author_attestation","sign_citation":"https://pith.science/pith/A4QWSBWXH37XVM66P2YT4JMH4V/action/citation_signature","submit_replication":"https://pith.science/pith/A4QWSBWXH37XVM66P2YT4JMH4V/action/replication_record"}},"created_at":"2026-07-05T08:59:54.425208+00:00","updated_at":"2026-07-05T08:59:54.425208+00:00"}