{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:45WMKHROISHWRYP4LJWTK4ZFOX","short_pith_number":"pith:45WMKHRO","schema_version":"1.0","canonical_sha256":"e76cc51e2e448f68e1fc5a6d35732575f5271b942dc7f4365e3ebccb7ce4c761","source":{"kind":"arxiv","id":"2503.00691","version":2},"attestation_state":"computed","paper":{"title":"How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Dongha Lee, Heejae Chon, HwanJo Yu, Joonwon Jang, Seonghyeon Lee","submitted_at":"2025-03-02T02:04:58Z","abstract_excerpt":"Language models (LMs) have exhibited impressive abilities in generating code 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. There is a lack of studies focused on assessing the diversity of generated code, which overlooks its importance in code LMs. Therefore, we propose a systematic approach to evaluate code diversity, introducing various metrics with inter-code similarity. Specifically, we introduce code clustering methods that leverages LMs' capabilities in code u"},"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":"2503.00691","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-02T02:04:58Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e91fd7b07ed43de724a262c9a28bf15576d8abe7b5d0bb02f55d2c18e0edac5d","abstract_canon_sha256":"1477942313ee6b3b950db23e151dd79614f8804ddaf82a5285d7fe736611c8e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:15.426859Z","signature_b64":"epOAyCd0LyjreF+ZK23YRc6UexuOY/5RFpYMu1Jj9ApVPUeoF9XTB/y7eTHYaY67JOk3VKOv4fXjr4c/PjhdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e76cc51e2e448f68e1fc5a6d35732575f5271b942dc7f4365e3ebccb7ce4c761","last_reissued_at":"2026-07-05T10:26:15.426344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:15.426344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Code","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Dongha Lee, Heejae Chon, HwanJo Yu, Joonwon Jang, Seonghyeon Lee","submitted_at":"2025-03-02T02:04:58Z","abstract_excerpt":"Language models (LMs) have exhibited impressive abilities in generating code 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. There is a lack of studies focused on assessing the diversity of generated code, which overlooks its importance in code LMs. Therefore, we propose a systematic approach to evaluate code diversity, introducing various metrics with inter-code similarity. Specifically, we introduce code clustering methods that leverages LMs' capabilities in code u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00691","kind":"arxiv","version":2},"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/2503.00691/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":"2503.00691","created_at":"2026-07-05T10:26:15.426412+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00691v2","created_at":"2026-07-05T10:26:15.426412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00691","created_at":"2026-07-05T10:26:15.426412+00:00"},{"alias_kind":"pith_short_12","alias_value":"45WMKHROISHW","created_at":"2026-07-05T10:26:15.426412+00:00"},{"alias_kind":"pith_short_16","alias_value":"45WMKHROISHWRYP4","created_at":"2026-07-05T10:26:15.426412+00:00"},{"alias_kind":"pith_short_8","alias_value":"45WMKHRO","created_at":"2026-07-05T10:26:15.426412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14445","citing_title":"FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/45WMKHROISHWRYP4LJWTK4ZFOX","json":"https://pith.science/pith/45WMKHROISHWRYP4LJWTK4ZFOX.json","graph_json":"https://pith.science/api/pith-number/45WMKHROISHWRYP4LJWTK4ZFOX/graph.json","events_json":"https://pith.science/api/pith-number/45WMKHROISHWRYP4LJWTK4ZFOX/events.json","paper":"https://pith.science/paper/45WMKHRO"},"agent_actions":{"view_html":"https://pith.science/pith/45WMKHROISHWRYP4LJWTK4ZFOX","download_json":"https://pith.science/pith/45WMKHROISHWRYP4LJWTK4ZFOX.json","view_paper":"https://pith.science/paper/45WMKHRO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00691&json=true","fetch_graph":"https://pith.science/api/pith-number/45WMKHROISHWRYP4LJWTK4ZFOX/graph.json","fetch_events":"https://pith.science/api/pith-number/45WMKHROISHWRYP4LJWTK4ZFOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45WMKHROISHWRYP4LJWTK4ZFOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45WMKHROISHWRYP4LJWTK4ZFOX/action/storage_attestation","attest_author":"https://pith.science/pith/45WMKHROISHWRYP4LJWTK4ZFOX/action/author_attestation","sign_citation":"https://pith.science/pith/45WMKHROISHWRYP4LJWTK4ZFOX/action/citation_signature","submit_replication":"https://pith.science/pith/45WMKHROISHWRYP4LJWTK4ZFOX/action/replication_record"}},"created_at":"2026-07-05T10:26:15.426412+00:00","updated_at":"2026-07-05T10:26:15.426412+00:00"}