{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EISSCDW5CBQ3OMV36X4LGPPOMH","short_pith_number":"pith:EISSCDW5","schema_version":"1.0","canonical_sha256":"2225210edd1061b732bbf5f8b33dee61d5ae465e9a0a6a8df79e81bf1152c3d1","source":{"kind":"arxiv","id":"2503.06680","version":2},"attestation_state":"computed","paper":{"title":"FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Guangyue Peng, Houfeng Wang, Scarlett Li, Shaoguang Mao, Wei Li, Wen Luo, Xin Zhang, Yangyu Huang, Zhongxin Guo","submitted_at":"2025-03-09T16:11:57Z","abstract_excerpt":"Implementing new features in repository-level codebases is a crucial application of code generation models. However, current benchmarks lack a dedicated evaluation framework for this capability. To fill this gap, we introduce FEA-Bench, a benchmark designed to assess the ability of large language models (LLMs) to perform incremental development within code repositories. We collect pull requests from 83 GitHub repositories and use rule-based and intent-based filtering to construct task instances focused on new feature development. Each task instance containing code changes is paired with releva"},"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":"2503.06680","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-09T16:11:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bc608de75b466d137e5c76b62428217cfbb5526425a0bfe0ba5f98c97fb37d05","abstract_canon_sha256":"5b0a2408325de7115a5a99af9636fc48c844255dbe0937a7d946b73ff5080779"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:15.984413Z","signature_b64":"C1frZBSf4lRbqNJTv3b4l6PQhUwcbeBxq02cQfMLcytBfHdlk3vPzCrGe5kiynHrX8nUH2UpbXPwwUEjVPNuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2225210edd1061b732bbf5f8b33dee61d5ae465e9a0a6a8df79e81bf1152c3d1","last_reissued_at":"2026-07-05T11:24:15.983873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:15.983873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Guangyue Peng, Houfeng Wang, Scarlett Li, Shaoguang Mao, Wei Li, Wen Luo, Xin Zhang, Yangyu Huang, Zhongxin Guo","submitted_at":"2025-03-09T16:11:57Z","abstract_excerpt":"Implementing new features in repository-level codebases is a crucial application of code generation models. However, current benchmarks lack a dedicated evaluation framework for this capability. To fill this gap, we introduce FEA-Bench, a benchmark designed to assess the ability of large language models (LLMs) to perform incremental development within code repositories. We collect pull requests from 83 GitHub repositories and use rule-based and intent-based filtering to construct task instances focused on new feature development. Each task instance containing code changes is paired with releva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06680","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/2503.06680/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":"2503.06680","created_at":"2026-07-05T11:24:15.983940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06680v2","created_at":"2026-07-05T11:24:15.983940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06680","created_at":"2026-07-05T11:24:15.983940+00:00"},{"alias_kind":"pith_short_12","alias_value":"EISSCDW5CBQ3","created_at":"2026-07-05T11:24:15.983940+00:00"},{"alias_kind":"pith_short_16","alias_value":"EISSCDW5CBQ3OMV3","created_at":"2026-07-05T11:24:15.983940+00:00"},{"alias_kind":"pith_short_8","alias_value":"EISSCDW5","created_at":"2026-07-05T11:24:15.983940+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19741","citing_title":"CityRAG: Stepping Into a City via Spatially-Grounded Video Generation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18293","citing_title":"Vibe Coding Ate My Homework: An evaluation of AI approaches to greenfield software engineering and programming","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18293","citing_title":"Vibe Coding Ate My Homework: An evaluation of AI approaches to greenfield software engineering and programming","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27492","citing_title":"Benchmarks are Not Enough: RAMP for Runtime Assessing of Agentic Models in Production Systems","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20374","citing_title":"CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03622","citing_title":"Toward Executable Repository-Level Code Generation via Environment Alignment","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19742","citing_title":"PlayCoder: Making LLM-Generated GUI Code Playable","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EISSCDW5CBQ3OMV36X4LGPPOMH","json":"https://pith.science/pith/EISSCDW5CBQ3OMV36X4LGPPOMH.json","graph_json":"https://pith.science/api/pith-number/EISSCDW5CBQ3OMV36X4LGPPOMH/graph.json","events_json":"https://pith.science/api/pith-number/EISSCDW5CBQ3OMV36X4LGPPOMH/events.json","paper":"https://pith.science/paper/EISSCDW5"},"agent_actions":{"view_html":"https://pith.science/pith/EISSCDW5CBQ3OMV36X4LGPPOMH","download_json":"https://pith.science/pith/EISSCDW5CBQ3OMV36X4LGPPOMH.json","view_paper":"https://pith.science/paper/EISSCDW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06680&json=true","fetch_graph":"https://pith.science/api/pith-number/EISSCDW5CBQ3OMV36X4LGPPOMH/graph.json","fetch_events":"https://pith.science/api/pith-number/EISSCDW5CBQ3OMV36X4LGPPOMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EISSCDW5CBQ3OMV36X4LGPPOMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EISSCDW5CBQ3OMV36X4LGPPOMH/action/storage_attestation","attest_author":"https://pith.science/pith/EISSCDW5CBQ3OMV36X4LGPPOMH/action/author_attestation","sign_citation":"https://pith.science/pith/EISSCDW5CBQ3OMV36X4LGPPOMH/action/citation_signature","submit_replication":"https://pith.science/pith/EISSCDW5CBQ3OMV36X4LGPPOMH/action/replication_record"}},"created_at":"2026-07-05T11:24:15.983940+00:00","updated_at":"2026-07-05T11:24:15.983940+00:00"}