{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RWYVEK3Z47JUVYWEZWRPKA4RXA","short_pith_number":"pith:RWYVEK3Z","schema_version":"1.0","canonical_sha256":"8db1522b79e7d34ae2c4cda2f50391b81c43ca8bfd8e1bb0c4918cc3b047c5fd","source":{"kind":"arxiv","id":"2401.07339","version":2},"attestation_state":"computed","paper":{"title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ge Li, Jia Li, Kechi Zhang, Xianjie Shi, Zhi Jin","submitted_at":"2024-01-14T18:12:03Z","abstract_excerpt":"Large Language Models (LLMs) have shown promise in automated code generation but typically excel only in simpler tasks such as generating standalone code units. Real-world software development, however, often involves complex code repositories (named repo) with complex dependencies and extensive documentation. To fill this gap, our research pivots towards evaluating LLMs in a more realistic setting -- real-world repo-level code generation. We introduce CodeAgentBench, a manually curated benchmark for repo-level code generation. This benchmark comprises five high-quality Python projects, encomp"},"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":"2401.07339","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-01-14T18:12:03Z","cross_cats_sorted":[],"title_canon_sha256":"4f9b7e2d957214ee6d4b18f42587fd51589403b69d3771bf397076f3673d0645","abstract_canon_sha256":"70d569d44ac842e166367b533935f00587b92bffcbbd4238fe3dcef6abc1b1c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:38.755803Z","signature_b64":"GTNN66aV8/ITN9ApGcVHGDJLLXdLwDCRjRMcLfp71NqRnogoesDUx7WKVJR+dCVPxbMKkvIHg3KVN0lqSxApAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8db1522b79e7d34ae2c4cda2f50391b81c43ca8bfd8e1bb0c4918cc3b047c5fd","last_reissued_at":"2026-07-05T08:53:38.755413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:38.755413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ge Li, Jia Li, Kechi Zhang, Xianjie Shi, Zhi Jin","submitted_at":"2024-01-14T18:12:03Z","abstract_excerpt":"Large Language Models (LLMs) have shown promise in automated code generation but typically excel only in simpler tasks such as generating standalone code units. Real-world software development, however, often involves complex code repositories (named repo) with complex dependencies and extensive documentation. To fill this gap, our research pivots towards evaluating LLMs in a more realistic setting -- real-world repo-level code generation. We introduce CodeAgentBench, a manually curated benchmark for repo-level code generation. This benchmark comprises five high-quality Python projects, encomp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07339","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/2401.07339/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":"2401.07339","created_at":"2026-07-05T08:53:38.755469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.07339v2","created_at":"2026-07-05T08:53:38.755469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07339","created_at":"2026-07-05T08:53:38.755469+00:00"},{"alias_kind":"pith_short_12","alias_value":"RWYVEK3Z47JU","created_at":"2026-07-05T08:53:38.755469+00:00"},{"alias_kind":"pith_short_16","alias_value":"RWYVEK3Z47JUVYWE","created_at":"2026-07-05T08:53:38.755469+00:00"},{"alias_kind":"pith_short_8","alias_value":"RWYVEK3Z","created_at":"2026-07-05T08:53:38.755469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26935","citing_title":"Where Do CoT Training Gains Land in LLM based Agents?","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26918","citing_title":"Diagnosing Task Insensitivity in Language Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09641","citing_title":"MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00530","citing_title":"Sakura: An Approach for Generating Complex Tests from Natural Language Test Descriptions","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22154","citing_title":"IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2510.18586","citing_title":"TokenCake: A KV-Cache-centric Serving Framework for LLM-based Multi-Agent Applications","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2602.14211","citing_title":"SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17957","citing_title":"Contextualized Code Pretraining for Code Generation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2506.20911","citing_title":"FaSTA$^*$: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2601.00376","citing_title":"In Line with Context: Repository-Level Code Generation via Context Inlining","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16321","citing_title":"LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2402.19473","citing_title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","ref_index":227,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16335","citing_title":"Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2404.13501","citing_title":"A Survey on the Memory Mechanism of Large Language Model based Agents","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12913","citing_title":"Revisiting DAgger in the Era of LLM-Agents","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08112","citing_title":"Context-Augmented Code Generation: How Product Context Improves AI Coding Agent Decision Compliance by 49%","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22659","citing_title":"RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19606","citing_title":"AblateCell: A Reproduce-then-Ablate Agent for Virtual Cell Repositories","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12220","citing_title":"Learning Project-wise Subsequent Code Edits via Interleaving Neural-based Induction and Tool-based Deduction","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02195","citing_title":"Beyond Translation Accuracy: Addressing False Failures in LLM-Based Code Translation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15309","citing_title":"MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02195","citing_title":"Beyond Translation Accuracy: Addressing False Failures in LLM-Based Code Translation","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RWYVEK3Z47JUVYWEZWRPKA4RXA","json":"https://pith.science/pith/RWYVEK3Z47JUVYWEZWRPKA4RXA.json","graph_json":"https://pith.science/api/pith-number/RWYVEK3Z47JUVYWEZWRPKA4RXA/graph.json","events_json":"https://pith.science/api/pith-number/RWYVEK3Z47JUVYWEZWRPKA4RXA/events.json","paper":"https://pith.science/paper/RWYVEK3Z"},"agent_actions":{"view_html":"https://pith.science/pith/RWYVEK3Z47JUVYWEZWRPKA4RXA","download_json":"https://pith.science/pith/RWYVEK3Z47JUVYWEZWRPKA4RXA.json","view_paper":"https://pith.science/paper/RWYVEK3Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.07339&json=true","fetch_graph":"https://pith.science/api/pith-number/RWYVEK3Z47JUVYWEZWRPKA4RXA/graph.json","fetch_events":"https://pith.science/api/pith-number/RWYVEK3Z47JUVYWEZWRPKA4RXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RWYVEK3Z47JUVYWEZWRPKA4RXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RWYVEK3Z47JUVYWEZWRPKA4RXA/action/storage_attestation","attest_author":"https://pith.science/pith/RWYVEK3Z47JUVYWEZWRPKA4RXA/action/author_attestation","sign_citation":"https://pith.science/pith/RWYVEK3Z47JUVYWEZWRPKA4RXA/action/citation_signature","submit_replication":"https://pith.science/pith/RWYVEK3Z47JUVYWEZWRPKA4RXA/action/replication_record"}},"created_at":"2026-07-05T08:53:38.755469+00:00","updated_at":"2026-07-05T08:53:38.755469+00:00"}