{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RWYVEK3Z47JUVYWEZWRPKA4RXA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"70d569d44ac842e166367b533935f00587b92bffcbbd4238fe3dcef6abc1b1c9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-01-14T18:12:03Z","title_canon_sha256":"4f9b7e2d957214ee6d4b18f42587fd51589403b69d3771bf397076f3673d0645"},"schema_version":"1.0","source":{"id":"2401.07339","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.07339","created_at":"2026-07-05T08:53:38Z"},{"alias_kind":"arxiv_version","alias_value":"2401.07339v2","created_at":"2026-07-05T08:53:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07339","created_at":"2026-07-05T08:53:38Z"},{"alias_kind":"pith_short_12","alias_value":"RWYVEK3Z47JU","created_at":"2026-07-05T08:53:38Z"},{"alias_kind":"pith_short_16","alias_value":"RWYVEK3Z47JUVYWE","created_at":"2026-07-05T08:53:38Z"},{"alias_kind":"pith_short_8","alias_value":"RWYVEK3Z","created_at":"2026-07-05T08:53:38Z"}],"graph_snapshots":[{"event_id":"sha256:e268d5221679cfc03a2e2b1e0d88a38cbdd5a43ef0751b44ffdc30910f303270","target":"graph","created_at":"2026-07-05T08:53:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2401.07339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ge Li, Jia Li, Kechi Zhang, Xianjie Shi, Zhi Jin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-01-14T18:12:03Z","title":"CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07339","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:692b643a51d329271116067db1d785a420a10108748ece88fb76fb7af2d3baa0","target":"record","created_at":"2026-07-05T08:53:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"70d569d44ac842e166367b533935f00587b92bffcbbd4238fe3dcef6abc1b1c9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-01-14T18:12:03Z","title_canon_sha256":"4f9b7e2d957214ee6d4b18f42587fd51589403b69d3771bf397076f3673d0645"},"schema_version":"1.0","source":{"id":"2401.07339","kind":"arxiv","version":2}},"canonical_sha256":"8db1522b79e7d34ae2c4cda2f50391b81c43ca8bfd8e1bb0c4918cc3b047c5fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8db1522b79e7d34ae2c4cda2f50391b81c43ca8bfd8e1bb0c4918cc3b047c5fd","first_computed_at":"2026-07-05T08:53:38.755413Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:38.755413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GTNN66aV8/ITN9ApGcVHGDJLLXdLwDCRjRMcLfp71NqRnogoesDUx7WKVJR+dCVPxbMKkvIHg3KVN0lqSxApAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:38.755803Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.07339","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:692b643a51d329271116067db1d785a420a10108748ece88fb76fb7af2d3baa0","sha256:e268d5221679cfc03a2e2b1e0d88a38cbdd5a43ef0751b44ffdc30910f303270"],"state_sha256":"63c9861a290fdf388d18bf954c515b047557e9ab2eaa4f1db41b708920ba39b5"}