{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZU3PBYK6C2XVR2SNUPRRHMNGKJ","short_pith_number":"pith:ZU3PBYK6","schema_version":"1.0","canonical_sha256":"cd36f0e15e16af58ea4da3e313b1a65279ade33d90aa138bffa9d47a25dfef2d","source":{"kind":"arxiv","id":"2410.14684","version":2},"attestation_state":"computed","paper":{"title":"RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Dong Yu, Hongming Zhang, Jiawei Han, Kaixin Ma, Mengzhao Jia, Siru Ouyang, Wenhao Yu, Zhihan Zhang, Zilin Xiao","submitted_at":"2024-10-03T05:45:26Z","abstract_excerpt":"Large Language Models (LLMs) excel in code generation yet struggle with modern AI software engineering tasks. Unlike traditional function-level or file-level coding tasks, AI software engineering requires not only basic coding proficiency but also advanced skills in managing and interacting with code repositories. However, existing methods often overlook the need for repository-level code understanding, which is crucial for accurately grasping the broader context and developing effective solutions. On this basis, we present RepoGraph, a plug-in module that manages a repository-level structure "},"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":"2410.14684","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-10-03T05:45:26Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"6942a859d9d8096d83a6bc4c7c146770ad52c8cf4adbcdb964849e58ce88a6fa","abstract_canon_sha256":"dca1231c15a7adc4c8d745ed2fda68ed5ecaba96b82a294d18ea1ac380cf047e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:11.822857Z","signature_b64":"MXpPomNrm8yX8m7+zMbBp8rkV1owVp7rkPH5Nd7rQ7dvogqqPQ/p/9ptYEbRNTQjdU0bigvDmtcLTnoImqkBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd36f0e15e16af58ea4da3e313b1a65279ade33d90aa138bffa9d47a25dfef2d","last_reissued_at":"2026-07-05T10:34:11.822325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:11.822325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Dong Yu, Hongming Zhang, Jiawei Han, Kaixin Ma, Mengzhao Jia, Siru Ouyang, Wenhao Yu, Zhihan Zhang, Zilin Xiao","submitted_at":"2024-10-03T05:45:26Z","abstract_excerpt":"Large Language Models (LLMs) excel in code generation yet struggle with modern AI software engineering tasks. Unlike traditional function-level or file-level coding tasks, AI software engineering requires not only basic coding proficiency but also advanced skills in managing and interacting with code repositories. However, existing methods often overlook the need for repository-level code understanding, which is crucial for accurately grasping the broader context and developing effective solutions. On this basis, we present RepoGraph, a plug-in module that manages a repository-level structure "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14684","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/2410.14684/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":"2410.14684","created_at":"2026-07-05T10:34:11.822396+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14684v2","created_at":"2026-07-05T10:34:11.822396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14684","created_at":"2026-07-05T10:34:11.822396+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZU3PBYK6C2XV","created_at":"2026-07-05T10:34:11.822396+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZU3PBYK6C2XVR2SN","created_at":"2026-07-05T10:34:11.822396+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZU3PBYK6","created_at":"2026-07-05T10:34:11.822396+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26979","citing_title":"How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22417","citing_title":"Code Isn't Memory: A Structural Codebase Index Inside a Coding Agent","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21963","citing_title":"Holmes: Multimodal Agentic Diagnosis for Mixed-Language Mobile Crashes at Industrial Scale","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20512","citing_title":"Probe-and-Refine Tuning of Repository Guidance for Coding Agents","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26979","citing_title":"How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01916","citing_title":"ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08135","citing_title":"TICoder: A Repository-Level Code Generation Framework with Test-Driven Planning and Implementation-Aware Reuse","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2601.00376","citing_title":"In Line with Context: Repository-Level Code Generation via Context Inlining","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03622","citing_title":"Toward Executable Repository-Level Code Generation via Environment Alignment","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18413","citing_title":"TypeScript Repository Indexing for Code Agent Retrieval","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04580","citing_title":"Beyond Fixed Tests: Repository-Level Issue Resolution as Coevolution of Code and Behavioral Constraints","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZU3PBYK6C2XVR2SNUPRRHMNGKJ","json":"https://pith.science/pith/ZU3PBYK6C2XVR2SNUPRRHMNGKJ.json","graph_json":"https://pith.science/api/pith-number/ZU3PBYK6C2XVR2SNUPRRHMNGKJ/graph.json","events_json":"https://pith.science/api/pith-number/ZU3PBYK6C2XVR2SNUPRRHMNGKJ/events.json","paper":"https://pith.science/paper/ZU3PBYK6"},"agent_actions":{"view_html":"https://pith.science/pith/ZU3PBYK6C2XVR2SNUPRRHMNGKJ","download_json":"https://pith.science/pith/ZU3PBYK6C2XVR2SNUPRRHMNGKJ.json","view_paper":"https://pith.science/paper/ZU3PBYK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14684&json=true","fetch_graph":"https://pith.science/api/pith-number/ZU3PBYK6C2XVR2SNUPRRHMNGKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZU3PBYK6C2XVR2SNUPRRHMNGKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZU3PBYK6C2XVR2SNUPRRHMNGKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZU3PBYK6C2XVR2SNUPRRHMNGKJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZU3PBYK6C2XVR2SNUPRRHMNGKJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZU3PBYK6C2XVR2SNUPRRHMNGKJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZU3PBYK6C2XVR2SNUPRRHMNGKJ/action/replication_record"}},"created_at":"2026-07-05T10:34:11.822396+00:00","updated_at":"2026-07-05T10:34:11.822396+00:00"}