{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DFTFA5SQDXOPTH6AFRIWB2PHOT","short_pith_number":"pith:DFTFA5SQ","schema_version":"1.0","canonical_sha256":"19665076501ddcf99fc02c5160e9e774c5c319ddf833bdd0c5416df06235d61a","source":{"kind":"arxiv","id":"2408.03910","version":2},"attestation_state":"computed","paper":{"title":"CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Bo Lan, Fei Wang, Michael Shieh, Wenmeng Zhou, Xiangyan Liu, Yang Liu, Zhicheng Zhang, Zhiyuan Hu","submitted_at":"2024-08-07T17:13:59Z","abstract_excerpt":"Large Language Models (LLMs) excel in stand-alone code tasks like HumanEval and MBPP, but struggle with handling entire code repositories. This challenge has prompted research on enhancing LLM-codebase interaction at a repository scale. Current solutions rely on similarity-based retrieval or manual tools and APIs, each with notable drawbacks. Similarity-based retrieval often has low recall in complex tasks, while manual tools and APIs are typically task-specific and require expert knowledge, reducing their generalizability across diverse code tasks and real-world applications. To mitigate thes"},"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":"2408.03910","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-08-07T17:13:59Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"57c4e2720692342ace37b1a1223053e551ffd18bf54df11876d583aee094652d","abstract_canon_sha256":"f861a9b62becd4ce4464a47369bfb12703b36343cd1a1cb2f791fc10655e4393"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:17.043334Z","signature_b64":"K921IRPIkLdmlxYe9hm06k2PMyU3SA0fjjQiNF3TC3/kCqV/g4s25nikl7G1wYrHzAOoPQbO74kTwYOJIIYYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19665076501ddcf99fc02c5160e9e774c5c319ddf833bdd0c5416df06235d61a","last_reissued_at":"2026-07-05T08:54:17.042918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:17.042918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Bo Lan, Fei Wang, Michael Shieh, Wenmeng Zhou, Xiangyan Liu, Yang Liu, Zhicheng Zhang, Zhiyuan Hu","submitted_at":"2024-08-07T17:13:59Z","abstract_excerpt":"Large Language Models (LLMs) excel in stand-alone code tasks like HumanEval and MBPP, but struggle with handling entire code repositories. This challenge has prompted research on enhancing LLM-codebase interaction at a repository scale. Current solutions rely on similarity-based retrieval or manual tools and APIs, each with notable drawbacks. Similarity-based retrieval often has low recall in complex tasks, while manual tools and APIs are typically task-specific and require expert knowledge, reducing their generalizability across diverse code tasks and real-world applications. To mitigate thes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03910","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/2408.03910/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":"2408.03910","created_at":"2026-07-05T08:54:17.042970+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.03910v2","created_at":"2026-07-05T08:54:17.042970+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03910","created_at":"2026-07-05T08:54:17.042970+00:00"},{"alias_kind":"pith_short_12","alias_value":"DFTFA5SQDXOP","created_at":"2026-07-05T08:54:17.042970+00:00"},{"alias_kind":"pith_short_16","alias_value":"DFTFA5SQDXOPTH6A","created_at":"2026-07-05T08:54:17.042970+00:00"},{"alias_kind":"pith_short_8","alias_value":"DFTFA5SQ","created_at":"2026-07-05T08:54:17.042970+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.14061","citing_title":"LLM Agents Can See Code Repositories","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":262,"is_internal_anchor":true},{"citing_arxiv_id":"2603.22048","citing_title":"Dynamic analysis enhances issue resolution","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17458","citing_title":"EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DFTFA5SQDXOPTH6AFRIWB2PHOT","json":"https://pith.science/pith/DFTFA5SQDXOPTH6AFRIWB2PHOT.json","graph_json":"https://pith.science/api/pith-number/DFTFA5SQDXOPTH6AFRIWB2PHOT/graph.json","events_json":"https://pith.science/api/pith-number/DFTFA5SQDXOPTH6AFRIWB2PHOT/events.json","paper":"https://pith.science/paper/DFTFA5SQ"},"agent_actions":{"view_html":"https://pith.science/pith/DFTFA5SQDXOPTH6AFRIWB2PHOT","download_json":"https://pith.science/pith/DFTFA5SQDXOPTH6AFRIWB2PHOT.json","view_paper":"https://pith.science/paper/DFTFA5SQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.03910&json=true","fetch_graph":"https://pith.science/api/pith-number/DFTFA5SQDXOPTH6AFRIWB2PHOT/graph.json","fetch_events":"https://pith.science/api/pith-number/DFTFA5SQDXOPTH6AFRIWB2PHOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DFTFA5SQDXOPTH6AFRIWB2PHOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DFTFA5SQDXOPTH6AFRIWB2PHOT/action/storage_attestation","attest_author":"https://pith.science/pith/DFTFA5SQDXOPTH6AFRIWB2PHOT/action/author_attestation","sign_citation":"https://pith.science/pith/DFTFA5SQDXOPTH6AFRIWB2PHOT/action/citation_signature","submit_replication":"https://pith.science/pith/DFTFA5SQDXOPTH6AFRIWB2PHOT/action/replication_record"}},"created_at":"2026-07-05T08:54:17.042970+00:00","updated_at":"2026-07-05T08:54:17.042970+00:00"}