{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OOW2UAOITPPXUOUSVUT5MKATMK","short_pith_number":"pith:OOW2UAOI","schema_version":"1.0","canonical_sha256":"73adaa01c89bdf7a3a92ad27d62813628260aba5c31f56113ec00a6649d711ed","source":{"kind":"arxiv","id":"2403.06095","version":4},"attestation_state":"computed","paper":{"title":"RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Hoang N. Phan, Huy N. Phan, Nghi D. Q. Bui, Tien N. Nguyen","submitted_at":"2024-03-10T05:10:34Z","abstract_excerpt":"Code Large Language Models (CodeLLMs) have demonstrated impressive proficiency in code completion tasks. However, they often fall short of fully understanding the extensive context of a project repository, such as the intricacies of relevant files and class hierarchies, which can result in less precise completions. To overcome these limitations, we present \\tool, a multifaceted framework designed to address the complex challenges associated with repository-level code completion. Central to RepoHYPER is the {\\em Repo-level Semantic Graph} (RSG), a novel semantic graph structure that encapsulate"},"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":"2403.06095","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SE","submitted_at":"2024-03-10T05:10:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b6c48456a20a90f8995b62f699d2f1376dd692d5466ec0bbb0720dbcbfec5ea7","abstract_canon_sha256":"4b484e03cf4f0b8dab727f4f3315cdcef6f8631e4ddf9e856e4e17b0ea7306df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:21.988159Z","signature_b64":"nIC8R0qDI8QQYrfAX9wKVyCRWQbnbb9jsoBuJAlVvu29oSMWdQoPYr/+8y1V4iY7rD7+1vAf3QVjLAp6iurYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73adaa01c89bdf7a3a92ad27d62813628260aba5c31f56113ec00a6649d711ed","last_reissued_at":"2026-07-05T08:55:21.987732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:21.987732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Hoang N. Phan, Huy N. Phan, Nghi D. Q. Bui, Tien N. Nguyen","submitted_at":"2024-03-10T05:10:34Z","abstract_excerpt":"Code Large Language Models (CodeLLMs) have demonstrated impressive proficiency in code completion tasks. However, they often fall short of fully understanding the extensive context of a project repository, such as the intricacies of relevant files and class hierarchies, which can result in less precise completions. To overcome these limitations, we present \\tool, a multifaceted framework designed to address the complex challenges associated with repository-level code completion. Central to RepoHYPER is the {\\em Repo-level Semantic Graph} (RSG), a novel semantic graph structure that encapsulate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06095","kind":"arxiv","version":4},"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/2403.06095/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":"2403.06095","created_at":"2026-07-05T08:55:21.987789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06095v4","created_at":"2026-07-05T08:55:21.987789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06095","created_at":"2026-07-05T08:55:21.987789+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOW2UAOITPPX","created_at":"2026-07-05T08:55:21.987789+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOW2UAOITPPXUOUS","created_at":"2026-07-05T08:55:21.987789+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOW2UAOI","created_at":"2026-07-05T08:55:21.987789+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":214,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOW2UAOITPPXUOUSVUT5MKATMK","json":"https://pith.science/pith/OOW2UAOITPPXUOUSVUT5MKATMK.json","graph_json":"https://pith.science/api/pith-number/OOW2UAOITPPXUOUSVUT5MKATMK/graph.json","events_json":"https://pith.science/api/pith-number/OOW2UAOITPPXUOUSVUT5MKATMK/events.json","paper":"https://pith.science/paper/OOW2UAOI"},"agent_actions":{"view_html":"https://pith.science/pith/OOW2UAOITPPXUOUSVUT5MKATMK","download_json":"https://pith.science/pith/OOW2UAOITPPXUOUSVUT5MKATMK.json","view_paper":"https://pith.science/paper/OOW2UAOI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06095&json=true","fetch_graph":"https://pith.science/api/pith-number/OOW2UAOITPPXUOUSVUT5MKATMK/graph.json","fetch_events":"https://pith.science/api/pith-number/OOW2UAOITPPXUOUSVUT5MKATMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOW2UAOITPPXUOUSVUT5MKATMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOW2UAOITPPXUOUSVUT5MKATMK/action/storage_attestation","attest_author":"https://pith.science/pith/OOW2UAOITPPXUOUSVUT5MKATMK/action/author_attestation","sign_citation":"https://pith.science/pith/OOW2UAOITPPXUOUSVUT5MKATMK/action/citation_signature","submit_replication":"https://pith.science/pith/OOW2UAOITPPXUOUSVUT5MKATMK/action/replication_record"}},"created_at":"2026-07-05T08:55:21.987789+00:00","updated_at":"2026-07-05T08:55:21.987789+00:00"}