{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7OMB3JIT25K27AVNVZTFDQEWHZ","short_pith_number":"pith:7OMB3JIT","schema_version":"1.0","canonical_sha256":"fb981da513d755af82adae6651c0963e407c6785ad9cdff95aea896230a4479a","source":{"kind":"arxiv","id":"2502.06633","version":1},"attestation_state":"computed","paper":{"title":"Combining Large Language Models with Static Analyzers for Code Review Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Houari Sahraoui, Imen Jaoua, Oussama Ben Sghaier","submitted_at":"2025-02-10T16:29:12Z","abstract_excerpt":"Code review is a crucial but often complex, subjective, and time-consuming activity in software development. Over the past decades, significant efforts have been made to automate this process. Early approaches focused on knowledge-based systems (KBS) that apply rule-based mechanisms to detect code issues, providing precise feedback but struggling with complex, context-dependent cases. More recent work has shifted toward fine-tuning pre-trained language models for code review, enabling broader issue coverage but often at the expense of precision. In this paper, we propose a hybrid approach that"},"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":"2502.06633","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-10T16:29:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6268ac1568c5bf7b002e32d5bcc22e07ae156bd4026ae5aba0cee58a2150b902","abstract_canon_sha256":"69051f19c37b6a6870ba330e7ab7321ebd2e0b42a50a9abbc82538295b77cfd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:09.825103Z","signature_b64":"xstKge1x2YxLycvBoyMCkMdA9TXAUVaEmVLIyVdmBkX0fCMPACR12dg5TBm0gX4Sit5oOLJcasPe7NpEYYtBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb981da513d755af82adae6651c0963e407c6785ad9cdff95aea896230a4479a","last_reissued_at":"2026-07-05T10:12:09.824600Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:09.824600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Combining Large Language Models with Static Analyzers for Code Review Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Houari Sahraoui, Imen Jaoua, Oussama Ben Sghaier","submitted_at":"2025-02-10T16:29:12Z","abstract_excerpt":"Code review is a crucial but often complex, subjective, and time-consuming activity in software development. Over the past decades, significant efforts have been made to automate this process. Early approaches focused on knowledge-based systems (KBS) that apply rule-based mechanisms to detect code issues, providing precise feedback but struggling with complex, context-dependent cases. More recent work has shifted toward fine-tuning pre-trained language models for code review, enabling broader issue coverage but often at the expense of precision. In this paper, we propose a hybrid approach that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06633","kind":"arxiv","version":1},"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/2502.06633/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":"2502.06633","created_at":"2026-07-05T10:12:09.824662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06633v1","created_at":"2026-07-05T10:12:09.824662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06633","created_at":"2026-07-05T10:12:09.824662+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OMB3JIT25K2","created_at":"2026-07-05T10:12:09.824662+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OMB3JIT25K27AVN","created_at":"2026-07-05T10:12:09.824662+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OMB3JIT","created_at":"2026-07-05T10:12:09.824662+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.11687","citing_title":"MetaLint: Easy-to-Hard Generalization for Code Linting","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7OMB3JIT25K27AVNVZTFDQEWHZ","json":"https://pith.science/pith/7OMB3JIT25K27AVNVZTFDQEWHZ.json","graph_json":"https://pith.science/api/pith-number/7OMB3JIT25K27AVNVZTFDQEWHZ/graph.json","events_json":"https://pith.science/api/pith-number/7OMB3JIT25K27AVNVZTFDQEWHZ/events.json","paper":"https://pith.science/paper/7OMB3JIT"},"agent_actions":{"view_html":"https://pith.science/pith/7OMB3JIT25K27AVNVZTFDQEWHZ","download_json":"https://pith.science/pith/7OMB3JIT25K27AVNVZTFDQEWHZ.json","view_paper":"https://pith.science/paper/7OMB3JIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06633&json=true","fetch_graph":"https://pith.science/api/pith-number/7OMB3JIT25K27AVNVZTFDQEWHZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7OMB3JIT25K27AVNVZTFDQEWHZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OMB3JIT25K27AVNVZTFDQEWHZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OMB3JIT25K27AVNVZTFDQEWHZ/action/storage_attestation","attest_author":"https://pith.science/pith/7OMB3JIT25K27AVNVZTFDQEWHZ/action/author_attestation","sign_citation":"https://pith.science/pith/7OMB3JIT25K27AVNVZTFDQEWHZ/action/citation_signature","submit_replication":"https://pith.science/pith/7OMB3JIT25K27AVNVZTFDQEWHZ/action/replication_record"}},"created_at":"2026-07-05T10:12:09.824662+00:00","updated_at":"2026-07-05T10:12:09.824662+00:00"}