{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IM4XH5NCPTW7ATRL4LZ5DJQ6GG","short_pith_number":"pith:IM4XH5NC","schema_version":"1.0","canonical_sha256":"433973f5a27cedf04e2be2f3d1a61e3188337a6c917db3b394e8f2b468877476","source":{"kind":"arxiv","id":"2504.10412","version":1},"attestation_state":"computed","paper":{"title":"AI-Driven Code Refactoring: Using Graph Neural Networks to Enhance Software Maintainability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Gopichand Bandarupalli","submitted_at":"2025-04-14T16:58:54Z","abstract_excerpt":"This study explores Graph Neural Networks (GNNs) as a transformative tool for code refactoring, using abstract syntax trees (ASTs) to boost software maintainability. It analyzes a dataset of 2 million snippets from CodeSearchNet and a custom 75000-file GitHub Python corpus, comparing GNNs against rule-based SonarQube and decision trees. Metrics include cyclomatic complexity (target below 10), coupling (target below 5), and refactoring precision. GNNs achieve 92% accuracy, reducing complexity by 35% and coupling by 33%, outperforming SonarQube (78%, 16%) and decision trees (85%, 25%). Preproces"},"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":"2504.10412","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-04-14T16:58:54Z","cross_cats_sorted":["cs.LG","cs.SE"],"title_canon_sha256":"e62a08ee83a3286bacb887ca9f3a7bb16f1baf47a953741418eb0d957f479b34","abstract_canon_sha256":"e03d12e5802696b8fdc32b2e766b9a92582b1b8978790f16fe5536927622c8fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:59.943452Z","signature_b64":"7sHsROfnWsh9UpQCfmhZmWIBbXN4AnJP2CqScwb78rsNwiDTDXnOZBYwJEw/ZJXvg+rWitRcE0TEFfIJRA0cBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"433973f5a27cedf04e2be2f3d1a61e3188337a6c917db3b394e8f2b468877476","last_reissued_at":"2026-07-05T10:48:59.942976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:59.942976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI-Driven Code Refactoring: Using Graph Neural Networks to Enhance Software Maintainability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.AI","authors_text":"Gopichand Bandarupalli","submitted_at":"2025-04-14T16:58:54Z","abstract_excerpt":"This study explores Graph Neural Networks (GNNs) as a transformative tool for code refactoring, using abstract syntax trees (ASTs) to boost software maintainability. It analyzes a dataset of 2 million snippets from CodeSearchNet and a custom 75000-file GitHub Python corpus, comparing GNNs against rule-based SonarQube and decision trees. Metrics include cyclomatic complexity (target below 10), coupling (target below 5), and refactoring precision. GNNs achieve 92% accuracy, reducing complexity by 35% and coupling by 33%, outperforming SonarQube (78%, 16%) and decision trees (85%, 25%). Preproces"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10412","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/2504.10412/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":"2504.10412","created_at":"2026-07-05T10:48:59.943032+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.10412v1","created_at":"2026-07-05T10:48:59.943032+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10412","created_at":"2026-07-05T10:48:59.943032+00:00"},{"alias_kind":"pith_short_12","alias_value":"IM4XH5NCPTW7","created_at":"2026-07-05T10:48:59.943032+00:00"},{"alias_kind":"pith_short_16","alias_value":"IM4XH5NCPTW7ATRL","created_at":"2026-07-05T10:48:59.943032+00:00"},{"alias_kind":"pith_short_8","alias_value":"IM4XH5NC","created_at":"2026-07-05T10:48:59.943032+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06523","citing_title":"Reinforcement Learning for Autonomous Warehouse Orchestration in SAP Logistics Execution: Redefining Supply Chain Agility","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IM4XH5NCPTW7ATRL4LZ5DJQ6GG","json":"https://pith.science/pith/IM4XH5NCPTW7ATRL4LZ5DJQ6GG.json","graph_json":"https://pith.science/api/pith-number/IM4XH5NCPTW7ATRL4LZ5DJQ6GG/graph.json","events_json":"https://pith.science/api/pith-number/IM4XH5NCPTW7ATRL4LZ5DJQ6GG/events.json","paper":"https://pith.science/paper/IM4XH5NC"},"agent_actions":{"view_html":"https://pith.science/pith/IM4XH5NCPTW7ATRL4LZ5DJQ6GG","download_json":"https://pith.science/pith/IM4XH5NCPTW7ATRL4LZ5DJQ6GG.json","view_paper":"https://pith.science/paper/IM4XH5NC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.10412&json=true","fetch_graph":"https://pith.science/api/pith-number/IM4XH5NCPTW7ATRL4LZ5DJQ6GG/graph.json","fetch_events":"https://pith.science/api/pith-number/IM4XH5NCPTW7ATRL4LZ5DJQ6GG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IM4XH5NCPTW7ATRL4LZ5DJQ6GG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IM4XH5NCPTW7ATRL4LZ5DJQ6GG/action/storage_attestation","attest_author":"https://pith.science/pith/IM4XH5NCPTW7ATRL4LZ5DJQ6GG/action/author_attestation","sign_citation":"https://pith.science/pith/IM4XH5NCPTW7ATRL4LZ5DJQ6GG/action/citation_signature","submit_replication":"https://pith.science/pith/IM4XH5NCPTW7ATRL4LZ5DJQ6GG/action/replication_record"}},"created_at":"2026-07-05T10:48:59.943032+00:00","updated_at":"2026-07-05T10:48:59.943032+00:00"}