{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DF4CVIN37Y7QQTQC4DGPPFDZKK","short_pith_number":"pith:DF4CVIN3","schema_version":"1.0","canonical_sha256":"19782aa1bbfe3f084e02e0ccf7947952bcd2ce3a9427528a3ef5f8f3c663d469","source":{"kind":"arxiv","id":"2505.02133","version":1},"attestation_state":"computed","paper":{"title":"Enhancing LLM Code Generation: A Systematic Evaluation of Multi-Agent Collaboration and Runtime Debugging for Improved Accuracy, Reliability, and Latency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Mohammed Mediani, Nazmus Ashrafi, Salah Bouktif","submitted_at":"2025-05-04T14:44:27Z","abstract_excerpt":"The use of large language models (LLMs) for automated code generation has emerged as a significant focus within AI research. As these pretrained models continue to evolve, their ability to understand and generate complex code structures has opened new possibilities for automating intricate programming tasks for the sake of accurate code generation. Although contemporary foundational models demonstrate promoting results, researchers continue to explore optimal post-training strategies to enhance code quality. These include supervised fine-tuning, retrieval-augmented generation (RAG), debugging,"},"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":"2505.02133","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-05-04T14:44:27Z","cross_cats_sorted":[],"title_canon_sha256":"67ccada352b3b9606b7092838adbfb2bdad8406f10d355a2f7e406c0080a94c0","abstract_canon_sha256":"795b061953ae3814a9951097d9323c91bea8073fc0a95324da73c0ad22295c0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:32.515960Z","signature_b64":"o50Hrx7wiAYCBw0vK5GKJvZ+xcE2xGhZtv++qmXL0huU3RIzzVwA8QWpapscAxN/lUrYKlAwl4qPJl0bolXKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19782aa1bbfe3f084e02e0ccf7947952bcd2ce3a9427528a3ef5f8f3c663d469","last_reissued_at":"2026-07-05T10:58:32.515458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:32.515458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing LLM Code Generation: A Systematic Evaluation of Multi-Agent Collaboration and Runtime Debugging for Improved Accuracy, Reliability, and Latency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Mohammed Mediani, Nazmus Ashrafi, Salah Bouktif","submitted_at":"2025-05-04T14:44:27Z","abstract_excerpt":"The use of large language models (LLMs) for automated code generation has emerged as a significant focus within AI research. As these pretrained models continue to evolve, their ability to understand and generate complex code structures has opened new possibilities for automating intricate programming tasks for the sake of accurate code generation. Although contemporary foundational models demonstrate promoting results, researchers continue to explore optimal post-training strategies to enhance code quality. These include supervised fine-tuning, retrieval-augmented generation (RAG), debugging,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02133","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/2505.02133/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":"2505.02133","created_at":"2026-07-05T10:58:32.515526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02133v1","created_at":"2026-07-05T10:58:32.515526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02133","created_at":"2026-07-05T10:58:32.515526+00:00"},{"alias_kind":"pith_short_12","alias_value":"DF4CVIN37Y7Q","created_at":"2026-07-05T10:58:32.515526+00:00"},{"alias_kind":"pith_short_16","alias_value":"DF4CVIN37Y7QQTQC","created_at":"2026-07-05T10:58:32.515526+00:00"},{"alias_kind":"pith_short_8","alias_value":"DF4CVIN3","created_at":"2026-07-05T10:58:32.515526+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00308","citing_title":"How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEval","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03619","citing_title":"The Infinite Mutation Engine? Measuring Polymorphism in LLM-Generated Offensive Code","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19201","citing_title":"Cascaded Code Editing: Large-Small Model Collaboration for Effective and Efficient Code Editing","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03619","citing_title":"The Infinite Mutation Engine? Measuring Polymorphism in LLM-Generated Offensive Code","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DF4CVIN37Y7QQTQC4DGPPFDZKK","json":"https://pith.science/pith/DF4CVIN37Y7QQTQC4DGPPFDZKK.json","graph_json":"https://pith.science/api/pith-number/DF4CVIN37Y7QQTQC4DGPPFDZKK/graph.json","events_json":"https://pith.science/api/pith-number/DF4CVIN37Y7QQTQC4DGPPFDZKK/events.json","paper":"https://pith.science/paper/DF4CVIN3"},"agent_actions":{"view_html":"https://pith.science/pith/DF4CVIN37Y7QQTQC4DGPPFDZKK","download_json":"https://pith.science/pith/DF4CVIN37Y7QQTQC4DGPPFDZKK.json","view_paper":"https://pith.science/paper/DF4CVIN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02133&json=true","fetch_graph":"https://pith.science/api/pith-number/DF4CVIN37Y7QQTQC4DGPPFDZKK/graph.json","fetch_events":"https://pith.science/api/pith-number/DF4CVIN37Y7QQTQC4DGPPFDZKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DF4CVIN37Y7QQTQC4DGPPFDZKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DF4CVIN37Y7QQTQC4DGPPFDZKK/action/storage_attestation","attest_author":"https://pith.science/pith/DF4CVIN37Y7QQTQC4DGPPFDZKK/action/author_attestation","sign_citation":"https://pith.science/pith/DF4CVIN37Y7QQTQC4DGPPFDZKK/action/citation_signature","submit_replication":"https://pith.science/pith/DF4CVIN37Y7QQTQC4DGPPFDZKK/action/replication_record"}},"created_at":"2026-07-05T10:58:32.515526+00:00","updated_at":"2026-07-05T10:58:32.515526+00:00"}