{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IKZ45LTA3GGWEMQVZ5JQQQ4PPA","short_pith_number":"pith:IKZ45LTA","schema_version":"1.0","canonical_sha256":"42b3ceae60d98d623215cf5308438f7837061c79d39132b37e58ad614ce52168","source":{"kind":"arxiv","id":"2502.02928","version":2},"attestation_state":"computed","paper":{"title":"Large Language Model Guided Self-Debugging Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Carlos C. N. Kuhn, Muntasir Adnan, Zhiwei Xu","submitted_at":"2025-02-05T06:43:40Z","abstract_excerpt":"Automated code generation is gaining significant importance in intelligent computer programming and system deployment. However, current approaches often face challenges in computational efficiency and lack robust mechanisms for code parsing and error correction. In this work, we propose a novel framework, PyCapsule, with a simple yet effective two-agent pipeline and efficient self-debugging modules for Python code generation. PyCapsule features sophisticated prompt inference, iterative error handling, and case testing, ensuring high generation stability, safety, and correctness. Empirically, P"},"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":"2502.02928","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-05T06:43:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b780a131bdbaf541c657fe6ed28399169225aa883d530a2d51d7db6aef342250","abstract_canon_sha256":"3f380ba36d4a84581f9b311dba1f61309c32cefdc39fe42c52ac62f877f0d9a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:07.767364Z","signature_b64":"YHPcIZKeqcohoAFl9kXA/Y7REeSkA3iSTuTyhDzaD/hwYk868EIwAOUwh0UCDey6+wkz8w/6nXWuYW5TY74wCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42b3ceae60d98d623215cf5308438f7837061c79d39132b37e58ad614ce52168","last_reissued_at":"2026-07-05T11:25:07.766871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:07.766871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Model Guided Self-Debugging Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Carlos C. N. Kuhn, Muntasir Adnan, Zhiwei Xu","submitted_at":"2025-02-05T06:43:40Z","abstract_excerpt":"Automated code generation is gaining significant importance in intelligent computer programming and system deployment. However, current approaches often face challenges in computational efficiency and lack robust mechanisms for code parsing and error correction. In this work, we propose a novel framework, PyCapsule, with a simple yet effective two-agent pipeline and efficient self-debugging modules for Python code generation. PyCapsule features sophisticated prompt inference, iterative error handling, and case testing, ensuring high generation stability, safety, and correctness. Empirically, P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02928","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/2502.02928/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":"2502.02928","created_at":"2026-07-05T11:25:07.766929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02928v2","created_at":"2026-07-05T11:25:07.766929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02928","created_at":"2026-07-05T11:25:07.766929+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKZ45LTA3GGW","created_at":"2026-07-05T11:25:07.766929+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKZ45LTA3GGWEMQV","created_at":"2026-07-05T11:25:07.766929+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKZ45LTA","created_at":"2026-07-05T11:25:07.766929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01360","citing_title":"Benchmarking Code Improvement with Progressive, Adaptive, and Interactive Feedback","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05720","citing_title":"Microskill Architecture: A Modular Skill-Driven Framework for AI-Native Code Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2508.07407","citing_title":"A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13564","citing_title":"Memory in the Age of AI Agents","ref_index":235,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IKZ45LTA3GGWEMQVZ5JQQQ4PPA","json":"https://pith.science/pith/IKZ45LTA3GGWEMQVZ5JQQQ4PPA.json","graph_json":"https://pith.science/api/pith-number/IKZ45LTA3GGWEMQVZ5JQQQ4PPA/graph.json","events_json":"https://pith.science/api/pith-number/IKZ45LTA3GGWEMQVZ5JQQQ4PPA/events.json","paper":"https://pith.science/paper/IKZ45LTA"},"agent_actions":{"view_html":"https://pith.science/pith/IKZ45LTA3GGWEMQVZ5JQQQ4PPA","download_json":"https://pith.science/pith/IKZ45LTA3GGWEMQVZ5JQQQ4PPA.json","view_paper":"https://pith.science/paper/IKZ45LTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02928&json=true","fetch_graph":"https://pith.science/api/pith-number/IKZ45LTA3GGWEMQVZ5JQQQ4PPA/graph.json","fetch_events":"https://pith.science/api/pith-number/IKZ45LTA3GGWEMQVZ5JQQQ4PPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKZ45LTA3GGWEMQVZ5JQQQ4PPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKZ45LTA3GGWEMQVZ5JQQQ4PPA/action/storage_attestation","attest_author":"https://pith.science/pith/IKZ45LTA3GGWEMQVZ5JQQQ4PPA/action/author_attestation","sign_citation":"https://pith.science/pith/IKZ45LTA3GGWEMQVZ5JQQQ4PPA/action/citation_signature","submit_replication":"https://pith.science/pith/IKZ45LTA3GGWEMQVZ5JQQQ4PPA/action/replication_record"}},"created_at":"2026-07-05T11:25:07.766929+00:00","updated_at":"2026-07-05T11:25:07.766929+00:00"}