{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WCBFZDNGFNZHAAQ2WEAIUUTHFR","short_pith_number":"pith:WCBFZDNG","schema_version":"1.0","canonical_sha256":"b0825c8da62b7270021ab1008a52672c4c877ef2c7347fab99354803b69843cf","source":{"kind":"arxiv","id":"2402.16906","version":6},"attestation_state":"computed","paper":{"title":"Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Jingbo Shang, Li Zhong, Zilong Wang","submitted_at":"2024-02-25T00:56:27Z","abstract_excerpt":"Large language models (LLMs) are leading significant progress in code generation. Beyond one-pass code generation, recent works further integrate unit tests and program verifiers into LLMs to iteratively refine the generated programs. However, these works consider the generated programs as an indivisible entity, which falls short for LLMs in debugging the programs, especially when the programs contain complex logic flows and data operations. In contrast, when human developers debug programs, they typically set breakpoints and selectively examine runtime execution information. The execution flo"},"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":"2402.16906","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-02-25T00:56:27Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"81f9994e16e91ef49cc5d6dcf6bc01aee9e707d9035aa40134a0b4204ac0af74","abstract_canon_sha256":"bf4fb918cd87c6d47dab4aa418fe35be09fffc692838a5472756a7b4e8bb63bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:45.987991Z","signature_b64":"Ulr1o/+3rWOp7FgBhqPN/p6zRQH+HdnxiBDX+WfR8v3bvXwjxRT1NFqcAjWrtBtX9QCBuw0+aiYo7tA7+ycECA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0825c8da62b7270021ab1008a52672c4c877ef2c7347fab99354803b69843cf","last_reissued_at":"2026-07-05T08:29:45.987575Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:45.987575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Jingbo Shang, Li Zhong, Zilong Wang","submitted_at":"2024-02-25T00:56:27Z","abstract_excerpt":"Large language models (LLMs) are leading significant progress in code generation. Beyond one-pass code generation, recent works further integrate unit tests and program verifiers into LLMs to iteratively refine the generated programs. However, these works consider the generated programs as an indivisible entity, which falls short for LLMs in debugging the programs, especially when the programs contain complex logic flows and data operations. In contrast, when human developers debug programs, they typically set breakpoints and selectively examine runtime execution information. The execution flo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16906","kind":"arxiv","version":6},"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/2402.16906/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":"2402.16906","created_at":"2026-07-05T08:29:45.987632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16906v6","created_at":"2026-07-05T08:29:45.987632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16906","created_at":"2026-07-05T08:29:45.987632+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCBFZDNGFNZH","created_at":"2026-07-05T08:29:45.987632+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCBFZDNGFNZHAAQ2","created_at":"2026-07-05T08:29:45.987632+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCBFZDNG","created_at":"2026-07-05T08:29:45.987632+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"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":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29815","citing_title":"SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2412.04590","citing_title":"Specification-Driven Code Translation Powered by Large Language Models: How Far Are We?","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19102","citing_title":"Prompt Optimization for LLM Code Generation via Reinforcement Learning","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2601.00376","citing_title":"In Line with Context: Repository-Level Code Generation via Context Inlining","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18571","citing_title":"Debug2Fix: Can Interactive Debugging Help Coding Agents Fix More Bugs?","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2603.22048","citing_title":"Dynamic analysis enhances issue resolution","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11922","citing_title":"StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10508","citing_title":"How Many Tries Does It Take? Iterative Self-Repair in LLM Code Generation Across Model Scales and Benchmarks","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10449","citing_title":"AdverMCTS: Combating Pseudo-Correctness in Code Generation via Adversarial Monte Carlo Tree Search","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WCBFZDNGFNZHAAQ2WEAIUUTHFR","json":"https://pith.science/pith/WCBFZDNGFNZHAAQ2WEAIUUTHFR.json","graph_json":"https://pith.science/api/pith-number/WCBFZDNGFNZHAAQ2WEAIUUTHFR/graph.json","events_json":"https://pith.science/api/pith-number/WCBFZDNGFNZHAAQ2WEAIUUTHFR/events.json","paper":"https://pith.science/paper/WCBFZDNG"},"agent_actions":{"view_html":"https://pith.science/pith/WCBFZDNGFNZHAAQ2WEAIUUTHFR","download_json":"https://pith.science/pith/WCBFZDNGFNZHAAQ2WEAIUUTHFR.json","view_paper":"https://pith.science/paper/WCBFZDNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16906&json=true","fetch_graph":"https://pith.science/api/pith-number/WCBFZDNGFNZHAAQ2WEAIUUTHFR/graph.json","fetch_events":"https://pith.science/api/pith-number/WCBFZDNGFNZHAAQ2WEAIUUTHFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCBFZDNGFNZHAAQ2WEAIUUTHFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCBFZDNGFNZHAAQ2WEAIUUTHFR/action/storage_attestation","attest_author":"https://pith.science/pith/WCBFZDNGFNZHAAQ2WEAIUUTHFR/action/author_attestation","sign_citation":"https://pith.science/pith/WCBFZDNGFNZHAAQ2WEAIUUTHFR/action/citation_signature","submit_replication":"https://pith.science/pith/WCBFZDNGFNZHAAQ2WEAIUUTHFR/action/replication_record"}},"created_at":"2026-07-05T08:29:45.987632+00:00","updated_at":"2026-07-05T08:29:45.987632+00:00"}