{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WR6TNTV5PJFSDQSKN5FAMHFMS3","short_pith_number":"pith:WR6TNTV5","schema_version":"1.0","canonical_sha256":"b47d36cebd7a4b21c24a6f4a061cac96d8b1f09534e95c55532fd59165b19b6f","source":{"kind":"arxiv","id":"2304.00385","version":2},"attestation_state":"computed","paper":{"title":"Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Chunqiu Steven Xia, Lingming Zhang","submitted_at":"2023-04-01T20:57:33Z","abstract_excerpt":"Automated Program Repair (APR) aims to automatically generate patches for buggy programs. Recent APR work has been focused on leveraging modern Large Language Models (LLMs) to directly generate patches for APR. Such LLM-based APR tools work by first constructing an input prompt built using the original buggy code and then queries the LLM to generate patches. While the LLM-based APR tools are able to achieve state-of-the-art results, it still follows the classic Generate and Validate repair paradigm of first generating lots of patches and then validating each one afterwards. This not only leads"},"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":"2304.00385","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-04-01T20:57:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2ed3b3631da20ad43d2b49daf90b878b7c4e6fe5852f0476fc6423e46bb09b1f","abstract_canon_sha256":"857195f8c8560bd321058e6115e88ab64f74b7e08da256459f23f203624cbee2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:41.467796Z","signature_b64":"zQi2uGGRKJtS8UPF/Qf8UlmN1zPv5DU2wjfYEzRmGn7ypnMRiX32eYlrnZs1Nn7bA8mIaSCcRpAjyBe5jzD1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b47d36cebd7a4b21c24a6f4a061cac96d8b1f09534e95c55532fd59165b19b6f","last_reissued_at":"2026-07-05T09:46:41.467305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:41.467305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Chunqiu Steven Xia, Lingming Zhang","submitted_at":"2023-04-01T20:57:33Z","abstract_excerpt":"Automated Program Repair (APR) aims to automatically generate patches for buggy programs. Recent APR work has been focused on leveraging modern Large Language Models (LLMs) to directly generate patches for APR. Such LLM-based APR tools work by first constructing an input prompt built using the original buggy code and then queries the LLM to generate patches. While the LLM-based APR tools are able to achieve state-of-the-art results, it still follows the classic Generate and Validate repair paradigm of first generating lots of patches and then validating each one afterwards. This not only leads"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.00385","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/2304.00385/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":"2304.00385","created_at":"2026-07-05T09:46:41.467373+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.00385v2","created_at":"2026-07-05T09:46:41.467373+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.00385","created_at":"2026-07-05T09:46:41.467373+00:00"},{"alias_kind":"pith_short_12","alias_value":"WR6TNTV5PJFS","created_at":"2026-07-05T09:46:41.467373+00:00"},{"alias_kind":"pith_short_16","alias_value":"WR6TNTV5PJFSDQSK","created_at":"2026-07-05T09:46:41.467373+00:00"},{"alias_kind":"pith_short_8","alias_value":"WR6TNTV5","created_at":"2026-07-05T09:46:41.467373+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07999","citing_title":"Efficient Skill Grounding via Code Refactoring with Small Language Models","ref_index":113,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08455","citing_title":"CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2305.12138","citing_title":"Exploring Code Analysis: Zero-Shot Insights on Syntax and Semantics with LLMs","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2408.01055","citing_title":"Towards Agentic Runtime Healing","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16725","citing_title":"Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2512.18436","citing_title":"VeruSAGE: A Study of Agent-Based Verification for Rust Systems","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18449","citing_title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03851","citing_title":"Beyond Crash-to-Patch: Patch Evolution for Linux Kernel Repair","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2407.01489","citing_title":"Agentless: Demystifying LLM-based Software Engineering Agents","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08455","citing_title":"CUDABeaver: Benchmarking LLM-Based Automated CUDA Debugging","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24218","citing_title":"RefEvo: Agentic Design with Co-Evolutionary Verification for Agile Reference Model Generation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17977","citing_title":"MASFuzzer: Fuzz Driver Generation and Adaptive Scheduling via Multidimensional API Sequences","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WR6TNTV5PJFSDQSKN5FAMHFMS3","json":"https://pith.science/pith/WR6TNTV5PJFSDQSKN5FAMHFMS3.json","graph_json":"https://pith.science/api/pith-number/WR6TNTV5PJFSDQSKN5FAMHFMS3/graph.json","events_json":"https://pith.science/api/pith-number/WR6TNTV5PJFSDQSKN5FAMHFMS3/events.json","paper":"https://pith.science/paper/WR6TNTV5"},"agent_actions":{"view_html":"https://pith.science/pith/WR6TNTV5PJFSDQSKN5FAMHFMS3","download_json":"https://pith.science/pith/WR6TNTV5PJFSDQSKN5FAMHFMS3.json","view_paper":"https://pith.science/paper/WR6TNTV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.00385&json=true","fetch_graph":"https://pith.science/api/pith-number/WR6TNTV5PJFSDQSKN5FAMHFMS3/graph.json","fetch_events":"https://pith.science/api/pith-number/WR6TNTV5PJFSDQSKN5FAMHFMS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WR6TNTV5PJFSDQSKN5FAMHFMS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WR6TNTV5PJFSDQSKN5FAMHFMS3/action/storage_attestation","attest_author":"https://pith.science/pith/WR6TNTV5PJFSDQSKN5FAMHFMS3/action/author_attestation","sign_citation":"https://pith.science/pith/WR6TNTV5PJFSDQSKN5FAMHFMS3/action/citation_signature","submit_replication":"https://pith.science/pith/WR6TNTV5PJFSDQSKN5FAMHFMS3/action/replication_record"}},"created_at":"2026-07-05T09:46:41.467373+00:00","updated_at":"2026-07-05T09:46:41.467373+00:00"}