{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P3SW5TQDWJ66SP67MI52MELCU3","short_pith_number":"pith:P3SW5TQD","schema_version":"1.0","canonical_sha256":"7ee56ece03b27de93fdf623ba61162a6eebf7b5c39e66ab2415d64668e99915c","source":{"kind":"arxiv","id":"2604.17338","version":4},"attestation_state":"computed","paper":{"title":"Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Frontier LLMs pass debugging tests above 76 percent yet edit with precision below 45 percent, often regenerating entire solutions instead of making targeted fixes.","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Honghua Dong, Miaosen Chai, Robin Jia, Shangshang Wang, Song Bian, Wang Bill Zhu, Willie Neiswanger, Yejia Liu","submitted_at":"2026-04-19T09:08:23Z","abstract_excerpt":"Unlike code completion, debugging requires localizing faults and applying targeted edits. We observe that frontier LLMs often regenerate correct but over-edited solutions during debugging. To evaluate how far LLMs are from precise debugging, we introduce the Precise Debugging Benchmark (PDB) framework, which automatically converts any coding dataset into a debugging benchmark with precision-aware evaluation. PDB generates buggy programs by synthesizing verified atomic bugs and composing them into multi-bug programs. We define two novel metrics, edit-level precision and bug-level recall, which "},"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":"2604.17338","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-19T09:08:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ae186650e23b68441935990920cd0cedd02e5a1ea8d2f2523644cc1cb669b4ac","abstract_canon_sha256":"603fc203afb649abde113a1836b1896540aab56d93223a4ca49f3caeb2df3143"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:11.747354Z","signature_b64":"j5wBEgjbJvRrRPyhaJn6u1Z9fq+islOP/gaZPhSw8jQvGQ2G82GOTzi/TqmVZsd2hkiRZQKBAJuT90TlScn3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ee56ece03b27de93fdf623ba61162a6eebf7b5c39e66ab2415d64668e99915c","last_reissued_at":"2026-05-20T00:02:11.746673Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:11.746673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Frontier LLMs pass debugging tests above 76 percent yet edit with precision below 45 percent, often regenerating entire solutions instead of making targeted fixes.","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Honghua Dong, Miaosen Chai, Robin Jia, Shangshang Wang, Song Bian, Wang Bill Zhu, Willie Neiswanger, Yejia Liu","submitted_at":"2026-04-19T09:08:23Z","abstract_excerpt":"Unlike code completion, debugging requires localizing faults and applying targeted edits. We observe that frontier LLMs often regenerate correct but over-edited solutions during debugging. To evaluate how far LLMs are from precise debugging, we introduce the Precise Debugging Benchmark (PDB) framework, which automatically converts any coding dataset into a debugging benchmark with precision-aware evaluation. PDB generates buggy programs by synthesizing verified atomic bugs and composing them into multi-bug programs. We define two novel metrics, edit-level precision and bug-level recall, which "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"frontier models, such as GPT-5.1-Codex and DeepSeek-V3.2-Thinking, achieve unit-test pass rates above 76% but exhibit precision below 45%, even when explicitly instructed to perform minimal debugging.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The automatically synthesized verified atomic bugs and their compositions accurately represent real-world debugging scenarios, and the new edit-level precision and bug-level recall metrics validly measure 'precise debugging' behavior.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Frontier LLMs pass unit tests over 76% of the time on debugging tasks but achieve edit precision below 45%, indicating regeneration rather than precise debugging.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Frontier LLMs pass debugging tests above 76 percent yet edit with precision below 45 percent, often regenerating entire solutions instead of making targeted fixes.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a0d6bb01a10e7ad1e8db6572a092252383a3053a08787a1d072936f35a79b5c4"},"source":{"id":"2604.17338","kind":"arxiv","version":4},"verdict":{"id":"e674bdeb-e6d4-473d-a1ed-67e9a97eae90","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T06:02:06.759620Z","strongest_claim":"frontier models, such as GPT-5.1-Codex and DeepSeek-V3.2-Thinking, achieve unit-test pass rates above 76% but exhibit precision below 45%, even when explicitly instructed to perform minimal debugging.","one_line_summary":"Frontier LLMs pass unit tests over 76% of the time on debugging tasks but achieve edit precision below 45%, indicating regeneration rather than precise debugging.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The automatically synthesized verified atomic bugs and their compositions accurately represent real-world debugging scenarios, and the new edit-level precision and bug-level recall metrics validly measure 'precise debugging' behavior.","pith_extraction_headline":"Frontier LLMs pass debugging tests above 76 percent yet edit with precision below 45 percent, often regenerating entire solutions instead of making targeted fixes."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.17338/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":"2604.17338","created_at":"2026-05-20T00:02:11.746762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.17338v4","created_at":"2026-05-20T00:02:11.746762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17338","created_at":"2026-05-20T00:02:11.746762+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3SW5TQDWJ66","created_at":"2026-05-20T00:02:11.746762+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3SW5TQDWJ66SP67","created_at":"2026-05-20T00:02:11.746762+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3SW5TQD","created_at":"2026-05-20T00:02:11.746762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3SW5TQDWJ66SP67MI52MELCU3","json":"https://pith.science/pith/P3SW5TQDWJ66SP67MI52MELCU3.json","graph_json":"https://pith.science/api/pith-number/P3SW5TQDWJ66SP67MI52MELCU3/graph.json","events_json":"https://pith.science/api/pith-number/P3SW5TQDWJ66SP67MI52MELCU3/events.json","paper":"https://pith.science/paper/P3SW5TQD"},"agent_actions":{"view_html":"https://pith.science/pith/P3SW5TQDWJ66SP67MI52MELCU3","download_json":"https://pith.science/pith/P3SW5TQDWJ66SP67MI52MELCU3.json","view_paper":"https://pith.science/paper/P3SW5TQD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.17338&json=true","fetch_graph":"https://pith.science/api/pith-number/P3SW5TQDWJ66SP67MI52MELCU3/graph.json","fetch_events":"https://pith.science/api/pith-number/P3SW5TQDWJ66SP67MI52MELCU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3SW5TQDWJ66SP67MI52MELCU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3SW5TQDWJ66SP67MI52MELCU3/action/storage_attestation","attest_author":"https://pith.science/pith/P3SW5TQDWJ66SP67MI52MELCU3/action/author_attestation","sign_citation":"https://pith.science/pith/P3SW5TQDWJ66SP67MI52MELCU3/action/citation_signature","submit_replication":"https://pith.science/pith/P3SW5TQDWJ66SP67MI52MELCU3/action/replication_record"}},"created_at":"2026-05-20T00:02:11.746762+00:00","updated_at":"2026-05-20T00:02:11.746762+00:00"}