{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P3SW5TQDWJ66SP67MI52MELCU3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"603fc203afb649abde113a1836b1896540aab56d93223a4ca49f3caeb2df3143","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-19T09:08:23Z","title_canon_sha256":"ae186650e23b68441935990920cd0cedd02e5a1ea8d2f2523644cc1cb669b4ac"},"schema_version":"1.0","source":{"id":"2604.17338","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.17338","created_at":"2026-05-20T00:02:11Z"},{"alias_kind":"arxiv_version","alias_value":"2604.17338v4","created_at":"2026-05-20T00:02:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17338","created_at":"2026-05-20T00:02:11Z"},{"alias_kind":"pith_short_12","alias_value":"P3SW5TQDWJ66","created_at":"2026-05-20T00:02:11Z"},{"alias_kind":"pith_short_16","alias_value":"P3SW5TQDWJ66SP67","created_at":"2026-05-20T00:02:11Z"},{"alias_kind":"pith_short_8","alias_value":"P3SW5TQD","created_at":"2026-05-20T00:02:11Z"}],"graph_snapshots":[{"event_id":"sha256:8523b9576f8c988f5f05075ca27a6e5cc2af852ca0d2859bb33a8f4f98f9b658","target":"graph","created_at":"2026-05-20T00:02:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"a0d6bb01a10e7ad1e8db6572a092252383a3053a08787a1d072936f35a79b5c4"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.17338/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Honghua Dong, Miaosen Chai, Robin Jia, Shangshang Wang, Song Bian, Wang Bill Zhu, Willie Neiswanger, Yejia Liu","cross_cats":["cs.CL"],"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.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-19T09:08:23Z","title":"Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.17338","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-10T06:02:06.759620Z","id":"e674bdeb-e6d4-473d-a1ed-67e9a97eae90","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"e674bdeb-e6d4-473d-a1ed-67e9a97eae90"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a4bedc55190a79f5a7536a016e823652d51af6d3ca2231c932e71e9b5063deaf","target":"record","created_at":"2026-05-20T00:02:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"603fc203afb649abde113a1836b1896540aab56d93223a4ca49f3caeb2df3143","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-04-19T09:08:23Z","title_canon_sha256":"ae186650e23b68441935990920cd0cedd02e5a1ea8d2f2523644cc1cb669b4ac"},"schema_version":"1.0","source":{"id":"2604.17338","kind":"arxiv","version":4}},"canonical_sha256":"7ee56ece03b27de93fdf623ba61162a6eebf7b5c39e66ab2415d64668e99915c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ee56ece03b27de93fdf623ba61162a6eebf7b5c39e66ab2415d64668e99915c","first_computed_at":"2026-05-20T00:02:11.746673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:11.746673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j5wBEgjbJvRrRPyhaJn6u1Z9fq+islOP/gaZPhSw8jQvGQ2G82GOTzi/TqmVZsd2hkiRZQKBAJuT90TlScn3DA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:11.747354Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.17338","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4bedc55190a79f5a7536a016e823652d51af6d3ca2231c932e71e9b5063deaf","sha256:8523b9576f8c988f5f05075ca27a6e5cc2af852ca0d2859bb33a8f4f98f9b658"],"state_sha256":"a8681113d93c4e51555870d9b7e130bb444fa8bf9ebc08e6932b3ccd9785ca88"}