{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UHF6IZ5RCMR5B6NPRQU4FA7KQQ","short_pith_number":"pith:UHF6IZ5R","schema_version":"1.0","canonical_sha256":"a1cbe467b11323d0f9af8c29c283ea840c6b9511fa49994e64054388c3eb3841","source":{"kind":"arxiv","id":"2605.08717","version":2},"attestation_state":"computed","paper":{"title":"Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"PROBE converts failed-run telemetry into structured evidence, diagnosis, and bounded guidance that agents can execute without changing their policy or tools.","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chenyu Zhao, Chetan Bansal, Dan Pei, Minghua Ma, Saravan Rajmohan, Shenglin Zhang, Wenwei Gu, Yihang Lin, Yongqian Sun, Zhimin Chen","submitted_at":"2026-05-09T06:02:08Z","abstract_excerpt":"Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad hoc. Existing systems expose traces or generate follow-up feedback, but they do not convert heterogeneous runtime evidence into grounded, bounded recovery guidance for a subsequent attempt. We present PROBE, a failure-anchored framework for structured recovery in software engineering agents. PROBE organizes failed-run telemetry into structured evidence, structured diagnosis, and bounded recovery guidance through a Telemetry Layer, a Diagnosis Lay"},"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":true},"canonical_record":{"source":{"id":"2605.08717","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-05-09T06:02:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7684fc60f87469cfd0f508d9be12c37293cd6f19c56ff84b07106587cdb61984","abstract_canon_sha256":"1b080022cb5a99fef2f3c76cab995cba4114931db8992531ecd03d3f9c1140c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:07.072830Z","signature_b64":"6Ek+DgDPRcjph6hErfVTj/6QAv1h2GEUvJ2u5rlWenxgGBcQarVM1IZKwyHesOOJ4znqY7b1ST+evPTpmV5KAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1cbe467b11323d0f9af8c29c283ea840c6b9511fa49994e64054388c3eb3841","last_reissued_at":"2026-06-08T01:04:07.071982Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:07.071982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"PROBE converts failed-run telemetry into structured evidence, diagnosis, and bounded guidance that agents can execute without changing their policy or tools.","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chenyu Zhao, Chetan Bansal, Dan Pei, Minghua Ma, Saravan Rajmohan, Shenglin Zhang, Wenwei Gu, Yihang Lin, Yongqian Sun, Zhimin Chen","submitted_at":"2026-05-09T06:02:08Z","abstract_excerpt":"Software engineering agents are increasingly deployed in evaluable engineering environments, yet post-failure recovery remains costly, manual, and ad hoc. Existing systems expose traces or generate follow-up feedback, but they do not convert heterogeneous runtime evidence into grounded, bounded recovery guidance for a subsequent attempt. We present PROBE, a failure-anchored framework for structured recovery in software engineering agents. PROBE organizes failed-run telemetry into structured evidence, structured diagnosis, and bounded recovery guidance through a Telemetry Layer, a Diagnosis Lay"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On 257 initially unresolved cases, PROBE achieves 65.37% Top-1 diagnosis accuracy and a 21.79% recovery rate, outperforming the strongest non-PROBE baseline by 43.58 and 12.45 percentage points.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the Guidance Gate can reliably produce diagnosis-derived guidance that is both evidence-grounded and executable within the unchanged scope of the agent's existing policy, toolset, and execution budget.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PROBE structures runtime telemetry into diagnoses and evidence-grounded guidance, raising recovery rates by 12.45 points over baselines on 257 unresolved software repair and AIOps cases.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PROBE converts failed-run telemetry into structured evidence, diagnosis, and bounded guidance that agents can execute without changing their policy or tools.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"627c1e15d69323dc8cdb3136bdc5da9110d3ac473f22b114745f7ba2a73ea623"},"source":{"id":"2605.08717","kind":"arxiv","version":2},"verdict":{"id":"dcd092c8-14ed-4f8f-b3d1-123d325dbb7c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T00:59:42.570340Z","strongest_claim":"On 257 initially unresolved cases, PROBE achieves 65.37% Top-1 diagnosis accuracy and a 21.79% recovery rate, outperforming the strongest non-PROBE baseline by 43.58 and 12.45 percentage points.","one_line_summary":"PROBE structures runtime telemetry into diagnoses and evidence-grounded guidance, raising recovery rates by 12.45 points over baselines on 257 unresolved software repair and AIOps cases.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the Guidance Gate can reliably produce diagnosis-derived guidance that is both evidence-grounded and executable within the unchanged scope of the agent's existing policy, toolset, and execution budget.","pith_extraction_headline":"PROBE converts failed-run telemetry into structured evidence, diagnosis, and bounded guidance that agents can execute without changing their policy or tools."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.08717/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T09:02:01.957960Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:35:47.929456Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T14:31:17.660461Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T10:50:59.212124Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7ac523fb323834d90cf3d678bdf5b1d59c5b5fd836d41a4fa218e367eea39870"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d34157f3f272412b0cf310d7c7245178c2f32905a6e85fd4b11a60293b26f6b2"},"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":"2605.08717","created_at":"2026-06-08T01:04:07.072121+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.08717v2","created_at":"2026-06-08T01:04:07.072121+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08717","created_at":"2026-06-08T01:04:07.072121+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHF6IZ5RCMR5","created_at":"2026-06-08T01:04:07.072121+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHF6IZ5RCMR5B6NP","created_at":"2026-06-08T01:04:07.072121+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHF6IZ5R","created_at":"2026-06-08T01:04:07.072121+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06273","citing_title":"AgentTether: Graph-Guided Diagnosis and Runtime Intervention for Reliable LLM Agent Operation","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ","json":"https://pith.science/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ.json","graph_json":"https://pith.science/api/pith-number/UHF6IZ5RCMR5B6NPRQU4FA7KQQ/graph.json","events_json":"https://pith.science/api/pith-number/UHF6IZ5RCMR5B6NPRQU4FA7KQQ/events.json","paper":"https://pith.science/paper/UHF6IZ5R"},"agent_actions":{"view_html":"https://pith.science/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ","download_json":"https://pith.science/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ.json","view_paper":"https://pith.science/paper/UHF6IZ5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.08717&json=true","fetch_graph":"https://pith.science/api/pith-number/UHF6IZ5RCMR5B6NPRQU4FA7KQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UHF6IZ5RCMR5B6NPRQU4FA7KQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ/action/storage_attestation","attest_author":"https://pith.science/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ/action/author_attestation","sign_citation":"https://pith.science/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ/action/citation_signature","submit_replication":"https://pith.science/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ/action/replication_record"}},"created_at":"2026-06-08T01:04:07.072121+00:00","updated_at":"2026-06-08T01:04:07.072121+00:00"}