{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UHF6IZ5RCMR5B6NPRQU4FA7KQQ","short_pith_number":"pith:UHF6IZ5R","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"},"canonical_sha256":"a1cbe467b11323d0f9af8c29c283ea840c6b9511fa49994e64054388c3eb3841","source":{"kind":"arxiv","id":"2605.08717","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08717","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08717v2","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08717","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"pith_short_12","alias_value":"UHF6IZ5RCMR5","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"pith_short_16","alias_value":"UHF6IZ5RCMR5B6NP","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"pith_short_8","alias_value":"UHF6IZ5R","created_at":"2026-06-08T01:04:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UHF6IZ5RCMR5B6NPRQU4FA7KQQ","target":"record","payload":{"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"},"canonical_sha256":"a1cbe467b11323d0f9af8c29c283ea840c6b9511fa49994e64054388c3eb3841","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"},"source_kind":"arxiv","source_id":"2605.08717","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:04:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c1BwxFzNM24ciI6tK4BI1cWqwppGBpBZKKN9wCyWzXAoBqgR4CPBmQNhuuttQ7RPuS73GoSyqruYZ4kUMo1WDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T06:54:56.138334Z"},"content_sha256":"371a55a1af2832f9de9ce34304a9be164720a2f43b495ee442b19cb0e1d56722","schema_version":"1.0","event_id":"sha256:371a55a1af2832f9de9ce34304a9be164720a2f43b495ee442b19cb0e1d56722"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UHF6IZ5RCMR5B6NPRQU4FA7KQQ","target":"graph","payload":{"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"},"verdict_id":"dcd092c8-14ed-4f8f-b3d1-123d325dbb7c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:04:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PY2jqJohenlVO7j1R/PrvV2Q3715m98P4ctYkHimou6NMpArZqcYe/Qparc5OVGNfQzmQyKMHoZae13UY5UlCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T06:54:56.139253Z"},"content_sha256":"31bf2ee805729b47a6f1ede34c2ff5ebeb868d84f7e38d64de4dce59f4a605de","schema_version":"1.0","event_id":"sha256:31bf2ee805729b47a6f1ede34c2ff5ebeb868d84f7e38d64de4dce59f4a605de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ/bundle.json","state_url":"https://pith.science/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-12T06:54:56Z","links":{"resolver":"https://pith.science/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ","bundle":"https://pith.science/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ/bundle.json","state":"https://pith.science/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UHF6IZ5RCMR5B6NPRQU4FA7KQQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UHF6IZ5RCMR5B6NPRQU4FA7KQQ","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":"1b080022cb5a99fef2f3c76cab995cba4114931db8992531ecd03d3f9c1140c1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-05-09T06:02:08Z","title_canon_sha256":"7684fc60f87469cfd0f508d9be12c37293cd6f19c56ff84b07106587cdb61984"},"schema_version":"1.0","source":{"id":"2605.08717","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.08717","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.08717v2","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08717","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"pith_short_12","alias_value":"UHF6IZ5RCMR5","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"pith_short_16","alias_value":"UHF6IZ5RCMR5B6NP","created_at":"2026-06-08T01:04:07Z"},{"alias_kind":"pith_short_8","alias_value":"UHF6IZ5R","created_at":"2026-06-08T01:04:07Z"}],"graph_snapshots":[{"event_id":"sha256:31bf2ee805729b47a6f1ede34c2ff5ebeb868d84f7e38d64de4dce59f4a605de","target":"graph","created_at":"2026-06-08T01:04:07Z","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":"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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"PROBE converts failed-run telemetry into structured evidence, diagnosis, and bounded guidance that agents can execute without changing their policy or tools."}],"snapshot_sha256":"627c1e15d69323dc8cdb3136bdc5da9110d3ac473f22b114745f7ba2a73ea623"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d34157f3f272412b0cf310d7c7245178c2f32905a6e85fd4b11a60293b26f6b2"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.08717/integrity.json","findings":[],"snapshot_sha256":"7ac523fb323834d90cf3d678bdf5b1d59c5b5fd836d41a4fa218e367eea39870","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chenyu Zhao, Chetan Bansal, Dan Pei, Minghua Ma, Saravan Rajmohan, Shenglin Zhang, Wenwei Gu, Yihang Lin, Yongqian Sun, Zhimin Chen","cross_cats":["cs.AI"],"headline":"PROBE converts failed-run telemetry into structured evidence, diagnosis, and bounded guidance that agents can execute without changing their policy or tools.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-05-09T06:02:08Z","title":"Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.08717","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T00:59:42.570340Z","id":"dcd092c8-14ed-4f8f-b3d1-123d325dbb7c","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"dcd092c8-14ed-4f8f-b3d1-123d325dbb7c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:371a55a1af2832f9de9ce34304a9be164720a2f43b495ee442b19cb0e1d56722","target":"record","created_at":"2026-06-08T01:04:07Z","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":"1b080022cb5a99fef2f3c76cab995cba4114931db8992531ecd03d3f9c1140c1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-05-09T06:02:08Z","title_canon_sha256":"7684fc60f87469cfd0f508d9be12c37293cd6f19c56ff84b07106587cdb61984"},"schema_version":"1.0","source":{"id":"2605.08717","kind":"arxiv","version":2}},"canonical_sha256":"a1cbe467b11323d0f9af8c29c283ea840c6b9511fa49994e64054388c3eb3841","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1cbe467b11323d0f9af8c29c283ea840c6b9511fa49994e64054388c3eb3841","first_computed_at":"2026-06-08T01:04:07.071982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:07.071982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6Ek+DgDPRcjph6hErfVTj/6QAv1h2GEUvJ2u5rlWenxgGBcQarVM1IZKwyHesOOJ4znqY7b1ST+evPTpmV5KAA==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:07.072830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.08717","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:371a55a1af2832f9de9ce34304a9be164720a2f43b495ee442b19cb0e1d56722","sha256:31bf2ee805729b47a6f1ede34c2ff5ebeb868d84f7e38d64de4dce59f4a605de"],"state_sha256":"c7f2cc8ff870d2609e0e2880e8417f9a439ecc777068fee1d8d620088ef4ef4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZUse8aLKubj5CARyodpXdFnfnjIhARNd0DG8yE/PBoZLQOS6EcCOE3PjoK8YDZ1y+RoEWXbHFIjVV7IYn7u+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T06:54:56.143060Z","bundle_sha256":"b918f8bc908ac96565dcf6450fbb778ed32868c3d206c5135dd0543dc545d530"}}