{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZF22ISFATGUSSMBL6UXDIXFR2B","short_pith_number":"pith:ZF22ISFA","schema_version":"1.0","canonical_sha256":"c975a448a099a929302bf52e345cb1d0715d2a964896182cbf3737d718d7cb7b","source":{"kind":"arxiv","id":"2309.05833","version":3},"attestation_state":"computed","paper":{"title":"PACE-LM: Prompting and Augmentation for Calibrated Confidence Estimation with GPT-4 in Cloud Incident Root Cause Analysis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Chetan Bansal, Dylan Zhang, Pedro Las-Casas, Rodrigo Fonseca, Saravan Rajmohan, Xuchao Zhang","submitted_at":"2023-09-11T21:24:00Z","abstract_excerpt":"Major cloud providers have employed advanced AI-based solutions like large language models to aid humans in identifying the root causes of cloud incidents. Despite the growing prevalence of AI-driven assistants in the root cause analysis process, their effectiveness in assisting on-call engineers is constrained by low accuracy due to the intrinsic difficulty of the task, a propensity for LLM-based approaches to hallucinate, and difficulties in distinguishing these well-disguised hallucinations. To address this challenge, we propose to perform confidence estimation for the predictions to help o"},"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":"2309.05833","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T21:24:00Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SE"],"title_canon_sha256":"ec707f09f031e3017b597cbfeea9c5a37bdecd1c6acc6b02f6d3575fd16cedef","abstract_canon_sha256":"d24dc7014c0b4f9944b3fb649cb3b6c7dc25908fe46373e8a10f99c70f8e0701"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:55:40.505858Z","signature_b64":"yPW0d/5eEtP2JNuqEl4s6X0AwL88iNt+KSUeMYkdnAp49hlzXMr9msylE8Fgg44RaLdz1O1bX1pAPclmnEbsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c975a448a099a929302bf52e345cb1d0715d2a964896182cbf3737d718d7cb7b","last_reissued_at":"2026-07-05T06:55:40.505399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:55:40.505399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PACE-LM: Prompting and Augmentation for Calibrated Confidence Estimation with GPT-4 in Cloud Incident Root Cause Analysis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Chetan Bansal, Dylan Zhang, Pedro Las-Casas, Rodrigo Fonseca, Saravan Rajmohan, Xuchao Zhang","submitted_at":"2023-09-11T21:24:00Z","abstract_excerpt":"Major cloud providers have employed advanced AI-based solutions like large language models to aid humans in identifying the root causes of cloud incidents. Despite the growing prevalence of AI-driven assistants in the root cause analysis process, their effectiveness in assisting on-call engineers is constrained by low accuracy due to the intrinsic difficulty of the task, a propensity for LLM-based approaches to hallucinate, and difficulties in distinguishing these well-disguised hallucinations. To address this challenge, we propose to perform confidence estimation for the predictions to help o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05833","kind":"arxiv","version":3},"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/2309.05833/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":"2309.05833","created_at":"2026-07-05T06:55:40.505457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.05833v3","created_at":"2026-07-05T06:55:40.505457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05833","created_at":"2026-07-05T06:55:40.505457+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZF22ISFATGUS","created_at":"2026-07-05T06:55:40.505457+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZF22ISFATGUSSMBL","created_at":"2026-07-05T06:55:40.505457+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZF22ISFA","created_at":"2026-07-05T06:55:40.505457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08717","citing_title":"Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2506.01481","citing_title":"TSGuard: Automated User-Centric Incident Diagnosis for AI Workloads in the Cloud","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06171","citing_title":"LLM-Augmented Knowledge Base Construction For Root Cause Analysis","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08717","citing_title":"Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZF22ISFATGUSSMBL6UXDIXFR2B","json":"https://pith.science/pith/ZF22ISFATGUSSMBL6UXDIXFR2B.json","graph_json":"https://pith.science/api/pith-number/ZF22ISFATGUSSMBL6UXDIXFR2B/graph.json","events_json":"https://pith.science/api/pith-number/ZF22ISFATGUSSMBL6UXDIXFR2B/events.json","paper":"https://pith.science/paper/ZF22ISFA"},"agent_actions":{"view_html":"https://pith.science/pith/ZF22ISFATGUSSMBL6UXDIXFR2B","download_json":"https://pith.science/pith/ZF22ISFATGUSSMBL6UXDIXFR2B.json","view_paper":"https://pith.science/paper/ZF22ISFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.05833&json=true","fetch_graph":"https://pith.science/api/pith-number/ZF22ISFATGUSSMBL6UXDIXFR2B/graph.json","fetch_events":"https://pith.science/api/pith-number/ZF22ISFATGUSSMBL6UXDIXFR2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZF22ISFATGUSSMBL6UXDIXFR2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZF22ISFATGUSSMBL6UXDIXFR2B/action/storage_attestation","attest_author":"https://pith.science/pith/ZF22ISFATGUSSMBL6UXDIXFR2B/action/author_attestation","sign_citation":"https://pith.science/pith/ZF22ISFATGUSSMBL6UXDIXFR2B/action/citation_signature","submit_replication":"https://pith.science/pith/ZF22ISFATGUSSMBL6UXDIXFR2B/action/replication_record"}},"created_at":"2026-07-05T06:55:40.505457+00:00","updated_at":"2026-07-05T06:55:40.505457+00:00"}