{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YDR4FNFU3VBT7K44KZP72C3RY3","short_pith_number":"pith:YDR4FNFU","schema_version":"1.0","canonical_sha256":"c0e3c2b4b4dd433fab9c565ffd0b71c6ee2cf78f505bfb7538dba9aee774811a","source":{"kind":"arxiv","id":"2605.08786","version":2},"attestation_state":"computed","paper":{"title":"PRIM: Meta-Learned Bayesian Root Cause Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"PRIM frames root cause analysis as Bayesian inference over a synthetic prior of causal models to enable fast zero-shot detection of distributional changes.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amadou Ba, Anish Dhir, Bradley Eck, Christopher Lohse, Jonas Wahl, Marco Ruffini","submitted_at":"2026-05-09T08:14:09Z","abstract_excerpt":"Root cause analysis (RCA) in complex systems is challenging due to error propagation across multiple variables, the need for structural causal knowledge, and the computational cost of inference at test time. We introduce PRIM (Prior-fitted Root cause Identification with Meta-learning), a causal meta-learning approach that frames RCA as a Bayesian inference task over a synthetic prior of causal models. By marginalising out structural uncertainty, PRIM implicitly identifies changes in the data-generating mechanism between baseline and anomalous periods. In doing so, PRIM infers distributional di"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.08786","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-09T08:14:09Z","cross_cats_sorted":[],"title_canon_sha256":"aa7eac8c29da22b031aa061f0c79cf3b566c23223ad051f0b6752485dd174d16","abstract_canon_sha256":"2881d97db176c55651176b3318e1daa4c4f953dea28b5460274bdd5c0ce6b8bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:41.580511Z","signature_b64":"ToSqH0ngJZSzpVjU+3ikfzJcx2d+r0MwYEOXVSKi925bZUywypHJRd9nVs4tmmEWSKMk5SMp5WKvBd1kI94FAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0e3c2b4b4dd433fab9c565ffd0b71c6ee2cf78f505bfb7538dba9aee774811a","last_reissued_at":"2026-05-20T00:00:41.579771Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:41.579771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PRIM: Meta-Learned Bayesian Root Cause Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"PRIM frames root cause analysis as Bayesian inference over a synthetic prior of causal models to enable fast zero-shot detection of distributional changes.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amadou Ba, Anish Dhir, Bradley Eck, Christopher Lohse, Jonas Wahl, Marco Ruffini","submitted_at":"2026-05-09T08:14:09Z","abstract_excerpt":"Root cause analysis (RCA) in complex systems is challenging due to error propagation across multiple variables, the need for structural causal knowledge, and the computational cost of inference at test time. We introduce PRIM (Prior-fitted Root cause Identification with Meta-learning), a causal meta-learning approach that frames RCA as a Bayesian inference task over a synthetic prior of causal models. By marginalising out structural uncertainty, PRIM implicitly identifies changes in the data-generating mechanism between baseline and anomalous periods. In doing so, PRIM infers distributional di"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"PRIM infers distributional differences without explicit statistical testing, and implicitly learns causal structure without model fitting at test time, enabling zero-shot inference in 17 ms for systems with up to 100 variables.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The synthetic prior of causal models used for meta-training is sufficiently representative of the structural and distributional properties of the target real-world systems (PetShop, CausRCA, and similar domains).","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PRIM is a meta-learned Bayesian RCA method that marginalizes structural uncertainty via a MACE transformer neural process for zero-shot inference on systems up to 100 variables.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"PRIM frames root cause analysis as Bayesian inference over a synthetic prior of causal models to enable fast zero-shot detection of distributional changes.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"86fabef7406290a477402536a5b8fab54c2fe04f925d40e9619172b7f588312e"},"source":{"id":"2605.08786","kind":"arxiv","version":2},"verdict":{"id":"bfef6a34-1070-47ed-8ebd-4b6d417bf45f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T17:50:16.290914Z","strongest_claim":"PRIM infers distributional differences without explicit statistical testing, and implicitly learns causal structure without model fitting at test time, enabling zero-shot inference in 17 ms for systems with up to 100 variables.","one_line_summary":"PRIM is a meta-learned Bayesian RCA method that marginalizes structural uncertainty via a MACE transformer neural process for zero-shot inference on systems up to 100 variables.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The synthetic prior of causal models used for meta-training is sufficiently representative of the structural and distributional properties of the target real-world systems (PetShop, CausRCA, and similar domains).","pith_extraction_headline":"PRIM frames root cause analysis as Bayesian inference over a synthetic prior of causal models to enable fast zero-shot detection of distributional changes."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.08786/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:34:34.751780Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T14:01:22.089275Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T10:49:12.562521Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"8da1f62bc8bc3af5eec7855cdb090092c0fb86d712f0dc3d5dbee65c9d8766b6"},"references":{"count":56,"sample":[{"doi":"","year":2024,"title":"Bruinsma, and Richard E","work_id":"492ff4ec-1bc3-47ae-9302-70558d42eead","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2004,"title":"Causal chain analysis and root causes: the giwa approach","work_id":"7a01f480-289c-4e21-bb41-19f3699fd828","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Why did the dis- tribution change? InInternational Conference on Artificial Intelligence and Statistics, pages 1666–1674","work_id":"cee19ea2-295c-4c83-8137-373c76e4e037","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Causal structure- based root cause analysis of outliers","work_id":"db1d9533-1fd0-48b8-95e4-7da9e0603116","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"Causeinfer: Automatic and distributed performance diagnosis with hierarchical causality graph in large distributed systems","work_id":"2a05288f-5f30-4415-a5c5-881b9ea8f290","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":56,"snapshot_sha256":"2fa46a1fb8f0d336dec7b07e8ad446f45cdbbfd0696f7f5ebacd48d4db3d5f1c","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"3f485fd1251937c019497137926599c78bc7fbf424f77affe6e3d9d3b9d845c8"},"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":"2605.08786","created_at":"2026-05-20T00:00:41.579864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.08786v2","created_at":"2026-05-20T00:00:41.579864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.08786","created_at":"2026-05-20T00:00:41.579864+00:00"},{"alias_kind":"pith_short_12","alias_value":"YDR4FNFU3VBT","created_at":"2026-05-20T00:00:41.579864+00:00"},{"alias_kind":"pith_short_16","alias_value":"YDR4FNFU3VBT7K44","created_at":"2026-05-20T00:00:41.579864+00:00"},{"alias_kind":"pith_short_8","alias_value":"YDR4FNFU","created_at":"2026-05-20T00:00:41.579864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YDR4FNFU3VBT7K44KZP72C3RY3","json":"https://pith.science/pith/YDR4FNFU3VBT7K44KZP72C3RY3.json","graph_json":"https://pith.science/api/pith-number/YDR4FNFU3VBT7K44KZP72C3RY3/graph.json","events_json":"https://pith.science/api/pith-number/YDR4FNFU3VBT7K44KZP72C3RY3/events.json","paper":"https://pith.science/paper/YDR4FNFU"},"agent_actions":{"view_html":"https://pith.science/pith/YDR4FNFU3VBT7K44KZP72C3RY3","download_json":"https://pith.science/pith/YDR4FNFU3VBT7K44KZP72C3RY3.json","view_paper":"https://pith.science/paper/YDR4FNFU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.08786&json=true","fetch_graph":"https://pith.science/api/pith-number/YDR4FNFU3VBT7K44KZP72C3RY3/graph.json","fetch_events":"https://pith.science/api/pith-number/YDR4FNFU3VBT7K44KZP72C3RY3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YDR4FNFU3VBT7K44KZP72C3RY3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YDR4FNFU3VBT7K44KZP72C3RY3/action/storage_attestation","attest_author":"https://pith.science/pith/YDR4FNFU3VBT7K44KZP72C3RY3/action/author_attestation","sign_citation":"https://pith.science/pith/YDR4FNFU3VBT7K44KZP72C3RY3/action/citation_signature","submit_replication":"https://pith.science/pith/YDR4FNFU3VBT7K44KZP72C3RY3/action/replication_record"}},"created_at":"2026-05-20T00:00:41.579864+00:00","updated_at":"2026-05-20T00:00:41.579864+00:00"}