{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MRRXOV5G2TF43YH4QEQ6FDYAEL","short_pith_number":"pith:MRRXOV5G","canonical_record":{"source":{"id":"2604.17616","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-19T21:01:52Z","cross_cats_sorted":[],"title_canon_sha256":"fcaae344a18dd9eea0a6679b72da433a2696a2f9b0dfc1265027ac56a968c046","abstract_canon_sha256":"2f8ac10f413151b2e18387514a891d78445302b5d40325c67af4636034dc2244"},"schema_version":"1.0"},"canonical_sha256":"64637757a6d4cbcde0fc8121e28f0022e852a26f01b18965ac0e425ccf0415b7","source":{"kind":"arxiv","id":"2604.17616","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.17616","created_at":"2026-06-01T02:03:41Z"},{"alias_kind":"arxiv_version","alias_value":"2604.17616v2","created_at":"2026-06-01T02:03:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17616","created_at":"2026-06-01T02:03:41Z"},{"alias_kind":"pith_short_12","alias_value":"MRRXOV5G2TF4","created_at":"2026-06-01T02:03:41Z"},{"alias_kind":"pith_short_16","alias_value":"MRRXOV5G2TF43YH4","created_at":"2026-06-01T02:03:41Z"},{"alias_kind":"pith_short_8","alias_value":"MRRXOV5G","created_at":"2026-06-01T02:03:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MRRXOV5G2TF43YH4QEQ6FDYAEL","target":"record","payload":{"canonical_record":{"source":{"id":"2604.17616","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-19T21:01:52Z","cross_cats_sorted":[],"title_canon_sha256":"fcaae344a18dd9eea0a6679b72da433a2696a2f9b0dfc1265027ac56a968c046","abstract_canon_sha256":"2f8ac10f413151b2e18387514a891d78445302b5d40325c67af4636034dc2244"},"schema_version":"1.0"},"canonical_sha256":"64637757a6d4cbcde0fc8121e28f0022e852a26f01b18965ac0e425ccf0415b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T02:03:41.094074Z","signature_b64":"pQeTk09w3yH3jOLtZj9l0vhmGlTvaCYNlz+/MSRSJgmnBVBUNHNCW6K/E8f+7MITdnLsCE07tRLqNTGF5hbeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64637757a6d4cbcde0fc8121e28f0022e852a26f01b18965ac0e425ccf0415b7","last_reissued_at":"2026-06-01T02:03:41.093009Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T02:03:41.093009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.17616","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":"2026-06-01T02:03:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sz8e6d8FSagOn52RCFXucIRhTSbfEZxKOG2bI1wpV+1s4BCrb6PLW4ii2yqAdRY3TycwKhDDFoSo/EI8+5RbBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T06:39:48.076234Z"},"content_sha256":"5b1a58a6e0437e007c95de79165e36e5353926ff7d67e1fd33b7aecf731344f9","schema_version":"1.0","event_id":"sha256:5b1a58a6e0437e007c95de79165e36e5353926ff7d67e1fd33b7aecf731344f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MRRXOV5G2TF43YH4QEQ6FDYAEL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conditional Attribution for Root Cause Analysis in Time-Series Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Explaining anomalies by retrieving similar normal states in learned latent spaces yields more reliable root cause attributions for time-series data.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cedric Schockaert, Didier Stricker, Jason Rambach, Karan Patil, Shashank Mishra","submitted_at":"2026-04-19T21:01:52Z","abstract_excerpt":"Root cause analysis (RCA) for time-series anomaly detection is critical for the reliable operation of complex real-world systems. Existing explanation methods often rely on unrealistic feature perturbations and ignore temporal and cross-feature dependencies, leading to unreliable attributions. We propose a conditional attribution framework that explains anomalies relative to contextually similar normal system states. Instead of using marginal or randomly sampled baselines, our method retrieves representative normal instances conditioned on the anomalous observation, enabling dependency-preserv"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on the SWaT and MSDS benchmarks demonstrate that the proposed approach consistently improves root-cause identification accuracy, temporal localization, and robustness across multiple anomaly detection models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That retrieval of normal instances in the learned VAE latent space and UMAP manifold embeddings preserves temporal and cross-feature dependencies and yields operationally meaningful explanations without introducing out-of-distribution artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Conditional attribution retrieves contextually similar normal states from VAE latent spaces and UMAP embeddings to explain time-series anomalies while preserving dependencies, improving root-cause accuracy on SWaT and MSDS benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Explaining anomalies by retrieving similar normal states in learned latent spaces yields more reliable root cause attributions for time-series data.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0596651597054dc6d599ef723febf6d285de682888258b19b53dbc161fac488a"},"source":{"id":"2604.17616","kind":"arxiv","version":2},"verdict":{"id":"7a586e0c-1180-4bf7-8a16-e5bbda961e0b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T06:12:40.915453Z","strongest_claim":"Experiments on the SWaT and MSDS benchmarks demonstrate that the proposed approach consistently improves root-cause identification accuracy, temporal localization, and robustness across multiple anomaly detection models.","one_line_summary":"Conditional attribution retrieves contextually similar normal states from VAE latent spaces and UMAP embeddings to explain time-series anomalies while preserving dependencies, improving root-cause accuracy on SWaT and MSDS benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That retrieval of normal instances in the learned VAE latent space and UMAP manifold embeddings preserves temporal and cross-feature dependencies and yields operationally meaningful explanations without introducing out-of-distribution artifacts.","pith_extraction_headline":"Explaining anomalies by retrieving similar normal states in learned latent spaces yields more reliable root cause attributions for time-series data."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.17616/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"},"verdict_id":"7a586e0c-1180-4bf7-8a16-e5bbda961e0b"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T02:03:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oyoJ3/jRrXGK4ad++6x+DYeWjWkZYFI/THGpW2YUjOuEdQelCd2tSd4KamB+M4IP8jZ0F3tMkdT0p77BITFnAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T06:39:48.077243Z"},"content_sha256":"3a7afb8514c640346d89024881d15e4dcc454078636d1a4fef9fab2848d9aa85","schema_version":"1.0","event_id":"sha256:3a7afb8514c640346d89024881d15e4dcc454078636d1a4fef9fab2848d9aa85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MRRXOV5G2TF43YH4QEQ6FDYAEL/bundle.json","state_url":"https://pith.science/pith/MRRXOV5G2TF43YH4QEQ6FDYAEL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MRRXOV5G2TF43YH4QEQ6FDYAEL/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":"2026-06-11T06:39:48Z","links":{"resolver":"https://pith.science/pith/MRRXOV5G2TF43YH4QEQ6FDYAEL","bundle":"https://pith.science/pith/MRRXOV5G2TF43YH4QEQ6FDYAEL/bundle.json","state":"https://pith.science/pith/MRRXOV5G2TF43YH4QEQ6FDYAEL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MRRXOV5G2TF43YH4QEQ6FDYAEL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MRRXOV5G2TF43YH4QEQ6FDYAEL","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":"2f8ac10f413151b2e18387514a891d78445302b5d40325c67af4636034dc2244","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-19T21:01:52Z","title_canon_sha256":"fcaae344a18dd9eea0a6679b72da433a2696a2f9b0dfc1265027ac56a968c046"},"schema_version":"1.0","source":{"id":"2604.17616","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.17616","created_at":"2026-06-01T02:03:41Z"},{"alias_kind":"arxiv_version","alias_value":"2604.17616v2","created_at":"2026-06-01T02:03:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17616","created_at":"2026-06-01T02:03:41Z"},{"alias_kind":"pith_short_12","alias_value":"MRRXOV5G2TF4","created_at":"2026-06-01T02:03:41Z"},{"alias_kind":"pith_short_16","alias_value":"MRRXOV5G2TF43YH4","created_at":"2026-06-01T02:03:41Z"},{"alias_kind":"pith_short_8","alias_value":"MRRXOV5G","created_at":"2026-06-01T02:03:41Z"}],"graph_snapshots":[{"event_id":"sha256:3a7afb8514c640346d89024881d15e4dcc454078636d1a4fef9fab2848d9aa85","target":"graph","created_at":"2026-06-01T02:03:41Z","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":"Experiments on the SWaT and MSDS benchmarks demonstrate that the proposed approach consistently improves root-cause identification accuracy, temporal localization, and robustness across multiple anomaly detection models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That retrieval of normal instances in the learned VAE latent space and UMAP manifold embeddings preserves temporal and cross-feature dependencies and yields operationally meaningful explanations without introducing out-of-distribution artifacts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Conditional attribution retrieves contextually similar normal states from VAE latent spaces and UMAP embeddings to explain time-series anomalies while preserving dependencies, improving root-cause accuracy on SWaT and MSDS benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Explaining anomalies by retrieving similar normal states in learned latent spaces yields more reliable root cause attributions for time-series data."}],"snapshot_sha256":"0596651597054dc6d599ef723febf6d285de682888258b19b53dbc161fac488a"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.17616/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Root cause analysis (RCA) for time-series anomaly detection is critical for the reliable operation of complex real-world systems. Existing explanation methods often rely on unrealistic feature perturbations and ignore temporal and cross-feature dependencies, leading to unreliable attributions. We propose a conditional attribution framework that explains anomalies relative to contextually similar normal system states. Instead of using marginal or randomly sampled baselines, our method retrieves representative normal instances conditioned on the anomalous observation, enabling dependency-preserv","authors_text":"Cedric Schockaert, Didier Stricker, Jason Rambach, Karan Patil, Shashank Mishra","cross_cats":[],"headline":"Explaining anomalies by retrieving similar normal states in learned latent spaces yields more reliable root cause attributions for time-series data.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-19T21:01:52Z","title":"Conditional Attribution for Root Cause Analysis in Time-Series Anomaly Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.17616","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T06:12:40.915453Z","id":"7a586e0c-1180-4bf7-8a16-e5bbda961e0b","model_set":{"reader":"grok-4.3"},"one_line_summary":"Conditional attribution retrieves contextually similar normal states from VAE latent spaces and UMAP embeddings to explain time-series anomalies while preserving dependencies, improving root-cause accuracy on SWaT and MSDS benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Explaining anomalies by retrieving similar normal states in learned latent spaces yields more reliable root cause attributions for time-series data.","strongest_claim":"Experiments on the SWaT and MSDS benchmarks demonstrate that the proposed approach consistently improves root-cause identification accuracy, temporal localization, and robustness across multiple anomaly detection models.","weakest_assumption":"That retrieval of normal instances in the learned VAE latent space and UMAP manifold embeddings preserves temporal and cross-feature dependencies and yields operationally meaningful explanations without introducing out-of-distribution artifacts."}},"verdict_id":"7a586e0c-1180-4bf7-8a16-e5bbda961e0b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5b1a58a6e0437e007c95de79165e36e5353926ff7d67e1fd33b7aecf731344f9","target":"record","created_at":"2026-06-01T02:03:41Z","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":"2f8ac10f413151b2e18387514a891d78445302b5d40325c67af4636034dc2244","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-04-19T21:01:52Z","title_canon_sha256":"fcaae344a18dd9eea0a6679b72da433a2696a2f9b0dfc1265027ac56a968c046"},"schema_version":"1.0","source":{"id":"2604.17616","kind":"arxiv","version":2}},"canonical_sha256":"64637757a6d4cbcde0fc8121e28f0022e852a26f01b18965ac0e425ccf0415b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64637757a6d4cbcde0fc8121e28f0022e852a26f01b18965ac0e425ccf0415b7","first_computed_at":"2026-06-01T02:03:41.093009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T02:03:41.093009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pQeTk09w3yH3jOLtZj9l0vhmGlTvaCYNlz+/MSRSJgmnBVBUNHNCW6K/E8f+7MITdnLsCE07tRLqNTGF5hbeAg==","signature_status":"signed_v1","signed_at":"2026-06-01T02:03:41.094074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.17616","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b1a58a6e0437e007c95de79165e36e5353926ff7d67e1fd33b7aecf731344f9","sha256:3a7afb8514c640346d89024881d15e4dcc454078636d1a4fef9fab2848d9aa85"],"state_sha256":"01f38b6c63d838dd96527d37050ee2725401d8a0756ccf15041c837699941315"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dt6XX59xwD4b6/dL2gHBbJEvS8DQL3tdTH6zzEqfLSNjfwWEgNWCsw7DP1xKHDuAXDmmBMe7QhLd7MDXcGeGDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T06:39:48.081579Z","bundle_sha256":"236bc746c7617254e4cc876ef8959f156d8c6a5632c1a51339e1fd1c769ad641"}}