{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:RZSZOROPRP447XS56YGCXLVOXZ","short_pith_number":"pith:RZSZOROP","canonical_record":{"source":{"id":"2504.09504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-13T10:07:52Z","cross_cats_sorted":[],"title_canon_sha256":"ff9b7c5520a4422180baaf2cfa9afd721962d333444160a6c9f04b7b318818a2","abstract_canon_sha256":"76c6a3e93401adb29541f3b6eb0ff3220f9b13c13a28ea02b688618d02dfc19c"},"schema_version":"1.0"},"canonical_sha256":"8e659745cf8bf9cfde5df60c2baeaebe549076bf94144f353244ee3f62bbad54","source":{"kind":"arxiv","id":"2504.09504","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09504","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09504v1","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09504","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_12","alias_value":"RZSZOROPRP44","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_16","alias_value":"RZSZOROPRP447XS5","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_8","alias_value":"RZSZOROP","created_at":"2026-07-05T10:48:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:RZSZOROPRP447XS56YGCXLVOXZ","target":"record","payload":{"canonical_record":{"source":{"id":"2504.09504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-13T10:07:52Z","cross_cats_sorted":[],"title_canon_sha256":"ff9b7c5520a4422180baaf2cfa9afd721962d333444160a6c9f04b7b318818a2","abstract_canon_sha256":"76c6a3e93401adb29541f3b6eb0ff3220f9b13c13a28ea02b688618d02dfc19c"},"schema_version":"1.0"},"canonical_sha256":"8e659745cf8bf9cfde5df60c2baeaebe549076bf94144f353244ee3f62bbad54","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:38.682994Z","signature_b64":"jJ8oQRd8lqeLAuBq3CX4D/aGw8+osxDLnWs7Wg2B2Nr5qdAl7ukzoOk8dO/g5THVDjQXi3TnphLZa2zsBy9BBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e659745cf8bf9cfde5df60c2baeaebe549076bf94144f353244ee3f62bbad54","last_reissued_at":"2026-07-05T10:48:38.682487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:38.682487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.09504","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:48:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HaxotjazNf70UgqoIbGtyX20VJbAGl2XQ6zLvFVFElNuxKWxtQwdahwE82cmcAaC919QFbAvtFA64PetR3H4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:52:35.569165Z"},"content_sha256":"afaf03878e1002c41162eb976be338eaebffdb757ebe912e3edfb323181cea09","schema_version":"1.0","event_id":"sha256:afaf03878e1002c41162eb976be338eaebffdb757ebe912e3edfb323181cea09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:RZSZOROPRP447XS56YGCXLVOXZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MADLLM: Multivariate Anomaly Detection via Pre-trained LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guokuan Li, Jianzong Wang, Jiguang Wan, Kai Lu, Wei Tao, Xiaoyang Qu","submitted_at":"2025-04-13T10:07:52Z","abstract_excerpt":"When applying pre-trained large language models (LLMs) to address anomaly detection tasks, the multivariate time series (MTS) modality of anomaly detection does not align with the text modality of LLMs. Existing methods simply transform the MTS data into multiple univariate time series sequences, which can cause many problems. This paper introduces MADLLM, a novel multivariate anomaly detection method via pre-trained LLMs. We design a new triple encoding technique to align the MTS modality with the text modality of LLMs. Specifically, this technique integrates the traditional patch embedding m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09504","kind":"arxiv","version":1},"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/2504.09504/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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:48:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KaeJStx2l1AL+dJ6Q9C/GXIYlCJZqHotNtuGxoPFf3mVj6oRFQSufByP0ShpDn4F5mJhHomhkt0K6v6lZB3bCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:52:35.569711Z"},"content_sha256":"f9ca7919bc3f8d43338fdefb3b155fc941801eaee17802a9ddf049bcbd0cdbf1","schema_version":"1.0","event_id":"sha256:f9ca7919bc3f8d43338fdefb3b155fc941801eaee17802a9ddf049bcbd0cdbf1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RZSZOROPRP447XS56YGCXLVOXZ/bundle.json","state_url":"https://pith.science/pith/RZSZOROPRP447XS56YGCXLVOXZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RZSZOROPRP447XS56YGCXLVOXZ/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":"2026-08-08T12:52:35Z","links":{"resolver":"https://pith.science/pith/RZSZOROPRP447XS56YGCXLVOXZ","bundle":"https://pith.science/pith/RZSZOROPRP447XS56YGCXLVOXZ/bundle.json","state":"https://pith.science/pith/RZSZOROPRP447XS56YGCXLVOXZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RZSZOROPRP447XS56YGCXLVOXZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RZSZOROPRP447XS56YGCXLVOXZ","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":"76c6a3e93401adb29541f3b6eb0ff3220f9b13c13a28ea02b688618d02dfc19c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-13T10:07:52Z","title_canon_sha256":"ff9b7c5520a4422180baaf2cfa9afd721962d333444160a6c9f04b7b318818a2"},"schema_version":"1.0","source":{"id":"2504.09504","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09504","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09504v1","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09504","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_12","alias_value":"RZSZOROPRP44","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_16","alias_value":"RZSZOROPRP447XS5","created_at":"2026-07-05T10:48:38Z"},{"alias_kind":"pith_short_8","alias_value":"RZSZOROP","created_at":"2026-07-05T10:48:38Z"}],"graph_snapshots":[{"event_id":"sha256:f9ca7919bc3f8d43338fdefb3b155fc941801eaee17802a9ddf049bcbd0cdbf1","target":"graph","created_at":"2026-07-05T10:48:38Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2504.09504/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When applying pre-trained large language models (LLMs) to address anomaly detection tasks, the multivariate time series (MTS) modality of anomaly detection does not align with the text modality of LLMs. Existing methods simply transform the MTS data into multiple univariate time series sequences, which can cause many problems. This paper introduces MADLLM, a novel multivariate anomaly detection method via pre-trained LLMs. We design a new triple encoding technique to align the MTS modality with the text modality of LLMs. Specifically, this technique integrates the traditional patch embedding m","authors_text":"Guokuan Li, Jianzong Wang, Jiguang Wan, Kai Lu, Wei Tao, Xiaoyang Qu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-13T10:07:52Z","title":"MADLLM: Multivariate Anomaly Detection via Pre-trained LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09504","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:afaf03878e1002c41162eb976be338eaebffdb757ebe912e3edfb323181cea09","target":"record","created_at":"2026-07-05T10:48:38Z","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":"76c6a3e93401adb29541f3b6eb0ff3220f9b13c13a28ea02b688618d02dfc19c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-13T10:07:52Z","title_canon_sha256":"ff9b7c5520a4422180baaf2cfa9afd721962d333444160a6c9f04b7b318818a2"},"schema_version":"1.0","source":{"id":"2504.09504","kind":"arxiv","version":1}},"canonical_sha256":"8e659745cf8bf9cfde5df60c2baeaebe549076bf94144f353244ee3f62bbad54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e659745cf8bf9cfde5df60c2baeaebe549076bf94144f353244ee3f62bbad54","first_computed_at":"2026-07-05T10:48:38.682487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:38.682487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jJ8oQRd8lqeLAuBq3CX4D/aGw8+osxDLnWs7Wg2B2Nr5qdAl7ukzoOk8dO/g5THVDjQXi3TnphLZa2zsBy9BBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:38.682994Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.09504","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afaf03878e1002c41162eb976be338eaebffdb757ebe912e3edfb323181cea09","sha256:f9ca7919bc3f8d43338fdefb3b155fc941801eaee17802a9ddf049bcbd0cdbf1"],"state_sha256":"3a4fd9cc9e23991c585a641f77278f5aa23de8893f814c201c966e9f0c3b9464"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bhrARf3modg8pXDnuDyWxYL7XbUbYUkTxG4XvAvEcbjXuVBZ1DAfXwCMSrmr/l9zZ7QxPNfJuvEHCvrjVEI8BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:52:35.573177Z","bundle_sha256":"f3acc5ffb454fa43cf4d1a45c51e283b1e8f6592e1d07e8b71561e5049ca86d4"}}