{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZEUM43YMDE5EVCOYJ7K2RMZ5S5","short_pith_number":"pith:ZEUM43YM","schema_version":"1.0","canonical_sha256":"c928ce6f0c193a4a89d84fd5a8b33d974dfddce5a31b98fa570eb6b25e39bd04","source":{"kind":"arxiv","id":"2607.01204","version":1},"attestation_state":"computed","paper":{"title":"TiRex-2: Generalizing TiRex to Multivariate Data and Streaming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bernhard Voggenberger, Daniel Klotz, Elias B\\\"urger, G\\\"unter Klambauer, Levente Z\\'olyomi, Marco Pichler, Patrick Podest, Sebastian B\\\"ock, Sepp Hochreiter, Wilhelm Berghammer","submitted_at":"2026-07-01T17:45:04Z","abstract_excerpt":"We introduce TiRex-2, a recurrent xLSTM-based time series foundation model that generalizes the univariate TiRex to multivariate forecasting with both past and future covariates. Real-world forecasting is inherently sequential: observations arrive continuously, variables evolve jointly, and a subset of covariates is known ahead of time. Existing Transformer-based time series foundation models capture cross-variate dependencies but incur quadratic complexity in context length and require full-history recomputation as new observations arrive. TiRex-2 addresses these limitations through a memory-"},"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":"2607.01204","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T17:45:04Z","cross_cats_sorted":[],"title_canon_sha256":"18c99759be04c84fa5ced680b4eb2438b075702cde94f098b9a824533fc0d821","abstract_canon_sha256":"f49ae1a400fbf4cdf11682a1dc3605cb028a53c86121b5e9e0aea581cc7ab91f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:18:32.694083Z","signature_b64":"vJ5RSQkvgAdb8Bsp+f2XuFHKcKs0DjYvb0EdXYkX4eVaWM6PBZKwpYZGiJgFjWF26V9h5H5Up+j+arQYcjX1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c928ce6f0c193a4a89d84fd5a8b33d974dfddce5a31b98fa570eb6b25e39bd04","last_reissued_at":"2026-07-02T01:18:32.693671Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:18:32.693671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TiRex-2: Generalizing TiRex to Multivariate Data and Streaming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bernhard Voggenberger, Daniel Klotz, Elias B\\\"urger, G\\\"unter Klambauer, Levente Z\\'olyomi, Marco Pichler, Patrick Podest, Sebastian B\\\"ock, Sepp Hochreiter, Wilhelm Berghammer","submitted_at":"2026-07-01T17:45:04Z","abstract_excerpt":"We introduce TiRex-2, a recurrent xLSTM-based time series foundation model that generalizes the univariate TiRex to multivariate forecasting with both past and future covariates. Real-world forecasting is inherently sequential: observations arrive continuously, variables evolve jointly, and a subset of covariates is known ahead of time. Existing Transformer-based time series foundation models capture cross-variate dependencies but incur quadratic complexity in context length and require full-history recomputation as new observations arrive. TiRex-2 addresses these limitations through a memory-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01204","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/2607.01204/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":"2607.01204","created_at":"2026-07-02T01:18:32.693735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01204v1","created_at":"2026-07-02T01:18:32.693735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01204","created_at":"2026-07-02T01:18:32.693735+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZEUM43YMDE5E","created_at":"2026-07-02T01:18:32.693735+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZEUM43YMDE5EVCOY","created_at":"2026-07-02T01:18:32.693735+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZEUM43YM","created_at":"2026-07-02T01:18:32.693735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZEUM43YMDE5EVCOYJ7K2RMZ5S5","json":"https://pith.science/pith/ZEUM43YMDE5EVCOYJ7K2RMZ5S5.json","graph_json":"https://pith.science/api/pith-number/ZEUM43YMDE5EVCOYJ7K2RMZ5S5/graph.json","events_json":"https://pith.science/api/pith-number/ZEUM43YMDE5EVCOYJ7K2RMZ5S5/events.json","paper":"https://pith.science/paper/ZEUM43YM"},"agent_actions":{"view_html":"https://pith.science/pith/ZEUM43YMDE5EVCOYJ7K2RMZ5S5","download_json":"https://pith.science/pith/ZEUM43YMDE5EVCOYJ7K2RMZ5S5.json","view_paper":"https://pith.science/paper/ZEUM43YM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01204&json=true","fetch_graph":"https://pith.science/api/pith-number/ZEUM43YMDE5EVCOYJ7K2RMZ5S5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZEUM43YMDE5EVCOYJ7K2RMZ5S5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZEUM43YMDE5EVCOYJ7K2RMZ5S5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZEUM43YMDE5EVCOYJ7K2RMZ5S5/action/storage_attestation","attest_author":"https://pith.science/pith/ZEUM43YMDE5EVCOYJ7K2RMZ5S5/action/author_attestation","sign_citation":"https://pith.science/pith/ZEUM43YMDE5EVCOYJ7K2RMZ5S5/action/citation_signature","submit_replication":"https://pith.science/pith/ZEUM43YMDE5EVCOYJ7K2RMZ5S5/action/replication_record"}},"created_at":"2026-07-02T01:18:32.693735+00:00","updated_at":"2026-07-02T01:18:32.693735+00:00"}