{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FHXQPRZWEJHN3QNPDPLALAC5B4","short_pith_number":"pith:FHXQPRZW","schema_version":"1.0","canonical_sha256":"29ef07c736224eddc1af1bd605805d0f21ff488a1d31d2fa04079d856bbf9313","source":{"kind":"arxiv","id":"2608.13262","version":1},"attestation_state":"computed","paper":{"title":"Into the ORBIT for Time Series: Training Regimes for Foundation Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hongjie Xia, Peiyuan Liu, Yiding Liu, Yifan Hu, Zewei Dong","submitted_at":"2026-08-13T14:00:39Z","abstract_excerpt":"Time series foundation models (TSFMs) have advanced primarily through architectural innovation, while training regimes for large-scale heterogeneous corpora remain under-explored. As a result, pre-training distributions are often poorly controlled with respect to domain imbalance, context requirements, prediction horizons, and missingness. We introduce ORBIT (Omni-Range Bootstrap Incremental Training), a training paradigm that makes this distribution explicit and controllable. ORBIT combines Bootstrap Multi-Level Sampling, which controls dataset exposure and samples records, target variables, "},"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":"2608.13262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-13T14:00:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d5201413d7406bded0b32db38cbe88c128d637eca07c3008a681eaeac90033ed","abstract_canon_sha256":"a9f4b1e0d03bde237f968d2c4b97c1c93209772f376473b1a83a78765750f8bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T01:00:48.286873Z","signature_b64":"istb6iYjC37xd/wKiLw6iMVseahvVaAz6w9Fo0GjT4xoMKeeOlD1rpVfw4CIuk0QNsg13Kf9Pt9zHt609wgjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29ef07c736224eddc1af1bd605805d0f21ff488a1d31d2fa04079d856bbf9313","last_reissued_at":"2026-08-14T01:00:48.284751Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T01:00:48.284751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Into the ORBIT for Time Series: Training Regimes for Foundation Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hongjie Xia, Peiyuan Liu, Yiding Liu, Yifan Hu, Zewei Dong","submitted_at":"2026-08-13T14:00:39Z","abstract_excerpt":"Time series foundation models (TSFMs) have advanced primarily through architectural innovation, while training regimes for large-scale heterogeneous corpora remain under-explored. As a result, pre-training distributions are often poorly controlled with respect to domain imbalance, context requirements, prediction horizons, and missingness. We introduce ORBIT (Omni-Range Bootstrap Incremental Training), a training paradigm that makes this distribution explicit and controllable. ORBIT combines Bootstrap Multi-Level Sampling, which controls dataset exposure and samples records, target variables, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.13262","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/2608.13262/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":"2608.13262","created_at":"2026-08-14T01:00:48.285753+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.13262v1","created_at":"2026-08-14T01:00:48.285753+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.13262","created_at":"2026-08-14T01:00:48.285753+00:00"},{"alias_kind":"pith_short_12","alias_value":"FHXQPRZWEJHN","created_at":"2026-08-14T01:00:48.285753+00:00"},{"alias_kind":"pith_short_16","alias_value":"FHXQPRZWEJHN3QNP","created_at":"2026-08-14T01:00:48.285753+00:00"},{"alias_kind":"pith_short_8","alias_value":"FHXQPRZW","created_at":"2026-08-14T01:00:48.285753+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/FHXQPRZWEJHN3QNPDPLALAC5B4","json":"https://pith.science/pith/FHXQPRZWEJHN3QNPDPLALAC5B4.json","graph_json":"https://pith.science/api/pith-number/FHXQPRZWEJHN3QNPDPLALAC5B4/graph.json","events_json":"https://pith.science/api/pith-number/FHXQPRZWEJHN3QNPDPLALAC5B4/events.json","paper":"https://pith.science/paper/FHXQPRZW"},"agent_actions":{"view_html":"https://pith.science/pith/FHXQPRZWEJHN3QNPDPLALAC5B4","download_json":"https://pith.science/pith/FHXQPRZWEJHN3QNPDPLALAC5B4.json","view_paper":"https://pith.science/paper/FHXQPRZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.13262&json=true","fetch_graph":"https://pith.science/api/pith-number/FHXQPRZWEJHN3QNPDPLALAC5B4/graph.json","fetch_events":"https://pith.science/api/pith-number/FHXQPRZWEJHN3QNPDPLALAC5B4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FHXQPRZWEJHN3QNPDPLALAC5B4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FHXQPRZWEJHN3QNPDPLALAC5B4/action/storage_attestation","attest_author":"https://pith.science/pith/FHXQPRZWEJHN3QNPDPLALAC5B4/action/author_attestation","sign_citation":"https://pith.science/pith/FHXQPRZWEJHN3QNPDPLALAC5B4/action/citation_signature","submit_replication":"https://pith.science/pith/FHXQPRZWEJHN3QNPDPLALAC5B4/action/replication_record"}},"created_at":"2026-08-14T01:00:48.285753+00:00","updated_at":"2026-08-14T01:00:48.285753+00:00"}