{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K2T6DHKC3W4WPEI27WLDNU62B4","short_pith_number":"pith:K2T6DHKC","schema_version":"1.0","canonical_sha256":"56a7e19d42ddb967911afd9636d3da0f10aee032c96808f47b5af54ff18b438c","source":{"kind":"arxiv","id":"2502.12920","version":3},"attestation_state":"computed","paper":{"title":"Lightweight Online Adaption for Time Series Foundation Model Forecasts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Artjom Joosen, Martin Asenov, Rajkarn Singh, Thomas L. Lee, William Toner","submitted_at":"2025-02-18T15:01:02Z","abstract_excerpt":"Foundation models (FMs) have emerged as a promising approach for time series forecasting. While effective, FMs typically remain fixed during deployment due to the high computational costs of learning them online. Consequently, deployed FMs fail to adapt their forecasts to current data characteristics, despite the availability of online feedback from newly arriving data. This raises the question of whether FM performance can be enhanced by the efficient usage of this feedback. We propose ELF to answer this question. ELF is a lightweight mechanism for the online adaption of FM forecasts in respo"},"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":"2502.12920","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-18T15:01:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f4d7fd3d1aff5738d36f5877d77ff313c53261e548802d59c9a77a7c2093c345","abstract_canon_sha256":"7150f64d820717677762d2a3bee647c78722cfccc7cfdabee8598b8a155d8eb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:31.591998Z","signature_b64":"DKvj7JFNsk2Hkp0PmQriuO92JR56AmlMAFL016yor/FBMrbwmJyoMtT0810XKuI8B7gvzLINm9/GZCBMnG04Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56a7e19d42ddb967911afd9636d3da0f10aee032c96808f47b5af54ff18b438c","last_reissued_at":"2026-07-05T11:45:31.591470Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:31.591470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lightweight Online Adaption for Time Series Foundation Model Forecasts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Artjom Joosen, Martin Asenov, Rajkarn Singh, Thomas L. Lee, William Toner","submitted_at":"2025-02-18T15:01:02Z","abstract_excerpt":"Foundation models (FMs) have emerged as a promising approach for time series forecasting. While effective, FMs typically remain fixed during deployment due to the high computational costs of learning them online. Consequently, deployed FMs fail to adapt their forecasts to current data characteristics, despite the availability of online feedback from newly arriving data. This raises the question of whether FM performance can be enhanced by the efficient usage of this feedback. We propose ELF to answer this question. ELF is a lightweight mechanism for the online adaption of FM forecasts in respo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12920","kind":"arxiv","version":3},"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/2502.12920/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":"2502.12920","created_at":"2026-07-05T11:45:31.591535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12920v3","created_at":"2026-07-05T11:45:31.591535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12920","created_at":"2026-07-05T11:45:31.591535+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2T6DHKC3W4W","created_at":"2026-07-05T11:45:31.591535+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2T6DHKC3W4WPEI2","created_at":"2026-07-05T11:45:31.591535+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2T6DHKC","created_at":"2026-07-05T11:45:31.591535+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08289","citing_title":"What If We Let Forecasting Forget? A Sparse Bottleneck for Cross-Variable Dependencies","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K2T6DHKC3W4WPEI27WLDNU62B4","json":"https://pith.science/pith/K2T6DHKC3W4WPEI27WLDNU62B4.json","graph_json":"https://pith.science/api/pith-number/K2T6DHKC3W4WPEI27WLDNU62B4/graph.json","events_json":"https://pith.science/api/pith-number/K2T6DHKC3W4WPEI27WLDNU62B4/events.json","paper":"https://pith.science/paper/K2T6DHKC"},"agent_actions":{"view_html":"https://pith.science/pith/K2T6DHKC3W4WPEI27WLDNU62B4","download_json":"https://pith.science/pith/K2T6DHKC3W4WPEI27WLDNU62B4.json","view_paper":"https://pith.science/paper/K2T6DHKC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12920&json=true","fetch_graph":"https://pith.science/api/pith-number/K2T6DHKC3W4WPEI27WLDNU62B4/graph.json","fetch_events":"https://pith.science/api/pith-number/K2T6DHKC3W4WPEI27WLDNU62B4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2T6DHKC3W4WPEI27WLDNU62B4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2T6DHKC3W4WPEI27WLDNU62B4/action/storage_attestation","attest_author":"https://pith.science/pith/K2T6DHKC3W4WPEI27WLDNU62B4/action/author_attestation","sign_citation":"https://pith.science/pith/K2T6DHKC3W4WPEI27WLDNU62B4/action/citation_signature","submit_replication":"https://pith.science/pith/K2T6DHKC3W4WPEI27WLDNU62B4/action/replication_record"}},"created_at":"2026-07-05T11:45:31.591535+00:00","updated_at":"2026-07-05T11:45:31.591535+00:00"}