{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V2ETR2PULDCHLF5DJ3UVC7PLKO","short_pith_number":"pith:V2ETR2PU","schema_version":"1.0","canonical_sha256":"ae8938e9f458c47597a34ee9517deb53ad096d692acd257b6383fead074b59e9","source":{"kind":"arxiv","id":"2505.04163","version":1},"attestation_state":"computed","paper":{"title":"Retrieval Augmented Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Jinsung Yoon, Meeyoung Cha, Sercan O Arik, Seungeon Lee, Sungwon Han","submitted_at":"2025-05-07T06:26:11Z","abstract_excerpt":"Time series forecasting uses historical data to predict future trends, leveraging the relationships between past observations and available features. In this paper, we propose RAFT, a retrieval-augmented time series forecasting method to provide sufficient inductive biases and complement the model's learning capacity. When forecasting the subsequent time frames, we directly retrieve historical data candidates from the training dataset with patterns most similar to the input, and utilize the future values of these candidates alongside the inputs to obtain predictions. This simple approach augme"},"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":"2505.04163","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-07T06:26:11Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"630ea20d9d528f671940dbdaf23d908a1931aa67c94cce59b52138f56be1155d","abstract_canon_sha256":"becbf72b81921ed8eae5dc770514627dbbe91a6f44036baf3b769ea5d572c2ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:37.684218Z","signature_b64":"yJ03PS8kb/RWckJ3dxPvlKi0IHv5oBbyGeFbUoipgXmCMbOIQ1jq7mGv/xGQtkpHd0Mzs0zfPsU0yLaOJUkECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae8938e9f458c47597a34ee9517deb53ad096d692acd257b6383fead074b59e9","last_reissued_at":"2026-07-05T10:59:37.683646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:37.683646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval Augmented Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Jinsung Yoon, Meeyoung Cha, Sercan O Arik, Seungeon Lee, Sungwon Han","submitted_at":"2025-05-07T06:26:11Z","abstract_excerpt":"Time series forecasting uses historical data to predict future trends, leveraging the relationships between past observations and available features. In this paper, we propose RAFT, a retrieval-augmented time series forecasting method to provide sufficient inductive biases and complement the model's learning capacity. When forecasting the subsequent time frames, we directly retrieve historical data candidates from the training dataset with patterns most similar to the input, and utilize the future values of these candidates alongside the inputs to obtain predictions. This simple approach augme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04163","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/2505.04163/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":"2505.04163","created_at":"2026-07-05T10:59:37.683711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.04163v1","created_at":"2026-07-05T10:59:37.683711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04163","created_at":"2026-07-05T10:59:37.683711+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2ETR2PULDCH","created_at":"2026-07-05T10:59:37.683711+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2ETR2PULDCHLF5D","created_at":"2026-07-05T10:59:37.683711+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2ETR2PU","created_at":"2026-07-05T10:59:37.683711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08857","citing_title":"RareCP: Regime-Aware Retrieval for Efficient Conformal Prediction","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V2ETR2PULDCHLF5DJ3UVC7PLKO","json":"https://pith.science/pith/V2ETR2PULDCHLF5DJ3UVC7PLKO.json","graph_json":"https://pith.science/api/pith-number/V2ETR2PULDCHLF5DJ3UVC7PLKO/graph.json","events_json":"https://pith.science/api/pith-number/V2ETR2PULDCHLF5DJ3UVC7PLKO/events.json","paper":"https://pith.science/paper/V2ETR2PU"},"agent_actions":{"view_html":"https://pith.science/pith/V2ETR2PULDCHLF5DJ3UVC7PLKO","download_json":"https://pith.science/pith/V2ETR2PULDCHLF5DJ3UVC7PLKO.json","view_paper":"https://pith.science/paper/V2ETR2PU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.04163&json=true","fetch_graph":"https://pith.science/api/pith-number/V2ETR2PULDCHLF5DJ3UVC7PLKO/graph.json","fetch_events":"https://pith.science/api/pith-number/V2ETR2PULDCHLF5DJ3UVC7PLKO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2ETR2PULDCHLF5DJ3UVC7PLKO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2ETR2PULDCHLF5DJ3UVC7PLKO/action/storage_attestation","attest_author":"https://pith.science/pith/V2ETR2PULDCHLF5DJ3UVC7PLKO/action/author_attestation","sign_citation":"https://pith.science/pith/V2ETR2PULDCHLF5DJ3UVC7PLKO/action/citation_signature","submit_replication":"https://pith.science/pith/V2ETR2PULDCHLF5DJ3UVC7PLKO/action/replication_record"}},"created_at":"2026-07-05T10:59:37.683711+00:00","updated_at":"2026-07-05T10:59:37.683711+00:00"}