{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:47DFXKCZ3BSUUEH3KGULSMQH4I","short_pith_number":"pith:47DFXKCZ","schema_version":"1.0","canonical_sha256":"e7c65ba859d8654a10fb51a8b93207e20632497a55f1a183dd34097afb60940e","source":{"kind":"arxiv","id":"2608.05571","version":1},"attestation_state":"computed","paper":{"title":"Align-RAG: Alignment Is All You Need for TSFM In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Bardiya Akhbari, Ehsan Adeli, Euan Ashley, Jack W. O'Sullivan, Layne C. Price, Mohammad Asadi, Raviteja Anantha, Soheil Hor, Tahoura Nedaee","submitted_at":"2026-08-06T03:43:45Z","abstract_excerpt":"Retrieval-augmented forecasting promises to adapt frozen Time Series Foundation Models (TSFMs) to new domains without fine-tuning, but recent methods typically rely on learned fusion modules, i.e., trained adapters that merge retrieved examples into the backbone's forecast, based on the assumption that frozen backbones cannot dynamically incorporate retrieved context on their own. We show this assumption is unnecessary. We introduce Align-RAG, a training-free method that applies a closed-form per-pair amplitude rescaling and integer-lag phase shift to retrieved past-future windows before they "},"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":"2608.05571","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T03:43:45Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"e17577cfcfb878700ad9613a5ad4c3f2135a53ed43a19cddd5bcf2b577ed762d","abstract_canon_sha256":"2d4974ce366b65d0d0b5d05495c36deb49f9d9738fd0c08a231f567378bb77e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:49:44.540909Z","signature_b64":"mKkVD2TQ0eggqIjnEGKayw0RCcbXbxiPKq4GmEp6mK/tt9pYUP976WgIJ9R2RJdT/Ndx9kFB7f0sCLcLTTTnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7c65ba859d8654a10fb51a8b93207e20632497a55f1a183dd34097afb60940e","last_reissued_at":"2026-08-07T00:49:44.539395Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:49:44.539395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Align-RAG: Alignment Is All You Need for TSFM In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.LG","authors_text":"Bardiya Akhbari, Ehsan Adeli, Euan Ashley, Jack W. O'Sullivan, Layne C. Price, Mohammad Asadi, Raviteja Anantha, Soheil Hor, Tahoura Nedaee","submitted_at":"2026-08-06T03:43:45Z","abstract_excerpt":"Retrieval-augmented forecasting promises to adapt frozen Time Series Foundation Models (TSFMs) to new domains without fine-tuning, but recent methods typically rely on learned fusion modules, i.e., trained adapters that merge retrieved examples into the backbone's forecast, based on the assumption that frozen backbones cannot dynamically incorporate retrieved context on their own. We show this assumption is unnecessary. We introduce Align-RAG, a training-free method that applies a closed-form per-pair amplitude rescaling and integer-lag phase shift to retrieved past-future windows before they "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05571","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/2608.05571/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":"2608.05571","created_at":"2026-08-07T00:49:44.540879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05571v1","created_at":"2026-08-07T00:49:44.540879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05571","created_at":"2026-08-07T00:49:44.540879+00:00"},{"alias_kind":"pith_short_12","alias_value":"47DFXKCZ3BSU","created_at":"2026-08-07T00:49:44.540879+00:00"},{"alias_kind":"pith_short_16","alias_value":"47DFXKCZ3BSUUEH3","created_at":"2026-08-07T00:49:44.540879+00:00"},{"alias_kind":"pith_short_8","alias_value":"47DFXKCZ","created_at":"2026-08-07T00:49:44.540879+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/47DFXKCZ3BSUUEH3KGULSMQH4I","json":"https://pith.science/pith/47DFXKCZ3BSUUEH3KGULSMQH4I.json","graph_json":"https://pith.science/api/pith-number/47DFXKCZ3BSUUEH3KGULSMQH4I/graph.json","events_json":"https://pith.science/api/pith-number/47DFXKCZ3BSUUEH3KGULSMQH4I/events.json","paper":"https://pith.science/paper/47DFXKCZ"},"agent_actions":{"view_html":"https://pith.science/pith/47DFXKCZ3BSUUEH3KGULSMQH4I","download_json":"https://pith.science/pith/47DFXKCZ3BSUUEH3KGULSMQH4I.json","view_paper":"https://pith.science/paper/47DFXKCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05571&json=true","fetch_graph":"https://pith.science/api/pith-number/47DFXKCZ3BSUUEH3KGULSMQH4I/graph.json","fetch_events":"https://pith.science/api/pith-number/47DFXKCZ3BSUUEH3KGULSMQH4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47DFXKCZ3BSUUEH3KGULSMQH4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47DFXKCZ3BSUUEH3KGULSMQH4I/action/storage_attestation","attest_author":"https://pith.science/pith/47DFXKCZ3BSUUEH3KGULSMQH4I/action/author_attestation","sign_citation":"https://pith.science/pith/47DFXKCZ3BSUUEH3KGULSMQH4I/action/citation_signature","submit_replication":"https://pith.science/pith/47DFXKCZ3BSUUEH3KGULSMQH4I/action/replication_record"}},"created_at":"2026-08-07T00:49:44.540879+00:00","updated_at":"2026-08-07T00:49:44.540879+00:00"}