{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3EG7EJT33XME2HL6VGN2PFY2PN","short_pith_number":"pith:3EG7EJT3","schema_version":"1.0","canonical_sha256":"d90df2267bddd84d1d7ea99ba7971a7b5f95162f2c997574c6fdf98f21bddcec","source":{"kind":"arxiv","id":"2506.12953","version":1},"attestation_state":"computed","paper":{"title":"Forecasting Time Series with LLMs via Patch-Based Prompting and Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Anish Gupta, An La, Anshul Vemulapalli, Franck Dernoncourt, Hongjie Chen, Mayank Bumb, Nesreen K. Ahmed, Ryan A. Rossi, Sri Harsha Vardhan Prasad Jella, Yu Wang","submitted_at":"2025-06-15T19:42:58Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have demonstrated new possibilities for accurate and efficient time series analysis, but prior work often required heavy fine-tuning and/or ignored inter-series correlations. In this work, we explore simple and flexible prompt-based strategies that enable LLMs to perform time series forecasting without extensive retraining or the use of a complex external architecture. Through the exploration of specialized prompting methods that leverage time series decomposition, patch-based tokenization, and similarity-based neighbor augmentation, we find that"},"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":"2506.12953","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-15T19:42:58Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"41118846186f505aee320994b1823d01abdf0388376589b462e4715451bece46","abstract_canon_sha256":"c0d1f8a8bd6d918e13e454efc10c9ffe8f57c25855b6e2218e7f90e54a51da2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:02.883763Z","signature_b64":"3DQOCI+s+ECaQrUL6kFcazaPpHP3Jq5wSFU9ZpJAQkCXqJifxVKhehRXLHTPgMoaN7FdeO9JFJSTwHD120nhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d90df2267bddd84d1d7ea99ba7971a7b5f95162f2c997574c6fdf98f21bddcec","last_reissued_at":"2026-07-05T11:22:02.883210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:02.883210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Forecasting Time Series with LLMs via Patch-Based Prompting and Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Anish Gupta, An La, Anshul Vemulapalli, Franck Dernoncourt, Hongjie Chen, Mayank Bumb, Nesreen K. Ahmed, Ryan A. Rossi, Sri Harsha Vardhan Prasad Jella, Yu Wang","submitted_at":"2025-06-15T19:42:58Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have demonstrated new possibilities for accurate and efficient time series analysis, but prior work often required heavy fine-tuning and/or ignored inter-series correlations. In this work, we explore simple and flexible prompt-based strategies that enable LLMs to perform time series forecasting without extensive retraining or the use of a complex external architecture. Through the exploration of specialized prompting methods that leverage time series decomposition, patch-based tokenization, and similarity-based neighbor augmentation, we find that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.12953","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/2506.12953/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":"2506.12953","created_at":"2026-07-05T11:22:02.883267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.12953v1","created_at":"2026-07-05T11:22:02.883267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.12953","created_at":"2026-07-05T11:22:02.883267+00:00"},{"alias_kind":"pith_short_12","alias_value":"3EG7EJT33XME","created_at":"2026-07-05T11:22:02.883267+00:00"},{"alias_kind":"pith_short_16","alias_value":"3EG7EJT33XME2HL6","created_at":"2026-07-05T11:22:02.883267+00:00"},{"alias_kind":"pith_short_8","alias_value":"3EG7EJT3","created_at":"2026-07-05T11:22:02.883267+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/3EG7EJT33XME2HL6VGN2PFY2PN","json":"https://pith.science/pith/3EG7EJT33XME2HL6VGN2PFY2PN.json","graph_json":"https://pith.science/api/pith-number/3EG7EJT33XME2HL6VGN2PFY2PN/graph.json","events_json":"https://pith.science/api/pith-number/3EG7EJT33XME2HL6VGN2PFY2PN/events.json","paper":"https://pith.science/paper/3EG7EJT3"},"agent_actions":{"view_html":"https://pith.science/pith/3EG7EJT33XME2HL6VGN2PFY2PN","download_json":"https://pith.science/pith/3EG7EJT33XME2HL6VGN2PFY2PN.json","view_paper":"https://pith.science/paper/3EG7EJT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.12953&json=true","fetch_graph":"https://pith.science/api/pith-number/3EG7EJT33XME2HL6VGN2PFY2PN/graph.json","fetch_events":"https://pith.science/api/pith-number/3EG7EJT33XME2HL6VGN2PFY2PN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3EG7EJT33XME2HL6VGN2PFY2PN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3EG7EJT33XME2HL6VGN2PFY2PN/action/storage_attestation","attest_author":"https://pith.science/pith/3EG7EJT33XME2HL6VGN2PFY2PN/action/author_attestation","sign_citation":"https://pith.science/pith/3EG7EJT33XME2HL6VGN2PFY2PN/action/citation_signature","submit_replication":"https://pith.science/pith/3EG7EJT33XME2HL6VGN2PFY2PN/action/replication_record"}},"created_at":"2026-07-05T11:22:02.883267+00:00","updated_at":"2026-07-05T11:22:02.883267+00:00"}