{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BDGTJBZ3PMITRVBMWJC3IXQKUV","short_pith_number":"pith:BDGTJBZ3","schema_version":"1.0","canonical_sha256":"08cd34873b7b1138d42cb245b45e0aa5723e66db820698df5d4b78518f7bcb54","source":{"kind":"arxiv","id":"2405.13867","version":2},"attestation_state":"computed","paper":{"title":"Scaling-laws for Large Time-series Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin D. Wandelt, James Alvey, Justin Alsing, Nam H. Nguyen, Thomas D. P. Edwards","submitted_at":"2024-05-22T17:48:17Z","abstract_excerpt":"Scaling laws for large language models (LLMs) have provided useful guidance in training ever larger models for predictable performance gains. Time series forecasting shares a similar sequential structure to language, and is amenable to large-scale transformer architectures. Here we show that foundational decoder-only time series transformer models exhibit analogous scaling-behavior to LLMs, with architectural details (aspect ratio and number of heads) having a minimal effect over broad ranges. We assemble a large corpus of heterogenous time series data on which to train, and establish for the "},"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":"2405.13867","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T17:48:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4d711647754b4fe30f80e277aeb95fde921093c601f64d88c961bee440d2bc70","abstract_canon_sha256":"247df4f156963b584e349cd7db85d4b78150d28915ca4724af39de699e0f5f7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:20.824817Z","signature_b64":"Js5NdZpw7wcnjnUAtIa6x0d+aiRShZNGM7MfFL3k6noONL00eCJCZ7uxYMPnVkUZzMudjJPNNas9nLGO/Dx7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08cd34873b7b1138d42cb245b45e0aa5723e66db820698df5d4b78518f7bcb54","last_reissued_at":"2026-07-05T09:58:20.824354Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:20.824354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling-laws for Large Time-series Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin D. Wandelt, James Alvey, Justin Alsing, Nam H. Nguyen, Thomas D. P. Edwards","submitted_at":"2024-05-22T17:48:17Z","abstract_excerpt":"Scaling laws for large language models (LLMs) have provided useful guidance in training ever larger models for predictable performance gains. Time series forecasting shares a similar sequential structure to language, and is amenable to large-scale transformer architectures. Here we show that foundational decoder-only time series transformer models exhibit analogous scaling-behavior to LLMs, with architectural details (aspect ratio and number of heads) having a minimal effect over broad ranges. We assemble a large corpus of heterogenous time series data on which to train, and establish for the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13867","kind":"arxiv","version":2},"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/2405.13867/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":"2405.13867","created_at":"2026-07-05T09:58:20.824409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13867v2","created_at":"2026-07-05T09:58:20.824409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13867","created_at":"2026-07-05T09:58:20.824409+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDGTJBZ3PMIT","created_at":"2026-07-05T09:58:20.824409+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDGTJBZ3PMITRVBM","created_at":"2026-07-05T09:58:20.824409+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDGTJBZ3","created_at":"2026-07-05T09:58:20.824409+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25986","citing_title":"The Inference-Compute Frontier and a Latency-Efficient Architecture for Limit Order Book Prediction","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07546","citing_title":"On the Invariance and Generality of Neural Scaling Laws","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BDGTJBZ3PMITRVBMWJC3IXQKUV","json":"https://pith.science/pith/BDGTJBZ3PMITRVBMWJC3IXQKUV.json","graph_json":"https://pith.science/api/pith-number/BDGTJBZ3PMITRVBMWJC3IXQKUV/graph.json","events_json":"https://pith.science/api/pith-number/BDGTJBZ3PMITRVBMWJC3IXQKUV/events.json","paper":"https://pith.science/paper/BDGTJBZ3"},"agent_actions":{"view_html":"https://pith.science/pith/BDGTJBZ3PMITRVBMWJC3IXQKUV","download_json":"https://pith.science/pith/BDGTJBZ3PMITRVBMWJC3IXQKUV.json","view_paper":"https://pith.science/paper/BDGTJBZ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13867&json=true","fetch_graph":"https://pith.science/api/pith-number/BDGTJBZ3PMITRVBMWJC3IXQKUV/graph.json","fetch_events":"https://pith.science/api/pith-number/BDGTJBZ3PMITRVBMWJC3IXQKUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDGTJBZ3PMITRVBMWJC3IXQKUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDGTJBZ3PMITRVBMWJC3IXQKUV/action/storage_attestation","attest_author":"https://pith.science/pith/BDGTJBZ3PMITRVBMWJC3IXQKUV/action/author_attestation","sign_citation":"https://pith.science/pith/BDGTJBZ3PMITRVBMWJC3IXQKUV/action/citation_signature","submit_replication":"https://pith.science/pith/BDGTJBZ3PMITRVBMWJC3IXQKUV/action/replication_record"}},"created_at":"2026-07-05T09:58:20.824409+00:00","updated_at":"2026-07-05T09:58:20.824409+00:00"}