{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QLKQSZYI5IV2FL6QP4YE4PZXDH","short_pith_number":"pith:QLKQSZYI","schema_version":"1.0","canonical_sha256":"82d5096708ea2ba2afd07f304e3f3719cb808e79abc9ebcd66c628ca48cec0e3","source":{"kind":"arxiv","id":"2509.15105","version":3},"attestation_state":"computed","paper":{"title":"Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hedi Zisling, Liran Nochumsohn, Omri Azencot, Raz Marshanski","submitted_at":"2025-09-18T16:11:31Z","abstract_excerpt":"Time series forecasting (TSF) is critical in domains like energy, finance, healthcare, and logistics, requiring models that generalize across diverse datasets. Large pre-trained models such as Chronos and Time-MoE show strong zero-shot (ZS) performance but suffer from high computational costs. In this work, we introduce Super-Linear, a lightweight and scalable mixture-of-experts (MoE) model for general forecasting. It replaces deep architectures with simple frequency-specialized linear experts, trained on resampled data across multiple frequency regimes. A lightweight spectral gating mechanism"},"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":"2509.15105","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-18T16:11:31Z","cross_cats_sorted":[],"title_canon_sha256":"2dae0e41fd2ad0fa9542953b6994a6edfc504683d845111f8267f7e19d89b4c5","abstract_canon_sha256":"4c9e54a7a5dfe7d82ae163ca946bc1e057e36b5d816ddb003d88d667f1802415"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:07.220963Z","signature_b64":"uN+HSoI2oDg6IovaHCDC9rfVgijRbIkFD4kjyzHhlwR1QuJluIyh0Z4oNsl80p5D5CBVdb2Pxd3ddVJ//GJCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82d5096708ea2ba2afd07f304e3f3719cb808e79abc9ebcd66c628ca48cec0e3","last_reissued_at":"2026-05-25T02:01:07.220033Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:07.220033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hedi Zisling, Liran Nochumsohn, Omri Azencot, Raz Marshanski","submitted_at":"2025-09-18T16:11:31Z","abstract_excerpt":"Time series forecasting (TSF) is critical in domains like energy, finance, healthcare, and logistics, requiring models that generalize across diverse datasets. Large pre-trained models such as Chronos and Time-MoE show strong zero-shot (ZS) performance but suffer from high computational costs. In this work, we introduce Super-Linear, a lightweight and scalable mixture-of-experts (MoE) model for general forecasting. It replaces deep architectures with simple frequency-specialized linear experts, trained on resampled data across multiple frequency regimes. A lightweight spectral gating mechanism"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.15105","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/2509.15105/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":"2509.15105","created_at":"2026-05-25T02:01:07.220160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.15105v3","created_at":"2026-05-25T02:01:07.220160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.15105","created_at":"2026-05-25T02:01:07.220160+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLKQSZYI5IV2","created_at":"2026-05-25T02:01:07.220160+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLKQSZYI5IV2FL6Q","created_at":"2026-05-25T02:01:07.220160+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLKQSZYI","created_at":"2026-05-25T02:01:07.220160+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.18534","citing_title":"XCTFormer: Leveraging Cross-Channel and Cross-Time Dependencies for Enhanced Time-Series Analysis","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QLKQSZYI5IV2FL6QP4YE4PZXDH","json":"https://pith.science/pith/QLKQSZYI5IV2FL6QP4YE4PZXDH.json","graph_json":"https://pith.science/api/pith-number/QLKQSZYI5IV2FL6QP4YE4PZXDH/graph.json","events_json":"https://pith.science/api/pith-number/QLKQSZYI5IV2FL6QP4YE4PZXDH/events.json","paper":"https://pith.science/paper/QLKQSZYI"},"agent_actions":{"view_html":"https://pith.science/pith/QLKQSZYI5IV2FL6QP4YE4PZXDH","download_json":"https://pith.science/pith/QLKQSZYI5IV2FL6QP4YE4PZXDH.json","view_paper":"https://pith.science/paper/QLKQSZYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.15105&json=true","fetch_graph":"https://pith.science/api/pith-number/QLKQSZYI5IV2FL6QP4YE4PZXDH/graph.json","fetch_events":"https://pith.science/api/pith-number/QLKQSZYI5IV2FL6QP4YE4PZXDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLKQSZYI5IV2FL6QP4YE4PZXDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLKQSZYI5IV2FL6QP4YE4PZXDH/action/storage_attestation","attest_author":"https://pith.science/pith/QLKQSZYI5IV2FL6QP4YE4PZXDH/action/author_attestation","sign_citation":"https://pith.science/pith/QLKQSZYI5IV2FL6QP4YE4PZXDH/action/citation_signature","submit_replication":"https://pith.science/pith/QLKQSZYI5IV2FL6QP4YE4PZXDH/action/replication_record"}},"created_at":"2026-05-25T02:01:07.220160+00:00","updated_at":"2026-05-25T02:01:07.220160+00:00"}