{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DDAUHVGGFGTEMX7JERESPQSBIP","short_pith_number":"pith:DDAUHVGG","schema_version":"1.0","canonical_sha256":"18c143d4c629a6465fe9244927c24143c2ff36ab1bf4a038f09837fbed758632","source":{"kind":"arxiv","id":"2307.03756","version":3},"attestation_state":"computed","paper":{"title":"FITS: Modeling Time Series with $10k$ Parameters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ailing Zeng, Qiang Xu, Zhijian Xu","submitted_at":"2023-07-06T15:01:58Z","abstract_excerpt":"In this paper, we introduce FITS, a lightweight yet powerful model for time series analysis. Unlike existing models that directly process raw time-domain data, FITS operates on the principle that time series can be manipulated through interpolation in the complex frequency domain. By discarding high-frequency components with negligible impact on time series data, FITS achieves performance comparable to state-of-the-art models for time series forecasting and anomaly detection tasks, while having a remarkably compact size of only approximately $10k$ parameters. Such a lightweight model can be ea"},"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":"2307.03756","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-06T15:01:58Z","cross_cats_sorted":[],"title_canon_sha256":"188ada026f0f5df140a64c5e31ac91eb5381c148e10dd32a1533c05ff544798c","abstract_canon_sha256":"d60f95ec83da609b25da40e3a898e6654bb314452578cbcf216a6d412849609d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:30:20.127559Z","signature_b64":"MrSjRQDHtq6W/ALT7AEdq2mcTovYFvmjWinhZJ9loberfNI+U9TUdRfJr02/+IFjL60HRGxgalGlkachJrvLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18c143d4c629a6465fe9244927c24143c2ff36ab1bf4a038f09837fbed758632","last_reissued_at":"2026-07-05T07:30:20.127135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:30:20.127135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FITS: Modeling Time Series with $10k$ Parameters","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ailing Zeng, Qiang Xu, Zhijian Xu","submitted_at":"2023-07-06T15:01:58Z","abstract_excerpt":"In this paper, we introduce FITS, a lightweight yet powerful model for time series analysis. Unlike existing models that directly process raw time-domain data, FITS operates on the principle that time series can be manipulated through interpolation in the complex frequency domain. By discarding high-frequency components with negligible impact on time series data, FITS achieves performance comparable to state-of-the-art models for time series forecasting and anomaly detection tasks, while having a remarkably compact size of only approximately $10k$ parameters. Such a lightweight model can be ea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03756","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/2307.03756/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":"2307.03756","created_at":"2026-07-05T07:30:20.127190+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.03756v3","created_at":"2026-07-05T07:30:20.127190+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03756","created_at":"2026-07-05T07:30:20.127190+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDAUHVGGFGTE","created_at":"2026-07-05T07:30:20.127190+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDAUHVGGFGTEMX7J","created_at":"2026-07-05T07:30:20.127190+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDAUHVGG","created_at":"2026-07-05T07:30:20.127190+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06796","citing_title":"Enhancing deep learning models for time series classification via knowledge distillation","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00431","citing_title":"Timesynth: A Temporal Fidelity Framework for Health Signal Digital Twins","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15105","citing_title":"Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2407.13278","citing_title":"Deep Time Series Models: A Comprehensive Survey and Benchmark","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22086","citing_title":"GenHAR: Generalizing Cross-domain Human Activity Recognition for Last-mile Delivery","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15774","citing_title":"Time Series Forecasting Through the Lens of Dynamics","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23597","citing_title":"Characteristic Root Analysis and Regularization for Linear Time Series Forecasting","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14551","citing_title":"SeesawNet: Towards Non-stationary Time Series Forecasting with Balanced Modeling of Common and Specific Dependencies","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DDAUHVGGFGTEMX7JERESPQSBIP","json":"https://pith.science/pith/DDAUHVGGFGTEMX7JERESPQSBIP.json","graph_json":"https://pith.science/api/pith-number/DDAUHVGGFGTEMX7JERESPQSBIP/graph.json","events_json":"https://pith.science/api/pith-number/DDAUHVGGFGTEMX7JERESPQSBIP/events.json","paper":"https://pith.science/paper/DDAUHVGG"},"agent_actions":{"view_html":"https://pith.science/pith/DDAUHVGGFGTEMX7JERESPQSBIP","download_json":"https://pith.science/pith/DDAUHVGGFGTEMX7JERESPQSBIP.json","view_paper":"https://pith.science/paper/DDAUHVGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.03756&json=true","fetch_graph":"https://pith.science/api/pith-number/DDAUHVGGFGTEMX7JERESPQSBIP/graph.json","fetch_events":"https://pith.science/api/pith-number/DDAUHVGGFGTEMX7JERESPQSBIP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDAUHVGGFGTEMX7JERESPQSBIP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDAUHVGGFGTEMX7JERESPQSBIP/action/storage_attestation","attest_author":"https://pith.science/pith/DDAUHVGGFGTEMX7JERESPQSBIP/action/author_attestation","sign_citation":"https://pith.science/pith/DDAUHVGGFGTEMX7JERESPQSBIP/action/citation_signature","submit_replication":"https://pith.science/pith/DDAUHVGGFGTEMX7JERESPQSBIP/action/replication_record"}},"created_at":"2026-07-05T07:30:20.127190+00:00","updated_at":"2026-07-05T07:30:20.127190+00:00"}