{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HUWRTDXL6USLK6BTBZJEH3MKQP","short_pith_number":"pith:HUWRTDXL","schema_version":"1.0","canonical_sha256":"3d2d198eebf524b578330e5243ed8a83d1222cac27de296e3a3cc2157dbe3a6c","source":{"kind":"arxiv","id":"2106.09305","version":3},"attestation_state":"computed","paper":{"title":"SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ailing Zeng, Lingna Ma, Minhao Liu, Muxi Chen, Qiang Xu, Qiuxia Lai, Zhijian Xu","submitted_at":"2021-06-17T08:15:04Z","abstract_excerpt":"One unique property of time series is that the temporal relations are largely preserved after downsampling into two sub-sequences. By taking advantage of this property, we propose a novel neural network architecture that conducts sample convolution and interaction for temporal modeling and forecasting, named SCINet. Specifically, SCINet is a recursive downsample-convolve-interact architecture. In each layer, we use multiple convolutional filters to extract distinct yet valuable temporal features from the downsampled sub-sequences or features. By combining these rich features aggregated from mu"},"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":"2106.09305","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T08:15:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"89f679decb2cf4d49d6b6881dd53a3763254baa5209d62656058c5d0cc87c3a9","abstract_canon_sha256":"762e89434adaf26159b20c119228caa0ffcde12b6cdf7a5fcbbcf35a7008134a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:07.837257Z","signature_b64":"hzeIewJNXwk/jh2V/H+QgPH0mrAFhQMaRIFIPSdVgt5wh/iqGF1zrJB6ckYxwoDzI9okYkgXELpgSC2+IwDmDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d2d198eebf524b578330e5243ed8a83d1222cac27de296e3a3cc2157dbe3a6c","last_reissued_at":"2026-07-05T05:06:07.836712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:07.836712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ailing Zeng, Lingna Ma, Minhao Liu, Muxi Chen, Qiang Xu, Qiuxia Lai, Zhijian Xu","submitted_at":"2021-06-17T08:15:04Z","abstract_excerpt":"One unique property of time series is that the temporal relations are largely preserved after downsampling into two sub-sequences. By taking advantage of this property, we propose a novel neural network architecture that conducts sample convolution and interaction for temporal modeling and forecasting, named SCINet. Specifically, SCINet is a recursive downsample-convolve-interact architecture. In each layer, we use multiple convolutional filters to extract distinct yet valuable temporal features from the downsampled sub-sequences or features. By combining these rich features aggregated from mu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09305","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/2106.09305/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":"2106.09305","created_at":"2026-07-05T05:06:07.836782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09305v3","created_at":"2026-07-05T05:06:07.836782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09305","created_at":"2026-07-05T05:06:07.836782+00:00"},{"alias_kind":"pith_short_12","alias_value":"HUWRTDXL6USL","created_at":"2026-07-05T05:06:07.836782+00:00"},{"alias_kind":"pith_short_16","alias_value":"HUWRTDXL6USLK6BT","created_at":"2026-07-05T05:06:07.836782+00:00"},{"alias_kind":"pith_short_8","alias_value":"HUWRTDXL","created_at":"2026-07-05T05:06:07.836782+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08234","citing_title":"RhyMix: A Lightweight Adaptive Multi-Rhythm Network for Long-Term Time Series Forecasting","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HUWRTDXL6USLK6BTBZJEH3MKQP","json":"https://pith.science/pith/HUWRTDXL6USLK6BTBZJEH3MKQP.json","graph_json":"https://pith.science/api/pith-number/HUWRTDXL6USLK6BTBZJEH3MKQP/graph.json","events_json":"https://pith.science/api/pith-number/HUWRTDXL6USLK6BTBZJEH3MKQP/events.json","paper":"https://pith.science/paper/HUWRTDXL"},"agent_actions":{"view_html":"https://pith.science/pith/HUWRTDXL6USLK6BTBZJEH3MKQP","download_json":"https://pith.science/pith/HUWRTDXL6USLK6BTBZJEH3MKQP.json","view_paper":"https://pith.science/paper/HUWRTDXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09305&json=true","fetch_graph":"https://pith.science/api/pith-number/HUWRTDXL6USLK6BTBZJEH3MKQP/graph.json","fetch_events":"https://pith.science/api/pith-number/HUWRTDXL6USLK6BTBZJEH3MKQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HUWRTDXL6USLK6BTBZJEH3MKQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HUWRTDXL6USLK6BTBZJEH3MKQP/action/storage_attestation","attest_author":"https://pith.science/pith/HUWRTDXL6USLK6BTBZJEH3MKQP/action/author_attestation","sign_citation":"https://pith.science/pith/HUWRTDXL6USLK6BTBZJEH3MKQP/action/citation_signature","submit_replication":"https://pith.science/pith/HUWRTDXL6USLK6BTBZJEH3MKQP/action/replication_record"}},"created_at":"2026-07-05T05:06:07.836782+00:00","updated_at":"2026-07-05T05:06:07.836782+00:00"}