{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6DU6TX27EWYQEUUJF3S7WMRBR2","short_pith_number":"pith:6DU6TX27","schema_version":"1.0","canonical_sha256":"f0e9e9df5f25b10252892ee5fb32218ebce95d71351df5f2c1903d3563a3fe54","source":{"kind":"arxiv","id":"1907.00235","version":3},"attestation_state":"computed","paper":{"title":"Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Shiyang Li, Wenhu Chen, Xiaoyong Jin, Xifeng Yan, Xiyou Zhou, Yao Xuan, Yu-Xiang Wang","submitted_at":"2019-06-29T16:36:04Z","abstract_excerpt":"Time series forecasting is an important problem across many domains, including predictions of solar plant energy output, electricity consumption, and traffic jam situation. In this paper, we propose to tackle such forecasting problem with Transformer [1]. Although impressed by its performance in our preliminary study, we found its two major weaknesses: (1) locality-agnostics: the point-wise dot-product self-attention in canonical Transformer architecture is insensitive to local context, which can make the model prone to anomalies in time series; (2) memory bottleneck: space complexity of canon"},"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":"1907.00235","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-29T16:36:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9638b863bc81485c92ac7e73c030b6e7982b0b2dd5014a4d0c5d93577fbcb7ae","abstract_canon_sha256":"4081787c4a9fa40179306d452c4b3d58fe31aca518f630a1bc4ce85277253d42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:29:28.431258Z","signature_b64":"reyHpaDhNKLYyYdepKi6wkIb0fL3Rn4ye+vG98v1WY6AMEyZV52X0eEPcs6prjwnvKMydiqycjUy16DCbinkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0e9e9df5f25b10252892ee5fb32218ebce95d71351df5f2c1903d3563a3fe54","last_reissued_at":"2026-07-05T00:29:28.430766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:29:28.430766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Shiyang Li, Wenhu Chen, Xiaoyong Jin, Xifeng Yan, Xiyou Zhou, Yao Xuan, Yu-Xiang Wang","submitted_at":"2019-06-29T16:36:04Z","abstract_excerpt":"Time series forecasting is an important problem across many domains, including predictions of solar plant energy output, electricity consumption, and traffic jam situation. In this paper, we propose to tackle such forecasting problem with Transformer [1]. Although impressed by its performance in our preliminary study, we found its two major weaknesses: (1) locality-agnostics: the point-wise dot-product self-attention in canonical Transformer architecture is insensitive to local context, which can make the model prone to anomalies in time series; (2) memory bottleneck: space complexity of canon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00235","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/1907.00235/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":"1907.00235","created_at":"2026-07-05T00:29:28.430826+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.00235v3","created_at":"2026-07-05T00:29:28.430826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00235","created_at":"2026-07-05T00:29:28.430826+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DU6TX27EWYQ","created_at":"2026-07-05T00:29:28.430826+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DU6TX27EWYQEUUJ","created_at":"2026-07-05T00:29:28.430826+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DU6TX27","created_at":"2026-07-05T00:29:28.430826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09498","citing_title":"Spectral Transformer Neural Processes","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DU6TX27EWYQEUUJF3S7WMRBR2","json":"https://pith.science/pith/6DU6TX27EWYQEUUJF3S7WMRBR2.json","graph_json":"https://pith.science/api/pith-number/6DU6TX27EWYQEUUJF3S7WMRBR2/graph.json","events_json":"https://pith.science/api/pith-number/6DU6TX27EWYQEUUJF3S7WMRBR2/events.json","paper":"https://pith.science/paper/6DU6TX27"},"agent_actions":{"view_html":"https://pith.science/pith/6DU6TX27EWYQEUUJF3S7WMRBR2","download_json":"https://pith.science/pith/6DU6TX27EWYQEUUJF3S7WMRBR2.json","view_paper":"https://pith.science/paper/6DU6TX27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.00235&json=true","fetch_graph":"https://pith.science/api/pith-number/6DU6TX27EWYQEUUJF3S7WMRBR2/graph.json","fetch_events":"https://pith.science/api/pith-number/6DU6TX27EWYQEUUJF3S7WMRBR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DU6TX27EWYQEUUJF3S7WMRBR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DU6TX27EWYQEUUJF3S7WMRBR2/action/storage_attestation","attest_author":"https://pith.science/pith/6DU6TX27EWYQEUUJF3S7WMRBR2/action/author_attestation","sign_citation":"https://pith.science/pith/6DU6TX27EWYQEUUJF3S7WMRBR2/action/citation_signature","submit_replication":"https://pith.science/pith/6DU6TX27EWYQEUUJF3S7WMRBR2/action/replication_record"}},"created_at":"2026-07-05T00:29:28.430826+00:00","updated_at":"2026-07-05T00:29:28.430826+00:00"}