{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZFCIC2ZLTGK4EXBDZEXADNN4ZJ","short_pith_number":"pith:ZFCIC2ZL","schema_version":"1.0","canonical_sha256":"c944816b2b9995c25c23c92e01b5bcca5080a7c84d484c18d52bdee73ff65fa7","source":{"kind":"arxiv","id":"2103.14438","version":1},"attestation_state":"computed","paper":{"title":"Gated Transformer Networks for Multivariate Time Series Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiahui Jiao, Minghao Liu, Shengqi Ren, Siyuan Ma, Wei Song, Yizhou Chen, Zhiguang Wang","submitted_at":"2021-03-26T12:43:32Z","abstract_excerpt":"Deep learning model (primarily convolutional networks and LSTM) for time series classification has been studied broadly by the community with the wide applications in different domains like healthcare, finance, industrial engineering and IoT. Meanwhile, Transformer Networks recently achieved frontier performance on various natural language processing and computer vision tasks. In this work, we explored a simple extension of the current Transformer Networks with gating, named Gated Transformer Networks (GTN) for the multivariate time series classification problem. With the gating that merges tw"},"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":"2103.14438","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-26T12:43:32Z","cross_cats_sorted":[],"title_canon_sha256":"1f660f7dbe0dcfaf9db8a34f8543f38ac4d82533130d5953c6b33109ef8f069b","abstract_canon_sha256":"137e2ad5e1429bab6ae316fa0a59dbac3216e2b64750cd86f78146a5d72752d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:33.792062Z","signature_b64":"zcM57p9aAjU6OeHY1wvkHblrx9EHL3jDVt2/zmlD7Q5p8yZVC2goU0v/HghNEAo6zKVSJ7p5EBLMm6bmyXC7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c944816b2b9995c25c23c92e01b5bcca5080a7c84d484c18d52bdee73ff65fa7","last_reissued_at":"2026-07-05T02:26:33.791651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:33.791651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gated Transformer Networks for Multivariate Time Series Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiahui Jiao, Minghao Liu, Shengqi Ren, Siyuan Ma, Wei Song, Yizhou Chen, Zhiguang Wang","submitted_at":"2021-03-26T12:43:32Z","abstract_excerpt":"Deep learning model (primarily convolutional networks and LSTM) for time series classification has been studied broadly by the community with the wide applications in different domains like healthcare, finance, industrial engineering and IoT. Meanwhile, Transformer Networks recently achieved frontier performance on various natural language processing and computer vision tasks. In this work, we explored a simple extension of the current Transformer Networks with gating, named Gated Transformer Networks (GTN) for the multivariate time series classification problem. With the gating that merges tw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.14438","kind":"arxiv","version":1},"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/2103.14438/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":"2103.14438","created_at":"2026-07-05T02:26:33.791710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.14438v1","created_at":"2026-07-05T02:26:33.791710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.14438","created_at":"2026-07-05T02:26:33.791710+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFCIC2ZLTGK4","created_at":"2026-07-05T02:26:33.791710+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFCIC2ZLTGK4EXBD","created_at":"2026-07-05T02:26:33.791710+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFCIC2ZL","created_at":"2026-07-05T02:26:33.791710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00081","citing_title":"DAStatFormer: A Hybrid Multibranch Transformer with Statistical Feature Integration for DAS-Based Pattern Recognitions","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2502.12370","citing_title":"Positional Encoding in Transformer-Based Time Series Models: A Survey","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22086","citing_title":"GenHAR: Generalizing Cross-domain Human Activity Recognition for Last-mile Delivery","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20275","citing_title":"You Don't Need Attention: Gated Convolutional Modeling for Watch-Based Fall Detection","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.14640","citing_title":"DyWPE: Signal-Aware Dynamic Wavelet Positional Encoding for Time Series Transformers","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFCIC2ZLTGK4EXBDZEXADNN4ZJ","json":"https://pith.science/pith/ZFCIC2ZLTGK4EXBDZEXADNN4ZJ.json","graph_json":"https://pith.science/api/pith-number/ZFCIC2ZLTGK4EXBDZEXADNN4ZJ/graph.json","events_json":"https://pith.science/api/pith-number/ZFCIC2ZLTGK4EXBDZEXADNN4ZJ/events.json","paper":"https://pith.science/paper/ZFCIC2ZL"},"agent_actions":{"view_html":"https://pith.science/pith/ZFCIC2ZLTGK4EXBDZEXADNN4ZJ","download_json":"https://pith.science/pith/ZFCIC2ZLTGK4EXBDZEXADNN4ZJ.json","view_paper":"https://pith.science/paper/ZFCIC2ZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.14438&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFCIC2ZLTGK4EXBDZEXADNN4ZJ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFCIC2ZLTGK4EXBDZEXADNN4ZJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFCIC2ZLTGK4EXBDZEXADNN4ZJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFCIC2ZLTGK4EXBDZEXADNN4ZJ/action/storage_attestation","attest_author":"https://pith.science/pith/ZFCIC2ZLTGK4EXBDZEXADNN4ZJ/action/author_attestation","sign_citation":"https://pith.science/pith/ZFCIC2ZLTGK4EXBDZEXADNN4ZJ/action/citation_signature","submit_replication":"https://pith.science/pith/ZFCIC2ZLTGK4EXBDZEXADNN4ZJ/action/replication_record"}},"created_at":"2026-07-05T02:26:33.791710+00:00","updated_at":"2026-07-05T02:26:33.791710+00:00"}