{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BXA7XHJ6T3GUAEU5HO6BQOWRJI","short_pith_number":"pith:BXA7XHJ6","schema_version":"1.0","canonical_sha256":"0dc1fb9d3e9ecd40129d3bbc183ad14a0ec9b4821aac9b3aae11dfa659f2be53","source":{"kind":"arxiv","id":"1906.09211","version":2},"attestation_state":"computed","paper":{"title":"Universal Approximation of Input-Output Maps by Temporal Convolutional Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Joshua Hanson, Maxim Raginsky","submitted_at":"2019-06-21T15:55:43Z","abstract_excerpt":"There has been a recent shift in sequence-to-sequence modeling from recurrent network architectures to convolutional network architectures due to computational advantages in training and operation while still achieving competitive performance. For systems having limited long-term temporal dependencies, the approximation capability of recurrent networks is essentially equivalent to that of temporal convolutional nets (TCNs). We prove that TCNs can approximate a large class of input-output maps having approximately finite memory to arbitrary error tolerance. Furthermore, we derive quantitative a"},"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":"1906.09211","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T15:55:43Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC","stat.ML"],"title_canon_sha256":"a9134cb64d77f17b959e205feeedce7654b3611e593928cb63393be7a081fd28","abstract_canon_sha256":"b6bb563319e07214d39c151e4183600c9096cf1bd735d75ccc2e0fdec81c97a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:06.667857Z","signature_b64":"cm4i9ekWprbUsVyRKCtpDURzzvusVE4jBojmtn2a97lXsZFpe92QWcqs3CIF9Hfs5dF6TuSp5hQA7vUw+1SEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0dc1fb9d3e9ecd40129d3bbc183ad14a0ec9b4821aac9b3aae11dfa659f2be53","last_reissued_at":"2026-07-05T00:15:06.667391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:06.667391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Approximation of Input-Output Maps by Temporal Convolutional Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Joshua Hanson, Maxim Raginsky","submitted_at":"2019-06-21T15:55:43Z","abstract_excerpt":"There has been a recent shift in sequence-to-sequence modeling from recurrent network architectures to convolutional network architectures due to computational advantages in training and operation while still achieving competitive performance. For systems having limited long-term temporal dependencies, the approximation capability of recurrent networks is essentially equivalent to that of temporal convolutional nets (TCNs). We prove that TCNs can approximate a large class of input-output maps having approximately finite memory to arbitrary error tolerance. Furthermore, we derive quantitative a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09211","kind":"arxiv","version":2},"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/1906.09211/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":"1906.09211","created_at":"2026-07-05T00:15:06.667449+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.09211v2","created_at":"2026-07-05T00:15:06.667449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09211","created_at":"2026-07-05T00:15:06.667449+00:00"},{"alias_kind":"pith_short_12","alias_value":"BXA7XHJ6T3GU","created_at":"2026-07-05T00:15:06.667449+00:00"},{"alias_kind":"pith_short_16","alias_value":"BXA7XHJ6T3GUAEU5","created_at":"2026-07-05T00:15:06.667449+00:00"},{"alias_kind":"pith_short_8","alias_value":"BXA7XHJ6","created_at":"2026-07-05T00:15:06.667449+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.09979","citing_title":"Dissipation-induced Quantum Homogenization for Temporal Information Processing","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BXA7XHJ6T3GUAEU5HO6BQOWRJI","json":"https://pith.science/pith/BXA7XHJ6T3GUAEU5HO6BQOWRJI.json","graph_json":"https://pith.science/api/pith-number/BXA7XHJ6T3GUAEU5HO6BQOWRJI/graph.json","events_json":"https://pith.science/api/pith-number/BXA7XHJ6T3GUAEU5HO6BQOWRJI/events.json","paper":"https://pith.science/paper/BXA7XHJ6"},"agent_actions":{"view_html":"https://pith.science/pith/BXA7XHJ6T3GUAEU5HO6BQOWRJI","download_json":"https://pith.science/pith/BXA7XHJ6T3GUAEU5HO6BQOWRJI.json","view_paper":"https://pith.science/paper/BXA7XHJ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.09211&json=true","fetch_graph":"https://pith.science/api/pith-number/BXA7XHJ6T3GUAEU5HO6BQOWRJI/graph.json","fetch_events":"https://pith.science/api/pith-number/BXA7XHJ6T3GUAEU5HO6BQOWRJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BXA7XHJ6T3GUAEU5HO6BQOWRJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BXA7XHJ6T3GUAEU5HO6BQOWRJI/action/storage_attestation","attest_author":"https://pith.science/pith/BXA7XHJ6T3GUAEU5HO6BQOWRJI/action/author_attestation","sign_citation":"https://pith.science/pith/BXA7XHJ6T3GUAEU5HO6BQOWRJI/action/citation_signature","submit_replication":"https://pith.science/pith/BXA7XHJ6T3GUAEU5HO6BQOWRJI/action/replication_record"}},"created_at":"2026-07-05T00:15:06.667449+00:00","updated_at":"2026-07-05T00:15:06.667449+00:00"}