{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LTKKLYT3CVPP4WYJWLFKDLVIFJ","short_pith_number":"pith:LTKKLYT3","schema_version":"1.0","canonical_sha256":"5cd4a5e27b155efe5b09b2caa1aea82a626e27485edbe5e19d9d451194b35778","source":{"kind":"arxiv","id":"2007.12141","version":2},"attestation_state":"computed","paper":{"title":"Dimension reduction in recurrent networks by canonicalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","math.DS"],"primary_cat":"math.OC","authors_text":"Juan-Pablo Ortega, Lyudmila Grigoryeva","submitted_at":"2020-07-23T17:12:37Z","abstract_excerpt":"Many recurrent neural network machine learning paradigms can be formulated using state-space representations. The classical notion of canonical state-space realization is adapted in this paper to accommodate semi-infinite inputs so that it can be used as a dimension reduction tool in the recurrent networks setup. The so-called input forgetting property is identified as the key hypothesis that guarantees the existence and uniqueness (up to system isomorphisms) of canonical realizations for causal and time-invariant input/output systems with semi-infinite inputs. Additionally, the notion of opti"},"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":"2007.12141","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-07-23T17:12:37Z","cross_cats_sorted":["cs.LG","cs.NE","math.DS"],"title_canon_sha256":"a85c0bca0b4b4a4c80671243ad52ba149dfe228fafb73b35ab4060ae96ba6bfd","abstract_canon_sha256":"359c3dec9995948dfbda1782e64ddcced2800d996ebc3511a65e9a874bd9981d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:59.197968Z","signature_b64":"JBqOdcblIZHRz0w+3CBcbTFwdWgsJ9lxwnqAMUXkXKfCqTUysn9kWlnPWYNu0WyQvOVw3dDRl9AnvYh6GZP+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cd4a5e27b155efe5b09b2caa1aea82a626e27485edbe5e19d9d451194b35778","last_reissued_at":"2026-07-05T03:04:59.197561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:59.197561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dimension reduction in recurrent networks by canonicalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","math.DS"],"primary_cat":"math.OC","authors_text":"Juan-Pablo Ortega, Lyudmila Grigoryeva","submitted_at":"2020-07-23T17:12:37Z","abstract_excerpt":"Many recurrent neural network machine learning paradigms can be formulated using state-space representations. The classical notion of canonical state-space realization is adapted in this paper to accommodate semi-infinite inputs so that it can be used as a dimension reduction tool in the recurrent networks setup. The so-called input forgetting property is identified as the key hypothesis that guarantees the existence and uniqueness (up to system isomorphisms) of canonical realizations for causal and time-invariant input/output systems with semi-infinite inputs. Additionally, the notion of opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.12141","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/2007.12141/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":"2007.12141","created_at":"2026-07-05T03:04:59.197614+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.12141v2","created_at":"2026-07-05T03:04:59.197614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.12141","created_at":"2026-07-05T03:04:59.197614+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTKKLYT3CVPP","created_at":"2026-07-05T03:04:59.197614+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTKKLYT3CVPP4WYJ","created_at":"2026-07-05T03:04:59.197614+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTKKLYT3","created_at":"2026-07-05T03:04:59.197614+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.05505","citing_title":"Dynamical Archetype Analysis: Autonomous Computation","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTKKLYT3CVPP4WYJWLFKDLVIFJ","json":"https://pith.science/pith/LTKKLYT3CVPP4WYJWLFKDLVIFJ.json","graph_json":"https://pith.science/api/pith-number/LTKKLYT3CVPP4WYJWLFKDLVIFJ/graph.json","events_json":"https://pith.science/api/pith-number/LTKKLYT3CVPP4WYJWLFKDLVIFJ/events.json","paper":"https://pith.science/paper/LTKKLYT3"},"agent_actions":{"view_html":"https://pith.science/pith/LTKKLYT3CVPP4WYJWLFKDLVIFJ","download_json":"https://pith.science/pith/LTKKLYT3CVPP4WYJWLFKDLVIFJ.json","view_paper":"https://pith.science/paper/LTKKLYT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.12141&json=true","fetch_graph":"https://pith.science/api/pith-number/LTKKLYT3CVPP4WYJWLFKDLVIFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/LTKKLYT3CVPP4WYJWLFKDLVIFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTKKLYT3CVPP4WYJWLFKDLVIFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTKKLYT3CVPP4WYJWLFKDLVIFJ/action/storage_attestation","attest_author":"https://pith.science/pith/LTKKLYT3CVPP4WYJWLFKDLVIFJ/action/author_attestation","sign_citation":"https://pith.science/pith/LTKKLYT3CVPP4WYJWLFKDLVIFJ/action/citation_signature","submit_replication":"https://pith.science/pith/LTKKLYT3CVPP4WYJWLFKDLVIFJ/action/replication_record"}},"created_at":"2026-07-05T03:04:59.197614+00:00","updated_at":"2026-07-05T03:04:59.197614+00:00"}