{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BUEVT2BYOHIYAKSVVGBJEKXDOD","short_pith_number":"pith:BUEVT2BY","canonical_record":{"source":{"id":"1905.12080","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T20:41:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"64bd742e71aca9fa7aedc38a613a3b8dfac5b78aa9edfafe8f14d494c78aa0e0","abstract_canon_sha256":"b0985007e1dae1dea040cb5a32b3f3594b45d389d402d0f2b4f69dfd618cdce2"},"schema_version":"1.0"},"canonical_sha256":"0d0959e83871d1802a55a982922ae370d2f3b531d3e71612727ec639a81f0656","source":{"kind":"arxiv","id":"1905.12080","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12080","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12080v2","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12080","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"BUEVT2BYOHIY","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"pith_short_16","alias_value":"BUEVT2BYOHIYAKSV","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"pith_short_8","alias_value":"BUEVT2BY","created_at":"2026-07-05T00:15:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BUEVT2BYOHIYAKSVVGBJEKXDOD","target":"record","payload":{"canonical_record":{"source":{"id":"1905.12080","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T20:41:27Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"64bd742e71aca9fa7aedc38a613a3b8dfac5b78aa9edfafe8f14d494c78aa0e0","abstract_canon_sha256":"b0985007e1dae1dea040cb5a32b3f3594b45d389d402d0f2b4f69dfd618cdce2"},"schema_version":"1.0"},"canonical_sha256":"0d0959e83871d1802a55a982922ae370d2f3b531d3e71612727ec639a81f0656","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:05.426032Z","signature_b64":"rvn3VTlVcCjgm2mB2lM7UOlSCATeNTlmPO7XuiTk6NQ/g6qLpL9IYIdy7kGS+TLUFz8PXBJU6M80l1SGyZJTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d0959e83871d1802a55a982922ae370d2f3b531d3e71612727ec639a81f0656","last_reissued_at":"2026-07-05T00:15:05.425520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:05.425520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.12080","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:15:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vdW9FWlL1s/tdCJLbWKn+0QIZ6kkjZga6HDGulC4Yr5zkeoxh0z4XtD+tuG87mTX6Y1o2TQseIt93IpATnbKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:02:04.057716Z"},"content_sha256":"937332ff2f110268be36a4b045e10452c50b8782ff4b94e6dd0eb7177b3d5061","schema_version":"1.0","event_id":"sha256:937332ff2f110268be36a4b045e10452c50b8782ff4b94e6dd0eb7177b3d5061"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BUEVT2BYOHIYAKSVVGBJEKXDOD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eugene Vorontsov, Gauthier Gidel, Giancarlo Kerg, Guillaume Lajoie, Kyle Goyette, Maximilian Puelma Touzel, Yoshua Bengio","submitted_at":"2019-05-28T20:41:27Z","abstract_excerpt":"A recent strategy to circumvent the exploding and vanishing gradient problem in RNNs, and to allow the stable propagation of signals over long time scales, is to constrain recurrent connectivity matrices to be orthogonal or unitary. This ensures eigenvalues with unit norm and thus stable dynamics and training. However this comes at the cost of reduced expressivity due to the limited variety of orthogonal transformations. We propose a novel connectivity structure based on the Schur decomposition and a splitting of the Schur form into normal and non-normal parts. This allows to parametrize matri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12080","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/1905.12080/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:15:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Zdah+k5dhFzEUPh746CCxYJK0GrsyzaVchBac7N9zSPAYaT6YvJYU7sKjtHN5HD+LkPh+3uYfZLW00P0U2HCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:02:04.058693Z"},"content_sha256":"bc53707fd7ccc3e863deb4b07604f158e18be3f62c8677a6efebd339e3d06144","schema_version":"1.0","event_id":"sha256:bc53707fd7ccc3e863deb4b07604f158e18be3f62c8677a6efebd339e3d06144"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BUEVT2BYOHIYAKSVVGBJEKXDOD/bundle.json","state_url":"https://pith.science/pith/BUEVT2BYOHIYAKSVVGBJEKXDOD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BUEVT2BYOHIYAKSVVGBJEKXDOD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T23:02:04Z","links":{"resolver":"https://pith.science/pith/BUEVT2BYOHIYAKSVVGBJEKXDOD","bundle":"https://pith.science/pith/BUEVT2BYOHIYAKSVVGBJEKXDOD/bundle.json","state":"https://pith.science/pith/BUEVT2BYOHIYAKSVVGBJEKXDOD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BUEVT2BYOHIYAKSVVGBJEKXDOD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BUEVT2BYOHIYAKSVVGBJEKXDOD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b0985007e1dae1dea040cb5a32b3f3594b45d389d402d0f2b4f69dfd618cdce2","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T20:41:27Z","title_canon_sha256":"64bd742e71aca9fa7aedc38a613a3b8dfac5b78aa9edfafe8f14d494c78aa0e0"},"schema_version":"1.0","source":{"id":"1905.12080","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12080","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12080v2","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12080","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"BUEVT2BYOHIY","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"pith_short_16","alias_value":"BUEVT2BYOHIYAKSV","created_at":"2026-07-05T00:15:05Z"},{"alias_kind":"pith_short_8","alias_value":"BUEVT2BY","created_at":"2026-07-05T00:15:05Z"}],"graph_snapshots":[{"event_id":"sha256:bc53707fd7ccc3e863deb4b07604f158e18be3f62c8677a6efebd339e3d06144","target":"graph","created_at":"2026-07-05T00:15:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1905.12080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A recent strategy to circumvent the exploding and vanishing gradient problem in RNNs, and to allow the stable propagation of signals over long time scales, is to constrain recurrent connectivity matrices to be orthogonal or unitary. This ensures eigenvalues with unit norm and thus stable dynamics and training. However this comes at the cost of reduced expressivity due to the limited variety of orthogonal transformations. We propose a novel connectivity structure based on the Schur decomposition and a splitting of the Schur form into normal and non-normal parts. This allows to parametrize matri","authors_text":"Eugene Vorontsov, Gauthier Gidel, Giancarlo Kerg, Guillaume Lajoie, Kyle Goyette, Maximilian Puelma Touzel, Yoshua Bengio","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T20:41:27Z","title":"Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12080","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:937332ff2f110268be36a4b045e10452c50b8782ff4b94e6dd0eb7177b3d5061","target":"record","created_at":"2026-07-05T00:15:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b0985007e1dae1dea040cb5a32b3f3594b45d389d402d0f2b4f69dfd618cdce2","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T20:41:27Z","title_canon_sha256":"64bd742e71aca9fa7aedc38a613a3b8dfac5b78aa9edfafe8f14d494c78aa0e0"},"schema_version":"1.0","source":{"id":"1905.12080","kind":"arxiv","version":2}},"canonical_sha256":"0d0959e83871d1802a55a982922ae370d2f3b531d3e71612727ec639a81f0656","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d0959e83871d1802a55a982922ae370d2f3b531d3e71612727ec639a81f0656","first_computed_at":"2026-07-05T00:15:05.425520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:15:05.425520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rvn3VTlVcCjgm2mB2lM7UOlSCATeNTlmPO7XuiTk6NQ/g6qLpL9IYIdy7kGS+TLUFz8PXBJU6M80l1SGyZJTDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:15:05.426032Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.12080","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:937332ff2f110268be36a4b045e10452c50b8782ff4b94e6dd0eb7177b3d5061","sha256:bc53707fd7ccc3e863deb4b07604f158e18be3f62c8677a6efebd339e3d06144"],"state_sha256":"5e6d2978c94d2c2f8cde0838cd0b7e3080b113b7d4a7d2b4904e6c4172363c51"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TLLOpR0dD3XZwabuOM+k2R0eoPPqkgRBZUCpyOF50/5vGED4/e7XOmRRgUZTcQPnufrCNOCImpe905agIPCPCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:02:04.070707Z","bundle_sha256":"90313ebce22d9075211cc84e35f68802cb01a49c43ef539a8c24d3fc833894d5"}}