{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QS5ZRF5ZYBUEKLTKWCX6JOKKGH","short_pith_number":"pith:QS5ZRF5Z","canonical_record":{"source":{"id":"1901.10801","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-30T13:07:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"03aac231020a284ce6f51d909fd49b0dee48b310750aa4c474a023bab67dd23b","abstract_canon_sha256":"4cd6f18457936e0dadbc39dfffb3db1f0a14ac9b48766495e16410cc95068905"},"schema_version":"1.0"},"canonical_sha256":"84bb9897b9c068452e6ab0afe4b94a31d890a8f1281582bbd21272549078a86e","source":{"kind":"arxiv","id":"1901.10801","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.10801","created_at":"2026-05-17T23:55:05Z"},{"alias_kind":"arxiv_version","alias_value":"1901.10801v1","created_at":"2026-05-17T23:55:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10801","created_at":"2026-05-17T23:55:05Z"},{"alias_kind":"pith_short_12","alias_value":"QS5ZRF5ZYBUE","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QS5ZRF5ZYBUEKLTK","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QS5ZRF5Z","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QS5ZRF5ZYBUEKLTKWCX6JOKKGH","target":"record","payload":{"canonical_record":{"source":{"id":"1901.10801","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-30T13:07:40Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"03aac231020a284ce6f51d909fd49b0dee48b310750aa4c474a023bab67dd23b","abstract_canon_sha256":"4cd6f18457936e0dadbc39dfffb3db1f0a14ac9b48766495e16410cc95068905"},"schema_version":"1.0"},"canonical_sha256":"84bb9897b9c068452e6ab0afe4b94a31d890a8f1281582bbd21272549078a86e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:05.987226Z","signature_b64":"CQ1CwC1mXUD+V3Xj5Z5qLWjk88fF6QZago56Cv0500sVK5v3S6WCb7O1vWUq9P/2An87Ky5L/qbFl9KorLkXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84bb9897b9c068452e6ab0afe4b94a31d890a8f1281582bbd21272549078a86e","last_reissued_at":"2026-05-17T23:55:05.986838Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:05.986838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.10801","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yr2DOSNVpFR5AbcFsXKRC+rVoZh52Pho8xhuH3RdE7O7X5NbxVZFIWV/UNKwV3IsfHhOvq1y1QJgIOB3ut5wBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:58:02.484980Z"},"content_sha256":"5646c1a48d3a7c760e9bf0474e7e40bc5bad66bca89373d6d5a7e349823d7f57","schema_version":"1.0","event_id":"sha256:5646c1a48d3a7c760e9bf0474e7e40bc5bad66bca89373d6d5a7e349823d7f57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QS5ZRF5ZYBUEKLTKWCX6JOKKGH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalized Tensor Models for Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ivan Oseledets, Oleksii Hrinchuk, Valentin Khrulkov","submitted_at":"2019-01-30T13:07:40Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) are very successful at solving challenging problems with sequential data. However, this observed efficiency is not yet entirely explained by theory. It is known that a certain class of multiplicative RNNs enjoys the property of depth efficiency --- a shallow network of exponentially large width is necessary to realize the same score function as computed by such an RNN. Such networks, however, are not very often applied to real life tasks. In this work, we attempt to reduce the gap between theory and practice by extending the theoretical analysis to RNNs which e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10801","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":""},"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":"2026-05-17T23:55:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fLAuvltxrPWCzPuhgQDzEuknegyRnzR9HdfqF+mFt4n4ptI/XJtCqfkbhrLmLFPaxpbF9z15nNJpZhCb6mjcAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T09:58:02.485912Z"},"content_sha256":"b314f8070be6a636eefb0a8c388f18957974fc116dc78ec8fc5a9705e6f39ef5","schema_version":"1.0","event_id":"sha256:b314f8070be6a636eefb0a8c388f18957974fc116dc78ec8fc5a9705e6f39ef5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QS5ZRF5ZYBUEKLTKWCX6JOKKGH/bundle.json","state_url":"https://pith.science/pith/QS5ZRF5ZYBUEKLTKWCX6JOKKGH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QS5ZRF5ZYBUEKLTKWCX6JOKKGH/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":"2026-08-22T09:58:02Z","links":{"resolver":"https://pith.science/pith/QS5ZRF5ZYBUEKLTKWCX6JOKKGH","bundle":"https://pith.science/pith/QS5ZRF5ZYBUEKLTKWCX6JOKKGH/bundle.json","state":"https://pith.science/pith/QS5ZRF5ZYBUEKLTKWCX6JOKKGH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QS5ZRF5ZYBUEKLTKWCX6JOKKGH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QS5ZRF5ZYBUEKLTKWCX6JOKKGH","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":"4cd6f18457936e0dadbc39dfffb3db1f0a14ac9b48766495e16410cc95068905","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-30T13:07:40Z","title_canon_sha256":"03aac231020a284ce6f51d909fd49b0dee48b310750aa4c474a023bab67dd23b"},"schema_version":"1.0","source":{"id":"1901.10801","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.10801","created_at":"2026-05-17T23:55:05Z"},{"alias_kind":"arxiv_version","alias_value":"1901.10801v1","created_at":"2026-05-17T23:55:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10801","created_at":"2026-05-17T23:55:05Z"},{"alias_kind":"pith_short_12","alias_value":"QS5ZRF5ZYBUE","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QS5ZRF5ZYBUEKLTK","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QS5ZRF5Z","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:b314f8070be6a636eefb0a8c388f18957974fc116dc78ec8fc5a9705e6f39ef5","target":"graph","created_at":"2026-05-17T23:55:05Z","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"},"paper":{"abstract_excerpt":"Recurrent Neural Networks (RNNs) are very successful at solving challenging problems with sequential data. However, this observed efficiency is not yet entirely explained by theory. It is known that a certain class of multiplicative RNNs enjoys the property of depth efficiency --- a shallow network of exponentially large width is necessary to realize the same score function as computed by such an RNN. Such networks, however, are not very often applied to real life tasks. In this work, we attempt to reduce the gap between theory and practice by extending the theoretical analysis to RNNs which e","authors_text":"Ivan Oseledets, Oleksii Hrinchuk, Valentin Khrulkov","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-30T13:07:40Z","title":"Generalized Tensor Models for Recurrent Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10801","kind":"arxiv","version":1},"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":"sha256:5646c1a48d3a7c760e9bf0474e7e40bc5bad66bca89373d6d5a7e349823d7f57","target":"record","created_at":"2026-05-17T23:55:05Z","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":"4cd6f18457936e0dadbc39dfffb3db1f0a14ac9b48766495e16410cc95068905","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-30T13:07:40Z","title_canon_sha256":"03aac231020a284ce6f51d909fd49b0dee48b310750aa4c474a023bab67dd23b"},"schema_version":"1.0","source":{"id":"1901.10801","kind":"arxiv","version":1}},"canonical_sha256":"84bb9897b9c068452e6ab0afe4b94a31d890a8f1281582bbd21272549078a86e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84bb9897b9c068452e6ab0afe4b94a31d890a8f1281582bbd21272549078a86e","first_computed_at":"2026-05-17T23:55:05.986838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:05.986838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CQ1CwC1mXUD+V3Xj5Z5qLWjk88fF6QZago56Cv0500sVK5v3S6WCb7O1vWUq9P/2An87Ky5L/qbFl9KorLkXDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:05.987226Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.10801","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5646c1a48d3a7c760e9bf0474e7e40bc5bad66bca89373d6d5a7e349823d7f57","sha256:b314f8070be6a636eefb0a8c388f18957974fc116dc78ec8fc5a9705e6f39ef5"],"state_sha256":"2622a456a694e179325fb1841ca17e644400007d1fd66cfec0bda997ea881f50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y8lYnlGjH85Qil1mWC2Z0AovgJDJ5tgFNNYiwBUTVfi62vzNy0mTRFDZXpvt+n8dP+2VP5O/vsWHeeJ1k6BHAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T09:58:02.490825Z","bundle_sha256":"92e2ada6d3347e875fc39c462d7854512479da6995c44cc5a413dc2ae9e927e0"}}