{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:3TTNHRO7KAE3NZIJ7BF2HQ4XJM","short_pith_number":"pith:3TTNHRO7","schema_version":"1.0","canonical_sha256":"dce6d3c5df5009b6e509f84ba3c3974b351bdfdf620ae1d94aff47d9061e0e7e","source":{"kind":"arxiv","id":"1612.05231","version":3},"attestation_state":"computed","paper":{"title":"Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"John Peurifoy, Li Jing, Marin Solja\\v{c}i\\'c, Max Tegmark, Scott Skirlo, Tena Dub\\v{c}ek, Yann LeCun, Yichen Shen","submitted_at":"2016-12-15T20:39:15Z","abstract_excerpt":"Using unitary (instead of general) matrices in artificial neural networks (ANNs) is a promising way to solve the gradient explosion/vanishing problem, as well as to enable ANNs to learn long-term correlations in the data. This approach appears particularly promising for Recurrent Neural Networks (RNNs). In this work, we present a new architecture for implementing an Efficient Unitary Neural Network (EUNNs); its main advantages can be summarized as follows. Firstly, the representation capacity of the unitary space in an EUNN is fully tunable, ranging from a subspace of SU(N) to the entire unita"},"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":"1612.05231","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-15T20:39:15Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"2c0510e07b535f98f200a84ec1dd6e38e1d9d60ef7c4709049da285076fedc30","abstract_canon_sha256":"ef2e0eecb93140a7d677e28ffb8cf1a3b7f5c695472096f3a8b29cfa04370d1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:26.481062Z","signature_b64":"/44FT8KY5XpEpGOhHVOBRp/tl93GOh7FIsEYID3lCDN2lzANh4NNE5zERIp3+8/qRKvmUd8BrbjaOni50eB6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dce6d3c5df5009b6e509f84ba3c3974b351bdfdf620ae1d94aff47d9061e0e7e","last_reissued_at":"2026-05-18T00:47:26.480164Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:26.480164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"John Peurifoy, Li Jing, Marin Solja\\v{c}i\\'c, Max Tegmark, Scott Skirlo, Tena Dub\\v{c}ek, Yann LeCun, Yichen Shen","submitted_at":"2016-12-15T20:39:15Z","abstract_excerpt":"Using unitary (instead of general) matrices in artificial neural networks (ANNs) is a promising way to solve the gradient explosion/vanishing problem, as well as to enable ANNs to learn long-term correlations in the data. This approach appears particularly promising for Recurrent Neural Networks (RNNs). In this work, we present a new architecture for implementing an Efficient Unitary Neural Network (EUNNs); its main advantages can be summarized as follows. Firstly, the representation capacity of the unitary space in an EUNN is fully tunable, ranging from a subspace of SU(N) to the entire unita"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.05231","kind":"arxiv","version":3},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1612.05231","created_at":"2026-05-18T00:47:26.480302+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.05231v3","created_at":"2026-05-18T00:47:26.480302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.05231","created_at":"2026-05-18T00:47:26.480302+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TTNHRO7KAE3","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TTNHRO7KAE3NZIJ","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TTNHRO7","created_at":"2026-05-18T12:29:58.707656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM","json":"https://pith.science/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM.json","graph_json":"https://pith.science/api/pith-number/3TTNHRO7KAE3NZIJ7BF2HQ4XJM/graph.json","events_json":"https://pith.science/api/pith-number/3TTNHRO7KAE3NZIJ7BF2HQ4XJM/events.json","paper":"https://pith.science/paper/3TTNHRO7"},"agent_actions":{"view_html":"https://pith.science/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM","download_json":"https://pith.science/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM.json","view_paper":"https://pith.science/paper/3TTNHRO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.05231&json=true","fetch_graph":"https://pith.science/api/pith-number/3TTNHRO7KAE3NZIJ7BF2HQ4XJM/graph.json","fetch_events":"https://pith.science/api/pith-number/3TTNHRO7KAE3NZIJ7BF2HQ4XJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM/action/storage_attestation","attest_author":"https://pith.science/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM/action/author_attestation","sign_citation":"https://pith.science/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM/action/citation_signature","submit_replication":"https://pith.science/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM/action/replication_record"}},"created_at":"2026-05-18T00:47:26.480302+00:00","updated_at":"2026-05-18T00:47:26.480302+00:00"}