{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:3TTNHRO7KAE3NZIJ7BF2HQ4XJM","short_pith_number":"pith:3TTNHRO7","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"},"canonical_sha256":"dce6d3c5df5009b6e509f84ba3c3974b351bdfdf620ae1d94aff47d9061e0e7e","source":{"kind":"arxiv","id":"1612.05231","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.05231","created_at":"2026-05-18T00:47:26Z"},{"alias_kind":"arxiv_version","alias_value":"1612.05231v3","created_at":"2026-05-18T00:47:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.05231","created_at":"2026-05-18T00:47:26Z"},{"alias_kind":"pith_short_12","alias_value":"3TTNHRO7KAE3","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"3TTNHRO7KAE3NZIJ","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"3TTNHRO7","created_at":"2026-05-18T12:29:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:3TTNHRO7KAE3NZIJ7BF2HQ4XJM","target":"record","payload":{"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"},"canonical_sha256":"dce6d3c5df5009b6e509f84ba3c3974b351bdfdf620ae1d94aff47d9061e0e7e","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"},"source_kind":"arxiv","source_id":"1612.05231","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:47:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"erfo/K19eJYXl9pY0K7n/bGZa+Y0n2ohR06uYyBZN0HV2CbJRjZ7viWdekXRc7KRxh5ZL1NkkP14xapoIrhFDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:39:10.422464Z"},"content_sha256":"b5dd41a077b1c82889a58e8e4ba0e6d0397dc1b0c28ccffb3f195019f02785b1","schema_version":"1.0","event_id":"sha256:b5dd41a077b1c82889a58e8e4ba0e6d0397dc1b0c28ccffb3f195019f02785b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:3TTNHRO7KAE3NZIJ7BF2HQ4XJM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:47:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UbGkUSAfcGQEIZ0zEoAduA7egy0miB2cENSdgP7vrfiF0tsELL8zMVvP4gbYglgyKnWZV91nnHqBD+kDTjcBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T23:39:10.423138Z"},"content_sha256":"62840e99543d965aafbb2010ce053713b89639e5da53f3757e0ffd700f550424","schema_version":"1.0","event_id":"sha256:62840e99543d965aafbb2010ce053713b89639e5da53f3757e0ffd700f550424"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM/bundle.json","state_url":"https://pith.science/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM/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":"2026-05-28T23:39:10Z","links":{"resolver":"https://pith.science/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM","bundle":"https://pith.science/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM/bundle.json","state":"https://pith.science/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3TTNHRO7KAE3NZIJ7BF2HQ4XJM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:3TTNHRO7KAE3NZIJ7BF2HQ4XJM","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":"ef2e0eecb93140a7d677e28ffb8cf1a3b7f5c695472096f3a8b29cfa04370d1c","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-15T20:39:15Z","title_canon_sha256":"2c0510e07b535f98f200a84ec1dd6e38e1d9d60ef7c4709049da285076fedc30"},"schema_version":"1.0","source":{"id":"1612.05231","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.05231","created_at":"2026-05-18T00:47:26Z"},{"alias_kind":"arxiv_version","alias_value":"1612.05231v3","created_at":"2026-05-18T00:47:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.05231","created_at":"2026-05-18T00:47:26Z"},{"alias_kind":"pith_short_12","alias_value":"3TTNHRO7KAE3","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_16","alias_value":"3TTNHRO7KAE3NZIJ","created_at":"2026-05-18T12:29:58Z"},{"alias_kind":"pith_short_8","alias_value":"3TTNHRO7","created_at":"2026-05-18T12:29:58Z"}],"graph_snapshots":[{"event_id":"sha256:62840e99543d965aafbb2010ce053713b89639e5da53f3757e0ffd700f550424","target":"graph","created_at":"2026-05-18T00:47:26Z","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":"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","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","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-15T20:39:15Z","title":"Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.05231","kind":"arxiv","version":3},"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:b5dd41a077b1c82889a58e8e4ba0e6d0397dc1b0c28ccffb3f195019f02785b1","target":"record","created_at":"2026-05-18T00:47:26Z","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":"ef2e0eecb93140a7d677e28ffb8cf1a3b7f5c695472096f3a8b29cfa04370d1c","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-15T20:39:15Z","title_canon_sha256":"2c0510e07b535f98f200a84ec1dd6e38e1d9d60ef7c4709049da285076fedc30"},"schema_version":"1.0","source":{"id":"1612.05231","kind":"arxiv","version":3}},"canonical_sha256":"dce6d3c5df5009b6e509f84ba3c3974b351bdfdf620ae1d94aff47d9061e0e7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dce6d3c5df5009b6e509f84ba3c3974b351bdfdf620ae1d94aff47d9061e0e7e","first_computed_at":"2026-05-18T00:47:26.480164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:47:26.480164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/44FT8KY5XpEpGOhHVOBRp/tl93GOh7FIsEYID3lCDN2lzANh4NNE5zERIp3+8/qRKvmUd8BrbjaOni50eB6CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:47:26.481062Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.05231","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5dd41a077b1c82889a58e8e4ba0e6d0397dc1b0c28ccffb3f195019f02785b1","sha256:62840e99543d965aafbb2010ce053713b89639e5da53f3757e0ffd700f550424"],"state_sha256":"cd6f81882780bfa9c73d5bf7122c7f249e09e60ca9e9afaf06847d190b21d6ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iq8zZcWpS/74Wwl3k57NqIdntTBIvaK2+q2jXUXRlq+UauGR2cI6+6WiZ2rvjJCJ+e6r9nUQsGKW66VHvIedAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T23:39:10.428092Z","bundle_sha256":"fffa6469b5ef88a39579f2195b6ba480f647bce7bbb3be158e9982cf7bab4351"}}