{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:EM52TR3P44SQVH25BTAAWRBYRX","short_pith_number":"pith:EM52TR3P","canonical_record":{"source":{"id":"1509.06569","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-09-22T12:31:03Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"8b16af44cfb3754694124194a421747bd76827f4e0f629c3f94cb860f2f92cea","abstract_canon_sha256":"84b00f666b6f62f1fa6b5f86df8ff45b2fa650eda8775ac1c052c16342052a2e"},"schema_version":"1.0"},"canonical_sha256":"233ba9c76fe7250a9f5d0cc00b44388dea8492b929977ea3e704a951d86bcb88","source":{"kind":"arxiv","id":"1509.06569","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.06569","created_at":"2026-05-18T01:24:03Z"},{"alias_kind":"arxiv_version","alias_value":"1509.06569v2","created_at":"2026-05-18T01:24:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.06569","created_at":"2026-05-18T01:24:03Z"},{"alias_kind":"pith_short_12","alias_value":"EM52TR3P44SQ","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"EM52TR3P44SQVH25","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"EM52TR3P","created_at":"2026-05-18T12:29:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:EM52TR3P44SQVH25BTAAWRBYRX","target":"record","payload":{"canonical_record":{"source":{"id":"1509.06569","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-09-22T12:31:03Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"8b16af44cfb3754694124194a421747bd76827f4e0f629c3f94cb860f2f92cea","abstract_canon_sha256":"84b00f666b6f62f1fa6b5f86df8ff45b2fa650eda8775ac1c052c16342052a2e"},"schema_version":"1.0"},"canonical_sha256":"233ba9c76fe7250a9f5d0cc00b44388dea8492b929977ea3e704a951d86bcb88","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:24:03.230263Z","signature_b64":"lZ+nsbSrmy+EcNC5yp1uK/sxBgNZsbOjapxvj0kJk6+GNmzCX0rZVgw7ud7Qa9PAixegwuCnESIQEU/kv8wLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"233ba9c76fe7250a9f5d0cc00b44388dea8492b929977ea3e704a951d86bcb88","last_reissued_at":"2026-05-18T01:24:03.229469Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:24:03.229469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1509.06569","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":"2026-05-18T01:24:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/798SQHQoofhJMFsrFFzcv/amGapIFvZxvQCkd+i908spW8T+gci2VMYshrlJoNfXjxKlsjdDbFs+xefDalOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T23:06:06.181161Z"},"content_sha256":"4bf7f75797826938e042769cdea49afa270d22f9507dd391fc4c94a4c6231946","schema_version":"1.0","event_id":"sha256:4bf7f75797826938e042769cdea49afa270d22f9507dd391fc4c94a4c6231946"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:EM52TR3P44SQVH25BTAAWRBYRX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tensorizing Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Alexander Novikov, Anton Osokin, Dmitry Podoprikhin, Dmitry Vetrov","submitted_at":"2015-09-22T12:31:03Z","abstract_excerpt":"Deep neural networks currently demonstrate state-of-the-art performance in several domains. At the same time, models of this class are very demanding in terms of computational resources. In particular, a large amount of memory is required by commonly used fully-connected layers, making it hard to use the models on low-end devices and stopping the further increase of the model size. In this paper we convert the dense weight matrices of the fully-connected layers to the Tensor Train format such that the number of parameters is reduced by a huge factor and at the same time the expressive power of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.06569","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":""},"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":"2026-05-18T01:24:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LZTeHJ0njtioK7DsJHBi+Xz3+yGCAgZYrpVmTbLXoLOxf+aOdgzhozit5o9xI1rww8fIidPDrtNz5gRigU+2AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T23:06:06.181794Z"},"content_sha256":"1847dfa6a9be3cbf304ffb4d24e3827e9a0aba66d191c20c3156d436acdf9de0","schema_version":"1.0","event_id":"sha256:1847dfa6a9be3cbf304ffb4d24e3827e9a0aba66d191c20c3156d436acdf9de0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EM52TR3P44SQVH25BTAAWRBYRX/bundle.json","state_url":"https://pith.science/pith/EM52TR3P44SQVH25BTAAWRBYRX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EM52TR3P44SQVH25BTAAWRBYRX/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":"2026-05-22T23:06:06Z","links":{"resolver":"https://pith.science/pith/EM52TR3P44SQVH25BTAAWRBYRX","bundle":"https://pith.science/pith/EM52TR3P44SQVH25BTAAWRBYRX/bundle.json","state":"https://pith.science/pith/EM52TR3P44SQVH25BTAAWRBYRX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EM52TR3P44SQVH25BTAAWRBYRX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:EM52TR3P44SQVH25BTAAWRBYRX","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":"84b00f666b6f62f1fa6b5f86df8ff45b2fa650eda8775ac1c052c16342052a2e","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-09-22T12:31:03Z","title_canon_sha256":"8b16af44cfb3754694124194a421747bd76827f4e0f629c3f94cb860f2f92cea"},"schema_version":"1.0","source":{"id":"1509.06569","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1509.06569","created_at":"2026-05-18T01:24:03Z"},{"alias_kind":"arxiv_version","alias_value":"1509.06569v2","created_at":"2026-05-18T01:24:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.06569","created_at":"2026-05-18T01:24:03Z"},{"alias_kind":"pith_short_12","alias_value":"EM52TR3P44SQ","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"EM52TR3P44SQVH25","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"EM52TR3P","created_at":"2026-05-18T12:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:1847dfa6a9be3cbf304ffb4d24e3827e9a0aba66d191c20c3156d436acdf9de0","target":"graph","created_at":"2026-05-18T01:24:03Z","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":"Deep neural networks currently demonstrate state-of-the-art performance in several domains. At the same time, models of this class are very demanding in terms of computational resources. In particular, a large amount of memory is required by commonly used fully-connected layers, making it hard to use the models on low-end devices and stopping the further increase of the model size. In this paper we convert the dense weight matrices of the fully-connected layers to the Tensor Train format such that the number of parameters is reduced by a huge factor and at the same time the expressive power of","authors_text":"Alexander Novikov, Anton Osokin, Dmitry Podoprikhin, Dmitry Vetrov","cross_cats":["cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-09-22T12:31:03Z","title":"Tensorizing Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.06569","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":"sha256:4bf7f75797826938e042769cdea49afa270d22f9507dd391fc4c94a4c6231946","target":"record","created_at":"2026-05-18T01:24:03Z","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":"84b00f666b6f62f1fa6b5f86df8ff45b2fa650eda8775ac1c052c16342052a2e","cross_cats_sorted":["cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-09-22T12:31:03Z","title_canon_sha256":"8b16af44cfb3754694124194a421747bd76827f4e0f629c3f94cb860f2f92cea"},"schema_version":"1.0","source":{"id":"1509.06569","kind":"arxiv","version":2}},"canonical_sha256":"233ba9c76fe7250a9f5d0cc00b44388dea8492b929977ea3e704a951d86bcb88","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"233ba9c76fe7250a9f5d0cc00b44388dea8492b929977ea3e704a951d86bcb88","first_computed_at":"2026-05-18T01:24:03.229469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:24:03.229469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lZ+nsbSrmy+EcNC5yp1uK/sxBgNZsbOjapxvj0kJk6+GNmzCX0rZVgw7ud7Qa9PAixegwuCnESIQEU/kv8wLCA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:24:03.230263Z","signed_message":"canonical_sha256_bytes"},"source_id":"1509.06569","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bf7f75797826938e042769cdea49afa270d22f9507dd391fc4c94a4c6231946","sha256:1847dfa6a9be3cbf304ffb4d24e3827e9a0aba66d191c20c3156d436acdf9de0"],"state_sha256":"c5a50441fc094c3d24c571bee64325904034a3da49d21c7d2e1feba8ed916dc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4d1fHZKbbeFj3fZB3hwtyUaFoNKEV+BqN1/CQ0hEt3w/YlvZ8pe5leafXY2RPZcemx06f2/njj4hZoXpTalqDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T23:06:06.184908Z","bundle_sha256":"70b4de0ca2976b71113ef8bdacbfc6c4c9069ee0a7769ce32cf8c394e17744bb"}}