{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:3CLG3UMJU7UV4PPP2USCSKI37B","short_pith_number":"pith:3CLG3UMJ","canonical_record":{"source":{"id":"1705.08052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-23T01:14:22Z","cross_cats_sorted":[],"title_canon_sha256":"03bbf0cbce22356d606c44c865ab8abb0f9d8832e5d4b01ed68ba81d4a7bfb43","abstract_canon_sha256":"13685d1ad385b05217405a28940d59ce150b66119930de31c46b5e7bb6e1b1f2"},"schema_version":"1.0"},"canonical_sha256":"d8966dd189a7e95e3defd52429291bf87e135fe2ab826bb14e84539bb39a8283","source":{"kind":"arxiv","id":"1705.08052","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08052","created_at":"2026-05-18T00:31:51Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08052v1","created_at":"2026-05-18T00:31:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08052","created_at":"2026-05-18T00:31:51Z"},{"alias_kind":"pith_short_12","alias_value":"3CLG3UMJU7UV","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3CLG3UMJU7UV4PPP","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3CLG3UMJ","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:3CLG3UMJU7UV4PPP2USCSKI37B","target":"record","payload":{"canonical_record":{"source":{"id":"1705.08052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-23T01:14:22Z","cross_cats_sorted":[],"title_canon_sha256":"03bbf0cbce22356d606c44c865ab8abb0f9d8832e5d4b01ed68ba81d4a7bfb43","abstract_canon_sha256":"13685d1ad385b05217405a28940d59ce150b66119930de31c46b5e7bb6e1b1f2"},"schema_version":"1.0"},"canonical_sha256":"d8966dd189a7e95e3defd52429291bf87e135fe2ab826bb14e84539bb39a8283","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:51.050293Z","signature_b64":"14KnIr1TIglOEnrY/8zv2hGgmzCYSi+c4Wa3W3oTRoe50d2kbxzWcg7yuYSfF/cPUZ0bpZhUslT5X2f8WuEWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8966dd189a7e95e3defd52429291bf87e135fe2ab826bb14e84539bb39a8283","last_reissued_at":"2026-05-18T00:31:51.049804Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:51.049804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.08052","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":"2026-05-18T00:31:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nGL6u+8O2ZfLjWPT9NKpcYhbZn+ded1MHO9VS1zR3dQkyzPLMo4hEtxB8aDonUO3Tox6Ec0EFSVS2BQ5IjaCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:38:33.110863Z"},"content_sha256":"6bf671a063f484e1a06cbeccd83e472c54f36b939da517b09867f75e4d8e2c83","schema_version":"1.0","event_id":"sha256:6bf671a063f484e1a06cbeccd83e472c54f36b939da517b09867f75e4d8e2c83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:3CLG3UMJU7UV4PPP2USCSKI37B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compressing Recurrent Neural Network with Tensor Train","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andros Tjandra, Sakriani Sakti, Satoshi Nakamura","submitted_at":"2017-05-23T01:14:22Z","abstract_excerpt":"Recurrent Neural Network (RNN) are a popular choice for modeling temporal and sequential tasks and achieve many state-of-the-art performance on various complex problems. However, most of the state-of-the-art RNNs have millions of parameters and require many computational resources for training and predicting new data. This paper proposes an alternative RNN model to reduce the number of parameters significantly by representing the weight parameters based on Tensor Train (TT) format. In this paper, we implement the TT-format representation for several RNN architectures such as simple RNN and Gat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08052","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":"2026-05-18T00:31:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RmNAqqsknBbxMRfuVy5Fx7R/fKQhMeSOBDO6xZ4JUCfls7rzcJN9ruW8S6qZwaSyuvn+lKZWyMlYFPpPXmzWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T21:38:33.111217Z"},"content_sha256":"2aab33759a89a11c9f2c624a6774b891e22cb8131e6212017610e726f85c6d85","schema_version":"1.0","event_id":"sha256:2aab33759a89a11c9f2c624a6774b891e22cb8131e6212017610e726f85c6d85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3CLG3UMJU7UV4PPP2USCSKI37B/bundle.json","state_url":"https://pith.science/pith/3CLG3UMJU7UV4PPP2USCSKI37B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3CLG3UMJU7UV4PPP2USCSKI37B/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":"2026-06-02T21:38:33Z","links":{"resolver":"https://pith.science/pith/3CLG3UMJU7UV4PPP2USCSKI37B","bundle":"https://pith.science/pith/3CLG3UMJU7UV4PPP2USCSKI37B/bundle.json","state":"https://pith.science/pith/3CLG3UMJU7UV4PPP2USCSKI37B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3CLG3UMJU7UV4PPP2USCSKI37B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3CLG3UMJU7UV4PPP2USCSKI37B","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":"13685d1ad385b05217405a28940d59ce150b66119930de31c46b5e7bb6e1b1f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-23T01:14:22Z","title_canon_sha256":"03bbf0cbce22356d606c44c865ab8abb0f9d8832e5d4b01ed68ba81d4a7bfb43"},"schema_version":"1.0","source":{"id":"1705.08052","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08052","created_at":"2026-05-18T00:31:51Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08052v1","created_at":"2026-05-18T00:31:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08052","created_at":"2026-05-18T00:31:51Z"},{"alias_kind":"pith_short_12","alias_value":"3CLG3UMJU7UV","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3CLG3UMJU7UV4PPP","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3CLG3UMJ","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:2aab33759a89a11c9f2c624a6774b891e22cb8131e6212017610e726f85c6d85","target":"graph","created_at":"2026-05-18T00:31:51Z","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 Network (RNN) are a popular choice for modeling temporal and sequential tasks and achieve many state-of-the-art performance on various complex problems. However, most of the state-of-the-art RNNs have millions of parameters and require many computational resources for training and predicting new data. This paper proposes an alternative RNN model to reduce the number of parameters significantly by representing the weight parameters based on Tensor Train (TT) format. In this paper, we implement the TT-format representation for several RNN architectures such as simple RNN and Gat","authors_text":"Andros Tjandra, Sakriani Sakti, Satoshi Nakamura","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-23T01:14:22Z","title":"Compressing Recurrent Neural Network with Tensor Train"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08052","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":"sha256:6bf671a063f484e1a06cbeccd83e472c54f36b939da517b09867f75e4d8e2c83","target":"record","created_at":"2026-05-18T00:31:51Z","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":"13685d1ad385b05217405a28940d59ce150b66119930de31c46b5e7bb6e1b1f2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-23T01:14:22Z","title_canon_sha256":"03bbf0cbce22356d606c44c865ab8abb0f9d8832e5d4b01ed68ba81d4a7bfb43"},"schema_version":"1.0","source":{"id":"1705.08052","kind":"arxiv","version":1}},"canonical_sha256":"d8966dd189a7e95e3defd52429291bf87e135fe2ab826bb14e84539bb39a8283","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8966dd189a7e95e3defd52429291bf87e135fe2ab826bb14e84539bb39a8283","first_computed_at":"2026-05-18T00:31:51.049804Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:51.049804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"14KnIr1TIglOEnrY/8zv2hGgmzCYSi+c4Wa3W3oTRoe50d2kbxzWcg7yuYSfF/cPUZ0bpZhUslT5X2f8WuEWBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:51.050293Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.08052","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bf671a063f484e1a06cbeccd83e472c54f36b939da517b09867f75e4d8e2c83","sha256:2aab33759a89a11c9f2c624a6774b891e22cb8131e6212017610e726f85c6d85"],"state_sha256":"a3cd3d96cfbb8b9b2c9c6e1f2aa2b0810aaa63683759c1c9bbabf6e65d8fafe8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IP8/C27uslUaSKnjO8UeyUnN2+KQQ52RyicUC4+l4UCe6UrxRMblQvATFlZddY/7t8bkEBCo9C1+Y0mULzLeDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T21:38:33.113259Z","bundle_sha256":"0d0192ebcd866d08eaa7de836a03def4d5c4b29936d4faccaf50fc928b88efc9"}}