{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7KMVPT4M2RWANGARU65PLLDVXC","short_pith_number":"pith:7KMVPT4M","canonical_record":{"source":{"id":"1802.10410","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-28T13:52:22Z","cross_cats_sorted":[],"title_canon_sha256":"1ac60dd827209b85b1041fa699fa6696e6ad17798b087d5c3105c705897d55df","abstract_canon_sha256":"b5f2b4b5c8cad0b223475accf3d960ee0e01f52d9756196ba2068bbf031a74d0"},"schema_version":"1.0"},"canonical_sha256":"fa9957cf8cd46c069811a7baf5ac75b89bdb9ef611b711dd5db5ef6ceb768ef0","source":{"kind":"arxiv","id":"1802.10410","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.10410","created_at":"2026-05-18T00:16:36Z"},{"alias_kind":"arxiv_version","alias_value":"1802.10410v2","created_at":"2026-05-18T00:16:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10410","created_at":"2026-05-18T00:16:36Z"},{"alias_kind":"pith_short_12","alias_value":"7KMVPT4M2RWA","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7KMVPT4M2RWANGAR","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7KMVPT4M","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7KMVPT4M2RWANGARU65PLLDVXC","target":"record","payload":{"canonical_record":{"source":{"id":"1802.10410","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-28T13:52:22Z","cross_cats_sorted":[],"title_canon_sha256":"1ac60dd827209b85b1041fa699fa6696e6ad17798b087d5c3105c705897d55df","abstract_canon_sha256":"b5f2b4b5c8cad0b223475accf3d960ee0e01f52d9756196ba2068bbf031a74d0"},"schema_version":"1.0"},"canonical_sha256":"fa9957cf8cd46c069811a7baf5ac75b89bdb9ef611b711dd5db5ef6ceb768ef0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:36.359969Z","signature_b64":"XaH05gRuLFCkIHXgO8WuzKsbYGqAIufQdSQPLeJdoK5iF1KFOmwdtOwwlQ0PbVmWQ2IxIrY25835ztcyPEzSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa9957cf8cd46c069811a7baf5ac75b89bdb9ef611b711dd5db5ef6ceb768ef0","last_reissued_at":"2026-05-18T00:16:36.359493Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:36.359493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.10410","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":"2026-05-18T00:16:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HvpiAgHiQow4w/E/FW1ZUo0CG0GRkQN4QumjUg/H23uwwbxqZQJQF/OHS0prehqJpqLiXNOxSD/zQwmQoaYhDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:09:32.035072Z"},"content_sha256":"9a99b3912dff0edd62285d9ffc01ba7ede2020aa0021ef337d065c62755ff1cd","schema_version":"1.0","event_id":"sha256:9a99b3912dff0edd62285d9ffc01ba7ede2020aa0021ef337d065c62755ff1cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7KMVPT4M2RWANGARU65PLLDVXC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tensor Decomposition for Compressing Recurrent Neural Network","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":"2018-02-28T13:52:22Z","abstract_excerpt":"In the machine learning fields, Recurrent Neural Network (RNN) has become a popular architecture for sequential data modeling. However, behind the impressive performance, RNNs require a large number of parameters for both training and inference. In this paper, we are trying to reduce the number of parameters and maintain the expressive power from RNN simultaneously. We utilize several tensor decompositions method including CANDECOMP/PARAFAC (CP), Tucker decomposition and Tensor Train (TT) to re-parameterize the Gated Recurrent Unit (GRU) RNN. We evaluate all tensor-based RNNs performance on se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10410","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":"2026-05-18T00:16:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NRuSnAUzM7rk97oTm8axpRgt0i59mc7wOk0f2f9lSKw2R3N7l5Nx0cXjrwSvHPQREWTb8i3x1RnvYLNhdb/8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:09:32.035433Z"},"content_sha256":"47fe5ce1ebc6338ad7f5223cc4cb9d8bda575c9262d97af95038998aa3483f76","schema_version":"1.0","event_id":"sha256:47fe5ce1ebc6338ad7f5223cc4cb9d8bda575c9262d97af95038998aa3483f76"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7KMVPT4M2RWANGARU65PLLDVXC/bundle.json","state_url":"https://pith.science/pith/7KMVPT4M2RWANGARU65PLLDVXC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7KMVPT4M2RWANGARU65PLLDVXC/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":"2026-06-01T21:09:32Z","links":{"resolver":"https://pith.science/pith/7KMVPT4M2RWANGARU65PLLDVXC","bundle":"https://pith.science/pith/7KMVPT4M2RWANGARU65PLLDVXC/bundle.json","state":"https://pith.science/pith/7KMVPT4M2RWANGARU65PLLDVXC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7KMVPT4M2RWANGARU65PLLDVXC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7KMVPT4M2RWANGARU65PLLDVXC","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":"b5f2b4b5c8cad0b223475accf3d960ee0e01f52d9756196ba2068bbf031a74d0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-28T13:52:22Z","title_canon_sha256":"1ac60dd827209b85b1041fa699fa6696e6ad17798b087d5c3105c705897d55df"},"schema_version":"1.0","source":{"id":"1802.10410","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.10410","created_at":"2026-05-18T00:16:36Z"},{"alias_kind":"arxiv_version","alias_value":"1802.10410v2","created_at":"2026-05-18T00:16:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10410","created_at":"2026-05-18T00:16:36Z"},{"alias_kind":"pith_short_12","alias_value":"7KMVPT4M2RWA","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7KMVPT4M2RWANGAR","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7KMVPT4M","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:47fe5ce1ebc6338ad7f5223cc4cb9d8bda575c9262d97af95038998aa3483f76","target":"graph","created_at":"2026-05-18T00:16:36Z","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":"In the machine learning fields, Recurrent Neural Network (RNN) has become a popular architecture for sequential data modeling. However, behind the impressive performance, RNNs require a large number of parameters for both training and inference. In this paper, we are trying to reduce the number of parameters and maintain the expressive power from RNN simultaneously. We utilize several tensor decompositions method including CANDECOMP/PARAFAC (CP), Tucker decomposition and Tensor Train (TT) to re-parameterize the Gated Recurrent Unit (GRU) RNN. We evaluate all tensor-based RNNs performance on se","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":"2018-02-28T13:52:22Z","title":"Tensor Decomposition for Compressing Recurrent Neural Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10410","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":"sha256:9a99b3912dff0edd62285d9ffc01ba7ede2020aa0021ef337d065c62755ff1cd","target":"record","created_at":"2026-05-18T00:16:36Z","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":"b5f2b4b5c8cad0b223475accf3d960ee0e01f52d9756196ba2068bbf031a74d0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-28T13:52:22Z","title_canon_sha256":"1ac60dd827209b85b1041fa699fa6696e6ad17798b087d5c3105c705897d55df"},"schema_version":"1.0","source":{"id":"1802.10410","kind":"arxiv","version":2}},"canonical_sha256":"fa9957cf8cd46c069811a7baf5ac75b89bdb9ef611b711dd5db5ef6ceb768ef0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa9957cf8cd46c069811a7baf5ac75b89bdb9ef611b711dd5db5ef6ceb768ef0","first_computed_at":"2026-05-18T00:16:36.359493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:36.359493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XaH05gRuLFCkIHXgO8WuzKsbYGqAIufQdSQPLeJdoK5iF1KFOmwdtOwwlQ0PbVmWQ2IxIrY25835ztcyPEzSCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:36.359969Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.10410","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a99b3912dff0edd62285d9ffc01ba7ede2020aa0021ef337d065c62755ff1cd","sha256:47fe5ce1ebc6338ad7f5223cc4cb9d8bda575c9262d97af95038998aa3483f76"],"state_sha256":"facbd20ace8eae9bf3638fb29affab0a24d0d84648c0103276cb2507edb7ee9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7gFmJpQwz69xfqJeNe2Si3zNP45hdCvMyep0hd42EsMIAQ08YEPLKwgHQiP/z7Zp7A9jT8hmk1sSKBPq/+B0Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T21:09:32.037378Z","bundle_sha256":"dfc5bd8092658c6cd762ea950c2e79e47d59931c64e7bc848958b74a78343017"}}