{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BAMY6XUDYC42CWQBO3EO3KUVC7","short_pith_number":"pith:BAMY6XUD","schema_version":"1.0","canonical_sha256":"08198f5e83c0b9a15a0176c8edaa9517e94596e95c237104590b5730a9d07ddd","source":{"kind":"arxiv","id":"1712.05134","version":2},"attestation_state":"computed","paper":{"title":"Learning Compact Recurrent Neural Networks with Block-Term Tensor Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Di Chen, Guangxi Li, Jinmian Ye, Linnan Wang, Shandian Zhe, Xinqi Chu, Zenglin Xu","submitted_at":"2017-12-14T09:24:27Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) are powerful sequence modeling tools. However, when dealing with high dimensional inputs, the training of RNNs becomes computational expensive due to the large number of model parameters. This hinders RNNs from solving many important computer vision tasks, such as Action Recognition in Videos and Image Captioning. To overcome this problem, we propose a compact and flexible structure, namely Block-Term tensor decomposition, which greatly reduces the parameters of RNNs and improves their training efficiency. Compared with alternative low-rank approximations, such"},"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":"1712.05134","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-14T09:24:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"db00c8e495741eb33a17ae432f8a16ed17bf805320a0cce5dc164df0a9344f3c","abstract_canon_sha256":"d4dd7aa4d139875345613a4347290ad3217be8724e11a6964e2a8bd6bf5be94a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:28.391096Z","signature_b64":"Zs+FdsH9ml0qZoh0dEaC9T66eb7/TZGDj1VBzK5DeiIGKl9plyuGIfDd6RwJyHZqzPh+tPWhnTdXqj0MaJGvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08198f5e83c0b9a15a0176c8edaa9517e94596e95c237104590b5730a9d07ddd","last_reissued_at":"2026-05-18T00:15:28.390451Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:28.390451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Compact Recurrent Neural Networks with Block-Term Tensor Decomposition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Di Chen, Guangxi Li, Jinmian Ye, Linnan Wang, Shandian Zhe, Xinqi Chu, Zenglin Xu","submitted_at":"2017-12-14T09:24:27Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) are powerful sequence modeling tools. However, when dealing with high dimensional inputs, the training of RNNs becomes computational expensive due to the large number of model parameters. This hinders RNNs from solving many important computer vision tasks, such as Action Recognition in Videos and Image Captioning. To overcome this problem, we propose a compact and flexible structure, namely Block-Term tensor decomposition, which greatly reduces the parameters of RNNs and improves their training efficiency. Compared with alternative low-rank approximations, such"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.05134","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1712.05134","created_at":"2026-05-18T00:15:28.390545+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.05134v2","created_at":"2026-05-18T00:15:28.390545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.05134","created_at":"2026-05-18T00:15:28.390545+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAMY6XUDYC42","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAMY6XUDYC42CWQB","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAMY6XUD","created_at":"2026-05-18T12:31:08.081275+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/BAMY6XUDYC42CWQBO3EO3KUVC7","json":"https://pith.science/pith/BAMY6XUDYC42CWQBO3EO3KUVC7.json","graph_json":"https://pith.science/api/pith-number/BAMY6XUDYC42CWQBO3EO3KUVC7/graph.json","events_json":"https://pith.science/api/pith-number/BAMY6XUDYC42CWQBO3EO3KUVC7/events.json","paper":"https://pith.science/paper/BAMY6XUD"},"agent_actions":{"view_html":"https://pith.science/pith/BAMY6XUDYC42CWQBO3EO3KUVC7","download_json":"https://pith.science/pith/BAMY6XUDYC42CWQBO3EO3KUVC7.json","view_paper":"https://pith.science/paper/BAMY6XUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.05134&json=true","fetch_graph":"https://pith.science/api/pith-number/BAMY6XUDYC42CWQBO3EO3KUVC7/graph.json","fetch_events":"https://pith.science/api/pith-number/BAMY6XUDYC42CWQBO3EO3KUVC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAMY6XUDYC42CWQBO3EO3KUVC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAMY6XUDYC42CWQBO3EO3KUVC7/action/storage_attestation","attest_author":"https://pith.science/pith/BAMY6XUDYC42CWQBO3EO3KUVC7/action/author_attestation","sign_citation":"https://pith.science/pith/BAMY6XUDYC42CWQBO3EO3KUVC7/action/citation_signature","submit_replication":"https://pith.science/pith/BAMY6XUDYC42CWQBO3EO3KUVC7/action/replication_record"}},"created_at":"2026-05-18T00:15:28.390545+00:00","updated_at":"2026-05-18T00:15:28.390545+00:00"}