{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WB45OKXEEIWLRQR6WEJJGWRGPS","short_pith_number":"pith:WB45OKXE","schema_version":"1.0","canonical_sha256":"b079d72ae4222cb8c23eb112935a267c94207a0b85aaf1c85efcbaa252a471c6","source":{"kind":"arxiv","id":"2009.08727","version":5},"attestation_state":"computed","paper":{"title":"Recurrent Graph Tensor Networks: A Low-Complexity Framework for Modelling High-Dimensional Multi-Way Sequence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Danilo P. Mandic, Yao Lei Xu","submitted_at":"2020-09-18T10:13:36Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) are among the most successful machine learning models for sequence modelling, but tend to suffer from an exponential increase in the number of parameters when dealing with large multidimensional data. To this end, we develop a multi-linear graph filter framework for approximating the modelling of hidden states in RNNs, which is embedded in a tensor network architecture to improve modelling power and reduce parameter complexity, resulting in a novel Recurrent Graph Tensor Network (RGTN). The proposed framework is validated through several multi-way sequence mode"},"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":"2009.08727","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-18T10:13:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"19c8374bdf5bc0ea55c0b640f9c80d141aa14790326f21b4e87d4b7f386fb703","abstract_canon_sha256":"d1dbc9aca2391cb8e777bac01084209f78a15e067aeb325dce7daef35b4be78e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:39:05.202956Z","signature_b64":"ZFqIxHhIwIy30g/4Dq2zKk7fb8PZWKUaS5f7kg3GQcoSb+fM9/E/ai9tb4bdH8+8rejVzZWPrVpxLaEv4912Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b079d72ae4222cb8c23eb112935a267c94207a0b85aaf1c85efcbaa252a471c6","last_reissued_at":"2026-07-05T02:39:05.202577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:39:05.202577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent Graph Tensor Networks: A Low-Complexity Framework for Modelling High-Dimensional Multi-Way Sequence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Danilo P. Mandic, Yao Lei Xu","submitted_at":"2020-09-18T10:13:36Z","abstract_excerpt":"Recurrent Neural Networks (RNNs) are among the most successful machine learning models for sequence modelling, but tend to suffer from an exponential increase in the number of parameters when dealing with large multidimensional data. To this end, we develop a multi-linear graph filter framework for approximating the modelling of hidden states in RNNs, which is embedded in a tensor network architecture to improve modelling power and reduce parameter complexity, resulting in a novel Recurrent Graph Tensor Network (RGTN). The proposed framework is validated through several multi-way sequence mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.08727","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2009.08727/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2009.08727","created_at":"2026-07-05T02:39:05.202631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.08727v5","created_at":"2026-07-05T02:39:05.202631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.08727","created_at":"2026-07-05T02:39:05.202631+00:00"},{"alias_kind":"pith_short_12","alias_value":"WB45OKXEEIWL","created_at":"2026-07-05T02:39:05.202631+00:00"},{"alias_kind":"pith_short_16","alias_value":"WB45OKXEEIWLRQR6","created_at":"2026-07-05T02:39:05.202631+00:00"},{"alias_kind":"pith_short_8","alias_value":"WB45OKXE","created_at":"2026-07-05T02:39:05.202631+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/WB45OKXEEIWLRQR6WEJJGWRGPS","json":"https://pith.science/pith/WB45OKXEEIWLRQR6WEJJGWRGPS.json","graph_json":"https://pith.science/api/pith-number/WB45OKXEEIWLRQR6WEJJGWRGPS/graph.json","events_json":"https://pith.science/api/pith-number/WB45OKXEEIWLRQR6WEJJGWRGPS/events.json","paper":"https://pith.science/paper/WB45OKXE"},"agent_actions":{"view_html":"https://pith.science/pith/WB45OKXEEIWLRQR6WEJJGWRGPS","download_json":"https://pith.science/pith/WB45OKXEEIWLRQR6WEJJGWRGPS.json","view_paper":"https://pith.science/paper/WB45OKXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.08727&json=true","fetch_graph":"https://pith.science/api/pith-number/WB45OKXEEIWLRQR6WEJJGWRGPS/graph.json","fetch_events":"https://pith.science/api/pith-number/WB45OKXEEIWLRQR6WEJJGWRGPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WB45OKXEEIWLRQR6WEJJGWRGPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WB45OKXEEIWLRQR6WEJJGWRGPS/action/storage_attestation","attest_author":"https://pith.science/pith/WB45OKXEEIWLRQR6WEJJGWRGPS/action/author_attestation","sign_citation":"https://pith.science/pith/WB45OKXEEIWLRQR6WEJJGWRGPS/action/citation_signature","submit_replication":"https://pith.science/pith/WB45OKXEEIWLRQR6WEJJGWRGPS/action/replication_record"}},"created_at":"2026-07-05T02:39:05.202631+00:00","updated_at":"2026-07-05T02:39:05.202631+00:00"}