{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X5ECQUTB5H77UJMQCE3TW65YPR","short_pith_number":"pith:X5ECQUTB","schema_version":"1.0","canonical_sha256":"bf48285261e9fffa259011373b7bb87c50ba87beac84fe0e392ada5fd6d27175","source":{"kind":"arxiv","id":"2307.15679","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Analysis and an Eigen Initializer for Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jose Principe, Ran Dou","submitted_at":"2023-07-28T17:14:58Z","abstract_excerpt":"In recurrent neural networks, learning long-term dependency is the main difficulty due to the vanishing and exploding gradient problem. Many researchers are dedicated to solving this issue and they proposed many algorithms. Although these algorithms have achieved great success, understanding how the information decays remains an open problem. In this paper, we study the dynamics of the hidden state in recurrent neural networks. We propose a new perspective to analyze the hidden state space based on an eigen decomposition of the weight matrix. We start the analysis by linear state space model a"},"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":"2307.15679","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-28T17:14:58Z","cross_cats_sorted":[],"title_canon_sha256":"23540a8f37cf22d4c76e3651de45a78003a3bb4f0b639253898e65fb862b1e0a","abstract_canon_sha256":"ed83cee97f4ad8ab7ff79551d705c5e79f54ed3eaf82d691b861de2dcf79822f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:38.262326Z","signature_b64":"hZtw3s3kauL0nn7Ro/dgAAMAt55XgREjOXE/ZfF2RlDBQlzIN1LCnPA5tA9zrRvLR4TKr/hIDz45Ulv46izIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf48285261e9fffa259011373b7bb87c50ba87beac84fe0e392ada5fd6d27175","last_reissued_at":"2026-07-05T06:35:38.261847Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:38.261847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Analysis and an Eigen Initializer for Recurrent Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jose Principe, Ran Dou","submitted_at":"2023-07-28T17:14:58Z","abstract_excerpt":"In recurrent neural networks, learning long-term dependency is the main difficulty due to the vanishing and exploding gradient problem. Many researchers are dedicated to solving this issue and they proposed many algorithms. Although these algorithms have achieved great success, understanding how the information decays remains an open problem. In this paper, we study the dynamics of the hidden state in recurrent neural networks. We propose a new perspective to analyze the hidden state space based on an eigen decomposition of the weight matrix. We start the analysis by linear state space model a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15679","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.15679/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":"2307.15679","created_at":"2026-07-05T06:35:38.261902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.15679v1","created_at":"2026-07-05T06:35:38.261902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15679","created_at":"2026-07-05T06:35:38.261902+00:00"},{"alias_kind":"pith_short_12","alias_value":"X5ECQUTB5H77","created_at":"2026-07-05T06:35:38.261902+00:00"},{"alias_kind":"pith_short_16","alias_value":"X5ECQUTB5H77UJMQ","created_at":"2026-07-05T06:35:38.261902+00:00"},{"alias_kind":"pith_short_8","alias_value":"X5ECQUTB","created_at":"2026-07-05T06:35:38.261902+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/X5ECQUTB5H77UJMQCE3TW65YPR","json":"https://pith.science/pith/X5ECQUTB5H77UJMQCE3TW65YPR.json","graph_json":"https://pith.science/api/pith-number/X5ECQUTB5H77UJMQCE3TW65YPR/graph.json","events_json":"https://pith.science/api/pith-number/X5ECQUTB5H77UJMQCE3TW65YPR/events.json","paper":"https://pith.science/paper/X5ECQUTB"},"agent_actions":{"view_html":"https://pith.science/pith/X5ECQUTB5H77UJMQCE3TW65YPR","download_json":"https://pith.science/pith/X5ECQUTB5H77UJMQCE3TW65YPR.json","view_paper":"https://pith.science/paper/X5ECQUTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.15679&json=true","fetch_graph":"https://pith.science/api/pith-number/X5ECQUTB5H77UJMQCE3TW65YPR/graph.json","fetch_events":"https://pith.science/api/pith-number/X5ECQUTB5H77UJMQCE3TW65YPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X5ECQUTB5H77UJMQCE3TW65YPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X5ECQUTB5H77UJMQCE3TW65YPR/action/storage_attestation","attest_author":"https://pith.science/pith/X5ECQUTB5H77UJMQCE3TW65YPR/action/author_attestation","sign_citation":"https://pith.science/pith/X5ECQUTB5H77UJMQCE3TW65YPR/action/citation_signature","submit_replication":"https://pith.science/pith/X5ECQUTB5H77UJMQCE3TW65YPR/action/replication_record"}},"created_at":"2026-07-05T06:35:38.261902+00:00","updated_at":"2026-07-05T06:35:38.261902+00:00"}