{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PQO7LH2SDVKD5CJIALQICLULBD","short_pith_number":"pith:PQO7LH2S","schema_version":"1.0","canonical_sha256":"7c1df59f521d543e892802e0812e8b08ff8845c133cc34a526f9d6369c324e0a","source":{"kind":"arxiv","id":"2307.11888","version":3},"attestation_state":"computed","paper":{"title":"Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Antonio Orvieto, Caglar Gulcehre, Razvan Pascanu, Samuel L. Smith, Soham De","submitted_at":"2023-07-21T20:09:06Z","abstract_excerpt":"Deep neural networks based on linear RNNs interleaved with position-wise MLPs are gaining traction as competitive approaches for sequence modeling. Examples of such architectures include state-space models (SSMs) like S4, LRU, and Mamba: recently proposed models that achieve promising performance on text, genetics, and other data that require long-range reasoning. Despite experimental evidence highlighting these architectures' effectiveness and computational efficiency, their expressive power remains relatively unexplored, especially in connection to specific choices crucial in practice - e.g."},"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":"2307.11888","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-21T20:09:06Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"c979a8245658d490166da066846c3f30deec07cf0e1318f103c024186ad31874","abstract_canon_sha256":"96e0b63996db48e5ee10df39f363796891b9f6aa13a5a9ff31ab650f95adf2b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:40.998164Z","signature_b64":"eMDEJibCgxNOFXWattxBHDDTf8JNAA8T97NKmmK4JYWoXpK58jJi9is7tEBFF1eYPj039bV2JWdICFz0yQ4nBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c1df59f521d543e892802e0812e8b08ff8845c133cc34a526f9d6369c324e0a","last_reissued_at":"2026-07-05T08:27:40.997643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:40.997643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Antonio Orvieto, Caglar Gulcehre, Razvan Pascanu, Samuel L. Smith, Soham De","submitted_at":"2023-07-21T20:09:06Z","abstract_excerpt":"Deep neural networks based on linear RNNs interleaved with position-wise MLPs are gaining traction as competitive approaches for sequence modeling. Examples of such architectures include state-space models (SSMs) like S4, LRU, and Mamba: recently proposed models that achieve promising performance on text, genetics, and other data that require long-range reasoning. Despite experimental evidence highlighting these architectures' effectiveness and computational efficiency, their expressive power remains relatively unexplored, especially in connection to specific choices crucial in practice - e.g."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.11888","kind":"arxiv","version":3},"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/2307.11888/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":"2307.11888","created_at":"2026-07-05T08:27:40.997713+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.11888v3","created_at":"2026-07-05T08:27:40.997713+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.11888","created_at":"2026-07-05T08:27:40.997713+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQO7LH2SDVKD","created_at":"2026-07-05T08:27:40.997713+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQO7LH2SDVKD5CJI","created_at":"2026-07-05T08:27:40.997713+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQO7LH2S","created_at":"2026-07-05T08:27:40.997713+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.19427","citing_title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PQO7LH2SDVKD5CJIALQICLULBD","json":"https://pith.science/pith/PQO7LH2SDVKD5CJIALQICLULBD.json","graph_json":"https://pith.science/api/pith-number/PQO7LH2SDVKD5CJIALQICLULBD/graph.json","events_json":"https://pith.science/api/pith-number/PQO7LH2SDVKD5CJIALQICLULBD/events.json","paper":"https://pith.science/paper/PQO7LH2S"},"agent_actions":{"view_html":"https://pith.science/pith/PQO7LH2SDVKD5CJIALQICLULBD","download_json":"https://pith.science/pith/PQO7LH2SDVKD5CJIALQICLULBD.json","view_paper":"https://pith.science/paper/PQO7LH2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.11888&json=true","fetch_graph":"https://pith.science/api/pith-number/PQO7LH2SDVKD5CJIALQICLULBD/graph.json","fetch_events":"https://pith.science/api/pith-number/PQO7LH2SDVKD5CJIALQICLULBD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQO7LH2SDVKD5CJIALQICLULBD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQO7LH2SDVKD5CJIALQICLULBD/action/storage_attestation","attest_author":"https://pith.science/pith/PQO7LH2SDVKD5CJIALQICLULBD/action/author_attestation","sign_citation":"https://pith.science/pith/PQO7LH2SDVKD5CJIALQICLULBD/action/citation_signature","submit_replication":"https://pith.science/pith/PQO7LH2SDVKD5CJIALQICLULBD/action/replication_record"}},"created_at":"2026-07-05T08:27:40.997713+00:00","updated_at":"2026-07-05T08:27:40.997713+00:00"}