{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R74JRSKXRAZCY64ZRURGPDVLOK","short_pith_number":"pith:R74JRSKX","schema_version":"1.0","canonical_sha256":"8ff898c95788322c7b998d22678eab72a5e7d1c9606fc46485a2897b1027f21b","source":{"kind":"arxiv","id":"2312.06837","version":4},"attestation_state":"computed","paper":{"title":"Spectral State Space Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Suo, Elad Hazan, Naman Agarwal, Xinyi Chen","submitted_at":"2023-12-11T21:00:28Z","abstract_excerpt":"This paper studies sequence modeling for prediction tasks with long range dependencies. We propose a new formulation for state space models (SSMs) based on learning linear dynamical systems with the spectral filtering algorithm (Hazan et al. (2017)). This gives rise to a novel sequence prediction architecture we call a spectral state space model.\n  Spectral state space models have two primary advantages. First, they have provable robustness properties as their performance depends on neither the spectrum of the underlying dynamics nor the dimensionality of the problem. Second, these models are "},"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":"2312.06837","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-11T21:00:28Z","cross_cats_sorted":[],"title_canon_sha256":"6d4ca3fed0f5bbbe7812963165cbc9656413b7ec026d1520a07a8e700360791a","abstract_canon_sha256":"961bbf3eb35ea0e11c03d4e052eb4b06a5cb0ab940f816dd73652ed4ac8c950f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:31.504417Z","signature_b64":"u7Gcn35vBQHBK75Y3enHl9bOmr53JJP0pPj3M7x+pgWfsCXrYobMoeL45oDzgz4wqtfKRgIBx47xbYdgFpc1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ff898c95788322c7b998d22678eab72a5e7d1c9606fc46485a2897b1027f21b","last_reissued_at":"2026-07-05T08:42:31.504066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:31.504066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectral State Space Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Suo, Elad Hazan, Naman Agarwal, Xinyi Chen","submitted_at":"2023-12-11T21:00:28Z","abstract_excerpt":"This paper studies sequence modeling for prediction tasks with long range dependencies. We propose a new formulation for state space models (SSMs) based on learning linear dynamical systems with the spectral filtering algorithm (Hazan et al. (2017)). This gives rise to a novel sequence prediction architecture we call a spectral state space model.\n  Spectral state space models have two primary advantages. First, they have provable robustness properties as their performance depends on neither the spectrum of the underlying dynamics nor the dimensionality of the problem. Second, these models are "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06837","kind":"arxiv","version":4},"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/2312.06837/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":"2312.06837","created_at":"2026-07-05T08:42:31.504122+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06837v4","created_at":"2026-07-05T08:42:31.504122+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06837","created_at":"2026-07-05T08:42:31.504122+00:00"},{"alias_kind":"pith_short_12","alias_value":"R74JRSKXRAZC","created_at":"2026-07-05T08:42:31.504122+00:00"},{"alias_kind":"pith_short_16","alias_value":"R74JRSKXRAZCY64Z","created_at":"2026-07-05T08:42:31.504122+00:00"},{"alias_kind":"pith_short_8","alias_value":"R74JRSKX","created_at":"2026-07-05T08:42:31.504122+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/R74JRSKXRAZCY64ZRURGPDVLOK","json":"https://pith.science/pith/R74JRSKXRAZCY64ZRURGPDVLOK.json","graph_json":"https://pith.science/api/pith-number/R74JRSKXRAZCY64ZRURGPDVLOK/graph.json","events_json":"https://pith.science/api/pith-number/R74JRSKXRAZCY64ZRURGPDVLOK/events.json","paper":"https://pith.science/paper/R74JRSKX"},"agent_actions":{"view_html":"https://pith.science/pith/R74JRSKXRAZCY64ZRURGPDVLOK","download_json":"https://pith.science/pith/R74JRSKXRAZCY64ZRURGPDVLOK.json","view_paper":"https://pith.science/paper/R74JRSKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06837&json=true","fetch_graph":"https://pith.science/api/pith-number/R74JRSKXRAZCY64ZRURGPDVLOK/graph.json","fetch_events":"https://pith.science/api/pith-number/R74JRSKXRAZCY64ZRURGPDVLOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R74JRSKXRAZCY64ZRURGPDVLOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R74JRSKXRAZCY64ZRURGPDVLOK/action/storage_attestation","attest_author":"https://pith.science/pith/R74JRSKXRAZCY64ZRURGPDVLOK/action/author_attestation","sign_citation":"https://pith.science/pith/R74JRSKXRAZCY64ZRURGPDVLOK/action/citation_signature","submit_replication":"https://pith.science/pith/R74JRSKXRAZCY64ZRURGPDVLOK/action/replication_record"}},"created_at":"2026-07-05T08:42:31.504122+00:00","updated_at":"2026-07-05T08:42:31.504122+00:00"}