{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N6W6KAULZZIXPTFS2PBCGGFME6","short_pith_number":"pith:N6W6KAUL","schema_version":"1.0","canonical_sha256":"6fade5028bce5177ccb2d3c22318ac279d59cfa8362cee205e9a77527269988f","source":{"kind":"arxiv","id":"2410.03943","version":3},"attestation_state":"computed","paper":{"title":"Oscillatory State-Space Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Daniela Rus, T. Konstantin Rusch","submitted_at":"2024-10-04T22:00:13Z","abstract_excerpt":"We propose Linear Oscillatory State-Space models (LinOSS) for efficiently learning on long sequences. Inspired by cortical dynamics of biological neural networks, we base our proposed LinOSS model on a system of forced harmonic oscillators. A stable discretization, integrated over time using fast associative parallel scans, yields the proposed state-space model. We prove that LinOSS produces stable dynamics only requiring nonnegative diagonal state matrix. This is in stark contrast to many previous state-space models relying heavily on restrictive parameterizations. Moreover, we rigorously sho"},"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":"2410.03943","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-04T22:00:13Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"2be6b90d898436d93c4ba8ec0037f2c6ff60c022eeec9d75614b4d26947ed581","abstract_canon_sha256":"b3fb70567d498f218e4105d10330b35b61a9dbaa98dc88d12fe542e15137a98a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:18.545874Z","signature_b64":"5HDoR6T9NSficA9miHjezdNJ+LDwZx17q8tTnMvxAfDCvANXNU0cxzBZei06y88eX8ORSLyMW9q/UWhBTePFAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fade5028bce5177ccb2d3c22318ac279d59cfa8362cee205e9a77527269988f","last_reissued_at":"2026-07-05T11:23:18.545350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:18.545350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Oscillatory State-Space Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Daniela Rus, T. Konstantin Rusch","submitted_at":"2024-10-04T22:00:13Z","abstract_excerpt":"We propose Linear Oscillatory State-Space models (LinOSS) for efficiently learning on long sequences. Inspired by cortical dynamics of biological neural networks, we base our proposed LinOSS model on a system of forced harmonic oscillators. A stable discretization, integrated over time using fast associative parallel scans, yields the proposed state-space model. We prove that LinOSS produces stable dynamics only requiring nonnegative diagonal state matrix. This is in stark contrast to many previous state-space models relying heavily on restrictive parameterizations. Moreover, we rigorously sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03943","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/2410.03943/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":"2410.03943","created_at":"2026-07-05T11:23:18.545415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03943v3","created_at":"2026-07-05T11:23:18.545415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03943","created_at":"2026-07-05T11:23:18.545415+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6W6KAULZZIX","created_at":"2026-07-05T11:23:18.545415+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6W6KAULZZIXPTFS","created_at":"2026-07-05T11:23:18.545415+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6W6KAUL","created_at":"2026-07-05T11:23:18.545415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.01015","citing_title":"Upper Approximation Bounds for Neural Oscillators","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09742","citing_title":"Upper Generalization Bounds for Neural Oscillators","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20595","citing_title":"An explicit operator explains end-to-end computation in the modern neural networks used for sequence and language modeling","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N6W6KAULZZIXPTFS2PBCGGFME6","json":"https://pith.science/pith/N6W6KAULZZIXPTFS2PBCGGFME6.json","graph_json":"https://pith.science/api/pith-number/N6W6KAULZZIXPTFS2PBCGGFME6/graph.json","events_json":"https://pith.science/api/pith-number/N6W6KAULZZIXPTFS2PBCGGFME6/events.json","paper":"https://pith.science/paper/N6W6KAUL"},"agent_actions":{"view_html":"https://pith.science/pith/N6W6KAULZZIXPTFS2PBCGGFME6","download_json":"https://pith.science/pith/N6W6KAULZZIXPTFS2PBCGGFME6.json","view_paper":"https://pith.science/paper/N6W6KAUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03943&json=true","fetch_graph":"https://pith.science/api/pith-number/N6W6KAULZZIXPTFS2PBCGGFME6/graph.json","fetch_events":"https://pith.science/api/pith-number/N6W6KAULZZIXPTFS2PBCGGFME6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6W6KAULZZIXPTFS2PBCGGFME6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6W6KAULZZIXPTFS2PBCGGFME6/action/storage_attestation","attest_author":"https://pith.science/pith/N6W6KAULZZIXPTFS2PBCGGFME6/action/author_attestation","sign_citation":"https://pith.science/pith/N6W6KAULZZIXPTFS2PBCGGFME6/action/citation_signature","submit_replication":"https://pith.science/pith/N6W6KAULZZIXPTFS2PBCGGFME6/action/replication_record"}},"created_at":"2026-07-05T11:23:18.545415+00:00","updated_at":"2026-07-05T11:23:18.545415+00:00"}