{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VTQCHYLSJYXYSK6ZMK4LDTCEGK","short_pith_number":"pith:VTQCHYLS","schema_version":"1.0","canonical_sha256":"ace023e1724e2f892bd962b8b1cc4432a4f13f8c0ab8cc05f19e95178a716f17","source":{"kind":"arxiv","id":"2303.09489","version":1},"attestation_state":"computed","paper":{"title":"Effectively Modeling Time Series with Simple Discrete State Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Christopher R\\'e, Karan Goel, Khaled K. Saab, Michael Poli, Michael Zhang, Tri Dao","submitted_at":"2023-03-16T17:08:21Z","abstract_excerpt":"Time series modeling is a well-established problem, which often requires that methods (1) expressively represent complicated dependencies, (2) forecast long horizons, and (3) efficiently train over long sequences. State-space models (SSMs) are classical models for time series, and prior works combine SSMs with deep learning layers for efficient sequence modeling. However, we find fundamental limitations with these prior approaches, proving their SSM representations cannot express autoregressive time series processes. We thus introduce SpaceTime, a new state-space time series architecture that "},"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":"2303.09489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-16T17:08:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"027b96cd0c791af03e676f26dcbd89c2c068b0f2fcdc1472a013e3d976998b54","abstract_canon_sha256":"0c7f2e2a53e3a7d752aabfd9b7d94e19ffcb7d5c07c587e8a59a4bf40bcb872c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:54.070826Z","signature_b64":"fxZkq9pYgqrHbb74Ox8rfbf4Y3MReNYN8i1pgMZJdLd+Rp2ATduPtgahpEs31wjJOKE9sQqqOg9tVUxOpm6TDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ace023e1724e2f892bd962b8b1cc4432a4f13f8c0ab8cc05f19e95178a716f17","last_reissued_at":"2026-07-05T05:51:54.070483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:54.070483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effectively Modeling Time Series with Simple Discrete State Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Christopher R\\'e, Karan Goel, Khaled K. Saab, Michael Poli, Michael Zhang, Tri Dao","submitted_at":"2023-03-16T17:08:21Z","abstract_excerpt":"Time series modeling is a well-established problem, which often requires that methods (1) expressively represent complicated dependencies, (2) forecast long horizons, and (3) efficiently train over long sequences. State-space models (SSMs) are classical models for time series, and prior works combine SSMs with deep learning layers for efficient sequence modeling. However, we find fundamental limitations with these prior approaches, proving their SSM representations cannot express autoregressive time series processes. We thus introduce SpaceTime, a new state-space time series architecture that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09489","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/2303.09489/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":"2303.09489","created_at":"2026-07-05T05:51:54.070538+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09489v1","created_at":"2026-07-05T05:51:54.070538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09489","created_at":"2026-07-05T05:51:54.070538+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTQCHYLSJYXY","created_at":"2026-07-05T05:51:54.070538+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTQCHYLSJYXYSK6Z","created_at":"2026-07-05T05:51:54.070538+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTQCHYLS","created_at":"2026-07-05T05:51:54.070538+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15549","citing_title":"CTF4Nuclear: Common Task Framework for Nuclear Fission and Fusion Models","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2510.23166","citing_title":"Common Task Framework For a Critical Evaluation of Scientific Machine Learning Algorithms","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13807","citing_title":"Parallel Scan Recurrent Neural Quantum States for Scalable Variational Monte Carlo","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTQCHYLSJYXYSK6ZMK4LDTCEGK","json":"https://pith.science/pith/VTQCHYLSJYXYSK6ZMK4LDTCEGK.json","graph_json":"https://pith.science/api/pith-number/VTQCHYLSJYXYSK6ZMK4LDTCEGK/graph.json","events_json":"https://pith.science/api/pith-number/VTQCHYLSJYXYSK6ZMK4LDTCEGK/events.json","paper":"https://pith.science/paper/VTQCHYLS"},"agent_actions":{"view_html":"https://pith.science/pith/VTQCHYLSJYXYSK6ZMK4LDTCEGK","download_json":"https://pith.science/pith/VTQCHYLSJYXYSK6ZMK4LDTCEGK.json","view_paper":"https://pith.science/paper/VTQCHYLS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09489&json=true","fetch_graph":"https://pith.science/api/pith-number/VTQCHYLSJYXYSK6ZMK4LDTCEGK/graph.json","fetch_events":"https://pith.science/api/pith-number/VTQCHYLSJYXYSK6ZMK4LDTCEGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTQCHYLSJYXYSK6ZMK4LDTCEGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTQCHYLSJYXYSK6ZMK4LDTCEGK/action/storage_attestation","attest_author":"https://pith.science/pith/VTQCHYLSJYXYSK6ZMK4LDTCEGK/action/author_attestation","sign_citation":"https://pith.science/pith/VTQCHYLSJYXYSK6ZMK4LDTCEGK/action/citation_signature","submit_replication":"https://pith.science/pith/VTQCHYLSJYXYSK6ZMK4LDTCEGK/action/replication_record"}},"created_at":"2026-07-05T05:51:54.070538+00:00","updated_at":"2026-07-05T05:51:54.070538+00:00"}