{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QUDH4H7HAJQDNDKJCJBQS5BDLQ","short_pith_number":"pith:QUDH4H7H","schema_version":"1.0","canonical_sha256":"85067e1fe70260368d4912430974235c25971dbdd752401bada3423662fa5779","source":{"kind":"arxiv","id":"2206.12037","version":2},"attestation_state":"computed","paper":{"title":"How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Albert Gu, Aman Timalsina, Atri Rudra, Christopher R\\'e, Isys Johnson","submitted_at":"2022-06-24T02:24:41Z","abstract_excerpt":"Linear time-invariant state space models (SSM) are a classical model from engineering and statistics, that have recently been shown to be very promising in machine learning through the Structured State Space sequence model (S4). A core component of S4 involves initializing the SSM state matrix to a particular matrix called a HiPPO matrix, which was empirically important for S4's ability to handle long sequences. However, the specific matrix that S4 uses was actually derived in previous work for a particular time-varying dynamical system, and the use of this matrix as a time-invariant SSM had n"},"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":"2206.12037","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-24T02:24:41Z","cross_cats_sorted":[],"title_canon_sha256":"b75f6a2d845dc2c7ceda1c09c306641ef573735a3b076985a69205ce95ce5cef","abstract_canon_sha256":"b81d56f721e8fb32f7901380ffe6122f65f848e6f7fde386dac8bf177a8a10d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:14.977609Z","signature_b64":"MsuGc5euMLskXq0YNLpRn3iaNwEGCg4eNeYCMrEZ216aGaZQWq+w1QJT7uJ6I7GGefxbT14LwelI809eftsBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85067e1fe70260368d4912430974235c25971dbdd752401bada3423662fa5779","last_reissued_at":"2026-07-05T04:46:14.977183Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:14.977183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Albert Gu, Aman Timalsina, Atri Rudra, Christopher R\\'e, Isys Johnson","submitted_at":"2022-06-24T02:24:41Z","abstract_excerpt":"Linear time-invariant state space models (SSM) are a classical model from engineering and statistics, that have recently been shown to be very promising in machine learning through the Structured State Space sequence model (S4). A core component of S4 involves initializing the SSM state matrix to a particular matrix called a HiPPO matrix, which was empirically important for S4's ability to handle long sequences. However, the specific matrix that S4 uses was actually derived in previous work for a particular time-varying dynamical system, and the use of this matrix as a time-invariant SSM had n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12037","kind":"arxiv","version":2},"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/2206.12037/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":"2206.12037","created_at":"2026-07-05T04:46:14.977237+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.12037v2","created_at":"2026-07-05T04:46:14.977237+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12037","created_at":"2026-07-05T04:46:14.977237+00:00"},{"alias_kind":"pith_short_12","alias_value":"QUDH4H7HAJQD","created_at":"2026-07-05T04:46:14.977237+00:00"},{"alias_kind":"pith_short_16","alias_value":"QUDH4H7HAJQDNDKJ","created_at":"2026-07-05T04:46:14.977237+00:00"},{"alias_kind":"pith_short_8","alias_value":"QUDH4H7H","created_at":"2026-07-05T04:46:14.977237+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.18970","citing_title":"Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State- Space Architectures from S4 to Mamba","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2601.05527","citing_title":"DeMa: Dual-Path Delay-Aware Mamba for Efficient Multivariate Time Series Analysis","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11089","citing_title":"Structured State-Space Regularization for Generation-Friendly Image Tokenization","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2401.10774","citing_title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","ref_index":258,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08539","citing_title":"Continuity Laws for Sequential Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2111.00396","citing_title":"Efficiently Modeling Long Sequences with Structured State Spaces","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11089","citing_title":"Structured State-Space Regularization for Generation-Friendly Image Tokenization","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QUDH4H7HAJQDNDKJCJBQS5BDLQ","json":"https://pith.science/pith/QUDH4H7HAJQDNDKJCJBQS5BDLQ.json","graph_json":"https://pith.science/api/pith-number/QUDH4H7HAJQDNDKJCJBQS5BDLQ/graph.json","events_json":"https://pith.science/api/pith-number/QUDH4H7HAJQDNDKJCJBQS5BDLQ/events.json","paper":"https://pith.science/paper/QUDH4H7H"},"agent_actions":{"view_html":"https://pith.science/pith/QUDH4H7HAJQDNDKJCJBQS5BDLQ","download_json":"https://pith.science/pith/QUDH4H7HAJQDNDKJCJBQS5BDLQ.json","view_paper":"https://pith.science/paper/QUDH4H7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.12037&json=true","fetch_graph":"https://pith.science/api/pith-number/QUDH4H7HAJQDNDKJCJBQS5BDLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QUDH4H7HAJQDNDKJCJBQS5BDLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QUDH4H7HAJQDNDKJCJBQS5BDLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QUDH4H7HAJQDNDKJCJBQS5BDLQ/action/storage_attestation","attest_author":"https://pith.science/pith/QUDH4H7HAJQDNDKJCJBQS5BDLQ/action/author_attestation","sign_citation":"https://pith.science/pith/QUDH4H7HAJQDNDKJCJBQS5BDLQ/action/citation_signature","submit_replication":"https://pith.science/pith/QUDH4H7HAJQDNDKJCJBQS5BDLQ/action/replication_record"}},"created_at":"2026-07-05T04:46:14.977237+00:00","updated_at":"2026-07-05T04:46:14.977237+00:00"}