{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YASV6WIF7MMOZ4M23PUR567DAM","short_pith_number":"pith:YASV6WIF","schema_version":"1.0","canonical_sha256":"c0255f5905fb18ecf19adbe91efbe3031a688fec158f45c6f156adc971ce51a6","source":{"kind":"arxiv","id":"2206.11893","version":2},"attestation_state":"computed","paper":{"title":"On the Parameterization and Initialization of Diagonal State Space Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Albert Gu, Ankit Gupta, Christopher R\\'e, Karan Goel","submitted_at":"2022-06-23T17:58:39Z","abstract_excerpt":"State space models (SSM) have recently been shown to be very effective as a deep learning layer as a promising alternative to sequence models such as RNNs, CNNs, or Transformers. The first version to show this potential was the S4 model, which is particularly effective on tasks involving long-range dependencies by using a prescribed state matrix called the HiPPO matrix. While this has an interpretable mathematical mechanism for modeling long dependencies, it introduces a custom representation and algorithm that can be difficult to implement. On the other hand, a recent variant of S4 called DSS"},"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":"2206.11893","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-23T17:58:39Z","cross_cats_sorted":[],"title_canon_sha256":"a1eafce19736fdb4431f2cdba66477c8d2a9572ae10923ed2fdf8914d2c44ea0","abstract_canon_sha256":"4d1a662f6d3083ff5b21cee5c0c696a204660277f5d5cb3ab439bc63a98b472d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:14.946818Z","signature_b64":"Wd1n/Mk5QSdwfA1BwCshDGkBmDNXeCpW3UK+B1cmLbT9ZQa2xAWEZHRDoGIeO9JOWPhrjLRGSRaKsDPgBGDMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0255f5905fb18ecf19adbe91efbe3031a688fec158f45c6f156adc971ce51a6","last_reissued_at":"2026-07-05T04:46:14.946411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:14.946411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Parameterization and Initialization of Diagonal State Space Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Albert Gu, Ankit Gupta, Christopher R\\'e, Karan Goel","submitted_at":"2022-06-23T17:58:39Z","abstract_excerpt":"State space models (SSM) have recently been shown to be very effective as a deep learning layer as a promising alternative to sequence models such as RNNs, CNNs, or Transformers. The first version to show this potential was the S4 model, which is particularly effective on tasks involving long-range dependencies by using a prescribed state matrix called the HiPPO matrix. While this has an interpretable mathematical mechanism for modeling long dependencies, it introduces a custom representation and algorithm that can be difficult to implement. On the other hand, a recent variant of S4 called DSS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.11893","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/2206.11893/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":"2206.11893","created_at":"2026-07-05T04:46:14.946465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.11893v2","created_at":"2026-07-05T04:46:14.946465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.11893","created_at":"2026-07-05T04:46:14.946465+00:00"},{"alias_kind":"pith_short_12","alias_value":"YASV6WIF7MMO","created_at":"2026-07-05T04:46:14.946465+00:00"},{"alias_kind":"pith_short_16","alias_value":"YASV6WIF7MMOZ4M2","created_at":"2026-07-05T04:46:14.946465+00:00"},{"alias_kind":"pith_short_8","alias_value":"YASV6WIF","created_at":"2026-07-05T04:46:14.946465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11049","citing_title":"Free Parametrization of L_2-Bounded Structured State-Space Controllers for Nonlinear Control with Stability Guarantees","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2503.23818","citing_title":"L2RU: a Structured State Space Model with prescribed L2-bound","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21070","citing_title":"Towards Understanding Self-Pretraining for Sequence Classification","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07483","citing_title":"Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2111.00396","citing_title":"Efficiently Modeling Long Sequences with Structured State Spaces","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07483","citing_title":"Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18580","citing_title":"Sessa: Selective State Space Attention","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YASV6WIF7MMOZ4M23PUR567DAM","json":"https://pith.science/pith/YASV6WIF7MMOZ4M23PUR567DAM.json","graph_json":"https://pith.science/api/pith-number/YASV6WIF7MMOZ4M23PUR567DAM/graph.json","events_json":"https://pith.science/api/pith-number/YASV6WIF7MMOZ4M23PUR567DAM/events.json","paper":"https://pith.science/paper/YASV6WIF"},"agent_actions":{"view_html":"https://pith.science/pith/YASV6WIF7MMOZ4M23PUR567DAM","download_json":"https://pith.science/pith/YASV6WIF7MMOZ4M23PUR567DAM.json","view_paper":"https://pith.science/paper/YASV6WIF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.11893&json=true","fetch_graph":"https://pith.science/api/pith-number/YASV6WIF7MMOZ4M23PUR567DAM/graph.json","fetch_events":"https://pith.science/api/pith-number/YASV6WIF7MMOZ4M23PUR567DAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YASV6WIF7MMOZ4M23PUR567DAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YASV6WIF7MMOZ4M23PUR567DAM/action/storage_attestation","attest_author":"https://pith.science/pith/YASV6WIF7MMOZ4M23PUR567DAM/action/author_attestation","sign_citation":"https://pith.science/pith/YASV6WIF7MMOZ4M23PUR567DAM/action/citation_signature","submit_replication":"https://pith.science/pith/YASV6WIF7MMOZ4M23PUR567DAM/action/replication_record"}},"created_at":"2026-07-05T04:46:14.946465+00:00","updated_at":"2026-07-05T04:46:14.946465+00:00"}