{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5EVQTZ2OQICR6ERHWFJKMYSZDN","short_pith_number":"pith:5EVQTZ2O","schema_version":"1.0","canonical_sha256":"e92b09e74e82051f1227b152a662591b51e37f4bdd26f5163a1d2013974dfa10","source":{"kind":"arxiv","id":"2203.14343","version":3},"attestation_state":"computed","paper":{"title":"Diagonal State Spaces are as Effective as Structured State Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Albert Gu, Ankit Gupta, Jonathan Berant","submitted_at":"2022-03-27T16:30:33Z","abstract_excerpt":"Modeling long range dependencies in sequential data is a fundamental step towards attaining human-level performance in many modalities such as text, vision, audio and video. While attention-based models are a popular and effective choice in modeling short-range interactions, their performance on tasks requiring long range reasoning has been largely inadequate. In an exciting result, Gu et al. (ICLR 2022) proposed the $\\textit{Structured State Space}$ (S4) architecture delivering large gains over state-of-the-art models on several long-range tasks across various modalities. The core proposition"},"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":"2203.14343","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-27T16:30:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ea2efe704e5346695f62562a0e51c6e9536c5d407b6b0054f1f1e26ed519b6ff","abstract_canon_sha256":"9a394466cf1918de736f4e8bdd7c22f77f7120e5d64e4c04ee38cf7488f35813"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:39.935468Z","signature_b64":"x52g/V8M0fpi9tFLDW5i8aSPeasfh1mdWtkDnfap4j3rmahJb37jX5pkGusTmIfvRLg/RG0mz6cYGMutN+iNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e92b09e74e82051f1227b152a662591b51e37f4bdd26f5163a1d2013974dfa10","last_reissued_at":"2026-07-05T04:24:39.934986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:39.934986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diagonal State Spaces are as Effective as Structured State Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Albert Gu, Ankit Gupta, Jonathan Berant","submitted_at":"2022-03-27T16:30:33Z","abstract_excerpt":"Modeling long range dependencies in sequential data is a fundamental step towards attaining human-level performance in many modalities such as text, vision, audio and video. While attention-based models are a popular and effective choice in modeling short-range interactions, their performance on tasks requiring long range reasoning has been largely inadequate. In an exciting result, Gu et al. (ICLR 2022) proposed the $\\textit{Structured State Space}$ (S4) architecture delivering large gains over state-of-the-art models on several long-range tasks across various modalities. The core proposition"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14343","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/2203.14343/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":"2203.14343","created_at":"2026-07-05T04:24:39.935045+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.14343v3","created_at":"2026-07-05T04:24:39.935045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14343","created_at":"2026-07-05T04:24:39.935045+00:00"},{"alias_kind":"pith_short_12","alias_value":"5EVQTZ2OQICR","created_at":"2026-07-05T04:24:39.935045+00:00"},{"alias_kind":"pith_short_16","alias_value":"5EVQTZ2OQICR6ERH","created_at":"2026-07-05T04:24:39.935045+00:00"},{"alias_kind":"pith_short_8","alias_value":"5EVQTZ2O","created_at":"2026-07-05T04:24:39.935045+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23332","citing_title":"Don't Listen to Me: A Lightweight, Low-Latency Model for Own-Voice Cancellation in Far-Field Speech Enhancement","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11287","citing_title":"Beyond Similarity: Temporal Operator Attention for Time Series Analysis","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16341","citing_title":"Deep Learning for Virtual Reality User Identification: A Benchmark","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2312.06635","citing_title":"Gated Linear Attention Transformers with Hardware-Efficient Training","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11287","citing_title":"Beyond Similarity: Temporal Operator Attention for Time Series Analysis","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5EVQTZ2OQICR6ERHWFJKMYSZDN","json":"https://pith.science/pith/5EVQTZ2OQICR6ERHWFJKMYSZDN.json","graph_json":"https://pith.science/api/pith-number/5EVQTZ2OQICR6ERHWFJKMYSZDN/graph.json","events_json":"https://pith.science/api/pith-number/5EVQTZ2OQICR6ERHWFJKMYSZDN/events.json","paper":"https://pith.science/paper/5EVQTZ2O"},"agent_actions":{"view_html":"https://pith.science/pith/5EVQTZ2OQICR6ERHWFJKMYSZDN","download_json":"https://pith.science/pith/5EVQTZ2OQICR6ERHWFJKMYSZDN.json","view_paper":"https://pith.science/paper/5EVQTZ2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.14343&json=true","fetch_graph":"https://pith.science/api/pith-number/5EVQTZ2OQICR6ERHWFJKMYSZDN/graph.json","fetch_events":"https://pith.science/api/pith-number/5EVQTZ2OQICR6ERHWFJKMYSZDN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5EVQTZ2OQICR6ERHWFJKMYSZDN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5EVQTZ2OQICR6ERHWFJKMYSZDN/action/storage_attestation","attest_author":"https://pith.science/pith/5EVQTZ2OQICR6ERHWFJKMYSZDN/action/author_attestation","sign_citation":"https://pith.science/pith/5EVQTZ2OQICR6ERHWFJKMYSZDN/action/citation_signature","submit_replication":"https://pith.science/pith/5EVQTZ2OQICR6ERHWFJKMYSZDN/action/replication_record"}},"created_at":"2026-07-05T04:24:39.935045+00:00","updated_at":"2026-07-05T04:24:39.935045+00:00"}