{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VC7VOJVUC5757Y4R36PP7WN53M","short_pith_number":"pith:VC7VOJVU","schema_version":"1.0","canonical_sha256":"a8bf5726b4177fdfe391df9effd9bddb307e7b4cf316f3e4f9ba6a6172e9893c","source":{"kind":"arxiv","id":"2212.00768","version":3},"attestation_state":"computed","paper":{"title":"Simplifying and Understanding State Space Models with Diagonal Linear RNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Ankit Gupta, Harsh Mehta, Jonathan Berant","submitted_at":"2022-12-01T18:53:06Z","abstract_excerpt":"Sequence models based on linear state spaces (SSMs) have recently emerged as a promising choice of architecture for modeling long range dependencies across various modalities. However, they invariably rely on discretization of a continuous state space, which complicates their presentation and understanding. In this work, we dispose of the discretization step, and propose a model based on vanilla Diagonal Linear RNNs ($\\mathrm{DLR}$). We empirically show that, despite being conceptually much simpler, $\\mathrm{DLR}$ is as performant as previously-proposed SSMs on a variety of tasks and benchmark"},"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":"2212.00768","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-01T18:53:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"172d6f6d7baa6bdadfe76ea0795f5a1b335e5a6363a7456e3d0084f9f44ef60a","abstract_canon_sha256":"364cc8ea90e3f2324f32833dcc586e97768f6533ba1f073cbdd99c7321182c0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:33.312903Z","signature_b64":"v5IgEo7Q0OlHq/CRdStENjRclsjo0MqP0V/iuRhHhD8wsNv63hoDKgh081tAwciy94xTAXt1dWjoYo/XSGmeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8bf5726b4177fdfe391df9effd9bddb307e7b4cf316f3e4f9ba6a6172e9893c","last_reissued_at":"2026-07-05T07:12:33.312406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:33.312406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simplifying and Understanding State Space Models with Diagonal Linear RNNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Ankit Gupta, Harsh Mehta, Jonathan Berant","submitted_at":"2022-12-01T18:53:06Z","abstract_excerpt":"Sequence models based on linear state spaces (SSMs) have recently emerged as a promising choice of architecture for modeling long range dependencies across various modalities. However, they invariably rely on discretization of a continuous state space, which complicates their presentation and understanding. In this work, we dispose of the discretization step, and propose a model based on vanilla Diagonal Linear RNNs ($\\mathrm{DLR}$). We empirically show that, despite being conceptually much simpler, $\\mathrm{DLR}$ is as performant as previously-proposed SSMs on a variety of tasks and benchmark"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00768","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/2212.00768/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":"2212.00768","created_at":"2026-07-05T07:12:33.312463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.00768v3","created_at":"2026-07-05T07:12:33.312463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00768","created_at":"2026-07-05T07:12:33.312463+00:00"},{"alias_kind":"pith_short_12","alias_value":"VC7VOJVUC575","created_at":"2026-07-05T07:12:33.312463+00:00"},{"alias_kind":"pith_short_16","alias_value":"VC7VOJVUC5757Y4R","created_at":"2026-07-05T07:12:33.312463+00:00"},{"alias_kind":"pith_short_8","alias_value":"VC7VOJVU","created_at":"2026-07-05T07:12:33.312463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.21070","citing_title":"Towards Understanding Self-Pretraining for Sequence Classification","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2312.00752","citing_title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VC7VOJVUC5757Y4R36PP7WN53M","json":"https://pith.science/pith/VC7VOJVUC5757Y4R36PP7WN53M.json","graph_json":"https://pith.science/api/pith-number/VC7VOJVUC5757Y4R36PP7WN53M/graph.json","events_json":"https://pith.science/api/pith-number/VC7VOJVUC5757Y4R36PP7WN53M/events.json","paper":"https://pith.science/paper/VC7VOJVU"},"agent_actions":{"view_html":"https://pith.science/pith/VC7VOJVUC5757Y4R36PP7WN53M","download_json":"https://pith.science/pith/VC7VOJVUC5757Y4R36PP7WN53M.json","view_paper":"https://pith.science/paper/VC7VOJVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.00768&json=true","fetch_graph":"https://pith.science/api/pith-number/VC7VOJVUC5757Y4R36PP7WN53M/graph.json","fetch_events":"https://pith.science/api/pith-number/VC7VOJVUC5757Y4R36PP7WN53M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VC7VOJVUC5757Y4R36PP7WN53M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VC7VOJVUC5757Y4R36PP7WN53M/action/storage_attestation","attest_author":"https://pith.science/pith/VC7VOJVUC5757Y4R36PP7WN53M/action/author_attestation","sign_citation":"https://pith.science/pith/VC7VOJVUC5757Y4R36PP7WN53M/action/citation_signature","submit_replication":"https://pith.science/pith/VC7VOJVUC5757Y4R36PP7WN53M/action/replication_record"}},"created_at":"2026-07-05T07:12:33.312463+00:00","updated_at":"2026-07-05T07:12:33.312463+00:00"}