{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YAE5IE5M5MDAGKULGMZ6I5KXDS","short_pith_number":"pith:YAE5IE5M","schema_version":"1.0","canonical_sha256":"c009d413aceb06032a8b3333e475571cb0d92d2df7f7e7f7093ed039efe386cd","source":{"kind":"arxiv","id":"2310.01698","version":1},"attestation_state":"computed","paper":{"title":"Robustifying State-space Models for Long Sequences via Approximate Diagonalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Annan Yu, Arnur Nigmetov, Dmitriy Morozov, Michael W. Mahoney, N. Benjamin Erichson","submitted_at":"2023-10-02T23:36:13Z","abstract_excerpt":"State-space models (SSMs) have recently emerged as a framework for learning long-range sequence tasks. An example is the structured state-space sequence (S4) layer, which uses the diagonal-plus-low-rank structure of the HiPPO initialization framework. However, the complicated structure of the S4 layer poses challenges; and, in an effort to address these challenges, models such as S4D and S5 have considered a purely diagonal structure. This choice simplifies the implementation, improves computational efficiency, and allows channel communication. However, diagonalizing the HiPPO framework is its"},"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":"2310.01698","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-02T23:36:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3596931114f05ae9771d48fc36d759a2cf84a12750105615aec77efa8f259fd0","abstract_canon_sha256":"241707b26a20dbea5640cf83924d258988a8d49d844f2e8f3364c8d280885fa0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:44.941899Z","signature_b64":"2eaCTPzZ9AW2HV++A/Mn08HM5wEpF+iFEgxrYbHXAWbXmNXNb36Eril6xcgFfJAd5gxH9OJmnTqVFw8Hya1jBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c009d413aceb06032a8b3333e475571cb0d92d2df7f7e7f7093ed039efe386cd","last_reissued_at":"2026-07-05T06:56:44.941418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:44.941418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustifying State-space Models for Long Sequences via Approximate Diagonalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Annan Yu, Arnur Nigmetov, Dmitriy Morozov, Michael W. Mahoney, N. Benjamin Erichson","submitted_at":"2023-10-02T23:36:13Z","abstract_excerpt":"State-space models (SSMs) have recently emerged as a framework for learning long-range sequence tasks. An example is the structured state-space sequence (S4) layer, which uses the diagonal-plus-low-rank structure of the HiPPO initialization framework. However, the complicated structure of the S4 layer poses challenges; and, in an effort to address these challenges, models such as S4D and S5 have considered a purely diagonal structure. This choice simplifies the implementation, improves computational efficiency, and allows channel communication. However, diagonalizing the HiPPO framework is its"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01698","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/2310.01698/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":"2310.01698","created_at":"2026-07-05T06:56:44.941477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01698v1","created_at":"2026-07-05T06:56:44.941477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01698","created_at":"2026-07-05T06:56:44.941477+00:00"},{"alias_kind":"pith_short_12","alias_value":"YAE5IE5M5MDA","created_at":"2026-07-05T06:56:44.941477+00:00"},{"alias_kind":"pith_short_16","alias_value":"YAE5IE5M5MDAGKUL","created_at":"2026-07-05T06:56:44.941477+00:00"},{"alias_kind":"pith_short_8","alias_value":"YAE5IE5M","created_at":"2026-07-05T06:56:44.941477+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08539","citing_title":"Continuity Laws for Sequential Models","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YAE5IE5M5MDAGKULGMZ6I5KXDS","json":"https://pith.science/pith/YAE5IE5M5MDAGKULGMZ6I5KXDS.json","graph_json":"https://pith.science/api/pith-number/YAE5IE5M5MDAGKULGMZ6I5KXDS/graph.json","events_json":"https://pith.science/api/pith-number/YAE5IE5M5MDAGKULGMZ6I5KXDS/events.json","paper":"https://pith.science/paper/YAE5IE5M"},"agent_actions":{"view_html":"https://pith.science/pith/YAE5IE5M5MDAGKULGMZ6I5KXDS","download_json":"https://pith.science/pith/YAE5IE5M5MDAGKULGMZ6I5KXDS.json","view_paper":"https://pith.science/paper/YAE5IE5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01698&json=true","fetch_graph":"https://pith.science/api/pith-number/YAE5IE5M5MDAGKULGMZ6I5KXDS/graph.json","fetch_events":"https://pith.science/api/pith-number/YAE5IE5M5MDAGKULGMZ6I5KXDS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YAE5IE5M5MDAGKULGMZ6I5KXDS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YAE5IE5M5MDAGKULGMZ6I5KXDS/action/storage_attestation","attest_author":"https://pith.science/pith/YAE5IE5M5MDAGKULGMZ6I5KXDS/action/author_attestation","sign_citation":"https://pith.science/pith/YAE5IE5M5MDAGKULGMZ6I5KXDS/action/citation_signature","submit_replication":"https://pith.science/pith/YAE5IE5M5MDAGKULGMZ6I5KXDS/action/replication_record"}},"created_at":"2026-07-05T06:56:44.941477+00:00","updated_at":"2026-07-05T06:56:44.941477+00:00"}