{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LUUGQPCH625PCMR2QQSNMW3UOY","short_pith_number":"pith:LUUGQPCH","schema_version":"1.0","canonical_sha256":"5d28683c47f6baf1323a8424d65b7476378301eb8492ebe8746ecc9e18e16c0f","source":{"kind":"arxiv","id":"2409.00563","version":3},"attestation_state":"computed","paper":{"title":"Sparse Mamba: Introducing Controllability, Observability, And Stability To Structural State Space Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ahmet Enis Cetin, Emadeldeen Hamdan, Hongyi Pan","submitted_at":"2024-08-31T23:25:12Z","abstract_excerpt":"Structured state space models' (SSMs) development in recent studies, such as Mamba and Mamba2, outperformed and solved the computational inefficiency of transformers and large language models at small to medium scale. In this work, we introduce the concept of controllability and observability to the original Mamba SSM's architecture in our Sparse-Mamba (S-Mamba) for natural language processing (NLP) applications. Moreover, we reinforce stability on the $nxn$ $A$ matrix on Mmaba2. The Mamba SSMs architecture drops the need for attention layers or multilayer perception blocks in transformers. Ho"},"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":"2409.00563","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-31T23:25:12Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"d85379c038f92370f687a808c0cd83f7f422aa10132b44fe28092a64fb06afe3","abstract_canon_sha256":"1c191381d1151b559d7474733d58236c49dde1d9a5d37b544d5a48665c4e8760"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:36.994178Z","signature_b64":"m3PQuMTTpDMxSfyct/P93YHhYR1nyLZAbH1BAlYkqfTcDFzHsCNm/e58ZGLra4tEqgxHuE1HU+cOKwrhAa+BCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d28683c47f6baf1323a8424d65b7476378301eb8492ebe8746ecc9e18e16c0f","last_reissued_at":"2026-07-05T09:33:36.993631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:36.993631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Mamba: Introducing Controllability, Observability, And Stability To Structural State Space Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ahmet Enis Cetin, Emadeldeen Hamdan, Hongyi Pan","submitted_at":"2024-08-31T23:25:12Z","abstract_excerpt":"Structured state space models' (SSMs) development in recent studies, such as Mamba and Mamba2, outperformed and solved the computational inefficiency of transformers and large language models at small to medium scale. In this work, we introduce the concept of controllability and observability to the original Mamba SSM's architecture in our Sparse-Mamba (S-Mamba) for natural language processing (NLP) applications. Moreover, we reinforce stability on the $nxn$ $A$ matrix on Mmaba2. The Mamba SSMs architecture drops the need for attention layers or multilayer perception blocks in transformers. Ho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00563","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/2409.00563/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":"2409.00563","created_at":"2026-07-05T09:33:36.993690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00563v3","created_at":"2026-07-05T09:33:36.993690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00563","created_at":"2026-07-05T09:33:36.993690+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUUGQPCH625P","created_at":"2026-07-05T09:33:36.993690+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUUGQPCH625PCMR2","created_at":"2026-07-05T09:33:36.993690+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUUGQPCH","created_at":"2026-07-05T09:33:36.993690+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.03433","citing_title":"When control meets large language models: From words to dynamics","ref_index":245,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUUGQPCH625PCMR2QQSNMW3UOY","json":"https://pith.science/pith/LUUGQPCH625PCMR2QQSNMW3UOY.json","graph_json":"https://pith.science/api/pith-number/LUUGQPCH625PCMR2QQSNMW3UOY/graph.json","events_json":"https://pith.science/api/pith-number/LUUGQPCH625PCMR2QQSNMW3UOY/events.json","paper":"https://pith.science/paper/LUUGQPCH"},"agent_actions":{"view_html":"https://pith.science/pith/LUUGQPCH625PCMR2QQSNMW3UOY","download_json":"https://pith.science/pith/LUUGQPCH625PCMR2QQSNMW3UOY.json","view_paper":"https://pith.science/paper/LUUGQPCH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00563&json=true","fetch_graph":"https://pith.science/api/pith-number/LUUGQPCH625PCMR2QQSNMW3UOY/graph.json","fetch_events":"https://pith.science/api/pith-number/LUUGQPCH625PCMR2QQSNMW3UOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUUGQPCH625PCMR2QQSNMW3UOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUUGQPCH625PCMR2QQSNMW3UOY/action/storage_attestation","attest_author":"https://pith.science/pith/LUUGQPCH625PCMR2QQSNMW3UOY/action/author_attestation","sign_citation":"https://pith.science/pith/LUUGQPCH625PCMR2QQSNMW3UOY/action/citation_signature","submit_replication":"https://pith.science/pith/LUUGQPCH625PCMR2QQSNMW3UOY/action/replication_record"}},"created_at":"2026-07-05T09:33:36.993690+00:00","updated_at":"2026-07-05T09:33:36.993690+00:00"}