{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6T2FSEAWI5DTA5MWFDEVHVWVUV","short_pith_number":"pith:6T2FSEAW","schema_version":"1.0","canonical_sha256":"f4f4591016474730759628c953d6d5a541fb7602e38278cf6d74c27f94d1aa84","source":{"kind":"arxiv","id":"2407.13772","version":2},"attestation_state":"computed","paper":{"title":"GroupMamba: Efficient Group-Based Visual State Space Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Shaker, Fahad Shahbaz Khan, Juergen Gall, Salman Khan, Syed Talal Wasim","submitted_at":"2024-07-18T17:59:58Z","abstract_excerpt":"State-space models (SSMs) have recently shown promise in capturing long-range dependencies with subquadratic computational complexity, making them attractive for various applications. However, purely SSM-based models face critical challenges related to stability and achieving state-of-the-art performance in computer vision tasks. Our paper addresses the challenges of scaling SSM-based models for computer vision, particularly the instability and inefficiency of large model sizes. We introduce a parameter-efficient modulated group mamba layer that divides the input channels into four groups and "},"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":"2407.13772","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-18T17:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"efe9486e23dfe732144312c182664c994787c23b753f44625f7bcf59812b33da","abstract_canon_sha256":"565941e584b389588d3576a30303a068f086c4a9bbbf18f137566a52012ecaff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:13.893867Z","signature_b64":"qVJ1WLLA/zegCHKtcKg7j76a8s1LuXwW5D5gQjHJwJ12E3h0h3Yw3aLf9lcFxxp0V3TdsW7sDZMD1StDUnPDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4f4591016474730759628c953d6d5a541fb7602e38278cf6d74c27f94d1aa84","last_reissued_at":"2026-07-05T10:41:13.893392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:13.893392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GroupMamba: Efficient Group-Based Visual State Space Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Shaker, Fahad Shahbaz Khan, Juergen Gall, Salman Khan, Syed Talal Wasim","submitted_at":"2024-07-18T17:59:58Z","abstract_excerpt":"State-space models (SSMs) have recently shown promise in capturing long-range dependencies with subquadratic computational complexity, making them attractive for various applications. However, purely SSM-based models face critical challenges related to stability and achieving state-of-the-art performance in computer vision tasks. Our paper addresses the challenges of scaling SSM-based models for computer vision, particularly the instability and inefficiency of large model sizes. We introduce a parameter-efficient modulated group mamba layer that divides the input channels into four groups and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13772","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/2407.13772/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":"2407.13772","created_at":"2026-07-05T10:41:13.893448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13772v2","created_at":"2026-07-05T10:41:13.893448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13772","created_at":"2026-07-05T10:41:13.893448+00:00"},{"alias_kind":"pith_short_12","alias_value":"6T2FSEAWI5DT","created_at":"2026-07-05T10:41:13.893448+00:00"},{"alias_kind":"pith_short_16","alias_value":"6T2FSEAWI5DTA5MW","created_at":"2026-07-05T10:41:13.893448+00:00"},{"alias_kind":"pith_short_8","alias_value":"6T2FSEAW","created_at":"2026-07-05T10:41:13.893448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24122","citing_title":"Bengal-HP_RU: A Dataset of Bengal People For Head Pose Estimation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14724","citing_title":"HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6T2FSEAWI5DTA5MWFDEVHVWVUV","json":"https://pith.science/pith/6T2FSEAWI5DTA5MWFDEVHVWVUV.json","graph_json":"https://pith.science/api/pith-number/6T2FSEAWI5DTA5MWFDEVHVWVUV/graph.json","events_json":"https://pith.science/api/pith-number/6T2FSEAWI5DTA5MWFDEVHVWVUV/events.json","paper":"https://pith.science/paper/6T2FSEAW"},"agent_actions":{"view_html":"https://pith.science/pith/6T2FSEAWI5DTA5MWFDEVHVWVUV","download_json":"https://pith.science/pith/6T2FSEAWI5DTA5MWFDEVHVWVUV.json","view_paper":"https://pith.science/paper/6T2FSEAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13772&json=true","fetch_graph":"https://pith.science/api/pith-number/6T2FSEAWI5DTA5MWFDEVHVWVUV/graph.json","fetch_events":"https://pith.science/api/pith-number/6T2FSEAWI5DTA5MWFDEVHVWVUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6T2FSEAWI5DTA5MWFDEVHVWVUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6T2FSEAWI5DTA5MWFDEVHVWVUV/action/storage_attestation","attest_author":"https://pith.science/pith/6T2FSEAWI5DTA5MWFDEVHVWVUV/action/author_attestation","sign_citation":"https://pith.science/pith/6T2FSEAWI5DTA5MWFDEVHVWVUV/action/citation_signature","submit_replication":"https://pith.science/pith/6T2FSEAWI5DTA5MWFDEVHVWVUV/action/replication_record"}},"created_at":"2026-07-05T10:41:13.893448+00:00","updated_at":"2026-07-05T10:41:13.893448+00:00"}