{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N3APXQDF5DIHCFEIGBNVTXBWQB","short_pith_number":"pith:N3APXQDF","schema_version":"1.0","canonical_sha256":"6ec0fbc065e8d0711488305b59dc368065710fc0c2344b8a61c0129d75e141ab","source":{"kind":"arxiv","id":"2407.08083","version":2},"attestation_state":"computed","paper":{"title":"MambaVision: A Hybrid Mamba-Transformer Vision Backbone","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Hatamizadeh, Jan Kautz","submitted_at":"2024-07-10T23:02:45Z","abstract_excerpt":"We propose a novel hybrid Mamba-Transformer backbone, MambaVision, specifically tailored for vision applications. Our core contribution includes redesigning the Mamba formulation to enhance its capability for efficient modeling of visual features. Through a comprehensive ablation study, we demonstrate the feasibility of integrating Vision Transformers (ViT) with Mamba. Our results show that equipping the Mamba architecture with self-attention blocks in the final layers greatly improves its capacity to capture long-range spatial dependencies. Based on these findings, we introduce a family of Ma"},"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":"2407.08083","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T23:02:45Z","cross_cats_sorted":[],"title_canon_sha256":"9f4370c0f15b9a79a8d6ab0a9fcd1aecab40e6662fd8e7dfb2b3d028d79d66ab","abstract_canon_sha256":"1dcf9b6e67d76165cd4fa699f3829d5352855fa095195018f98e28cc58f11450"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:34.676640Z","signature_b64":"l4z+UCozWAVDmzAUecYXZJhquBvAauZO9CmXmcDp8zFb8lNcza+SQZt7jPcMlpBDceHLsIC9JyqCwQW2Z3RwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ec0fbc065e8d0711488305b59dc368065710fc0c2344b8a61c0129d75e141ab","last_reissued_at":"2026-07-05T10:38:34.676145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:34.676145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MambaVision: A Hybrid Mamba-Transformer Vision Backbone","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ali Hatamizadeh, Jan Kautz","submitted_at":"2024-07-10T23:02:45Z","abstract_excerpt":"We propose a novel hybrid Mamba-Transformer backbone, MambaVision, specifically tailored for vision applications. Our core contribution includes redesigning the Mamba formulation to enhance its capability for efficient modeling of visual features. Through a comprehensive ablation study, we demonstrate the feasibility of integrating Vision Transformers (ViT) with Mamba. Our results show that equipping the Mamba architecture with self-attention blocks in the final layers greatly improves its capacity to capture long-range spatial dependencies. Based on these findings, we introduce a family of Ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08083","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/2407.08083/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":"2407.08083","created_at":"2026-07-05T10:38:34.676203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08083v2","created_at":"2026-07-05T10:38:34.676203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08083","created_at":"2026-07-05T10:38:34.676203+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3APXQDF5DIH","created_at":"2026-07-05T10:38:34.676203+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3APXQDF5DIHCFEI","created_at":"2026-07-05T10:38:34.676203+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3APXQDF","created_at":"2026-07-05T10:38:34.676203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20738","citing_title":"An approach with Visual and Tabular Mamba to multimodal medical data using Mixed Fusion","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2607.02158","citing_title":"Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUs","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00390","citing_title":"Zamba2-VL Technical Report","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03014","citing_title":"MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2408.01129","citing_title":"A Survey of Mamba","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2504.00470","citing_title":"Less is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14062","citing_title":"FractalMamba++: Scaling Vision Mamba Across Resolutions via Hilbert Fractal Geometry","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2505.18604","citing_title":"Exemplar-Free Continual Learning for State Space Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07819","citing_title":"Fusion Complexity Inversion: Why Simpler Cross View Modules Outperform SSMs and Cross View Attention Transformers for Pasture Biomass Regression","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14724","citing_title":"HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18721","citing_title":"A Controlled Benchmark of Visual State-Space Backbones with Domain-Shift and Boundary Analysis for Remote-Sensing Segmentation","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N3APXQDF5DIHCFEIGBNVTXBWQB","json":"https://pith.science/pith/N3APXQDF5DIHCFEIGBNVTXBWQB.json","graph_json":"https://pith.science/api/pith-number/N3APXQDF5DIHCFEIGBNVTXBWQB/graph.json","events_json":"https://pith.science/api/pith-number/N3APXQDF5DIHCFEIGBNVTXBWQB/events.json","paper":"https://pith.science/paper/N3APXQDF"},"agent_actions":{"view_html":"https://pith.science/pith/N3APXQDF5DIHCFEIGBNVTXBWQB","download_json":"https://pith.science/pith/N3APXQDF5DIHCFEIGBNVTXBWQB.json","view_paper":"https://pith.science/paper/N3APXQDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08083&json=true","fetch_graph":"https://pith.science/api/pith-number/N3APXQDF5DIHCFEIGBNVTXBWQB/graph.json","fetch_events":"https://pith.science/api/pith-number/N3APXQDF5DIHCFEIGBNVTXBWQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3APXQDF5DIHCFEIGBNVTXBWQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3APXQDF5DIHCFEIGBNVTXBWQB/action/storage_attestation","attest_author":"https://pith.science/pith/N3APXQDF5DIHCFEIGBNVTXBWQB/action/author_attestation","sign_citation":"https://pith.science/pith/N3APXQDF5DIHCFEIGBNVTXBWQB/action/citation_signature","submit_replication":"https://pith.science/pith/N3APXQDF5DIHCFEIGBNVTXBWQB/action/replication_record"}},"created_at":"2026-07-05T10:38:34.676203+00:00","updated_at":"2026-07-05T10:38:34.676203+00:00"}