{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N3APXQDF5DIHCFEIGBNVTXBWQB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1dcf9b6e67d76165cd4fa699f3829d5352855fa095195018f98e28cc58f11450","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T23:02:45Z","title_canon_sha256":"9f4370c0f15b9a79a8d6ab0a9fcd1aecab40e6662fd8e7dfb2b3d028d79d66ab"},"schema_version":"1.0","source":{"id":"2407.08083","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08083","created_at":"2026-07-05T10:38:34Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08083v2","created_at":"2026-07-05T10:38:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08083","created_at":"2026-07-05T10:38:34Z"},{"alias_kind":"pith_short_12","alias_value":"N3APXQDF5DIH","created_at":"2026-07-05T10:38:34Z"},{"alias_kind":"pith_short_16","alias_value":"N3APXQDF5DIHCFEI","created_at":"2026-07-05T10:38:34Z"},{"alias_kind":"pith_short_8","alias_value":"N3APXQDF","created_at":"2026-07-05T10:38:34Z"}],"graph_snapshots":[{"event_id":"sha256:2168ba28acadf0b2bc8131c15dbc7fcc62c63dc5bc3bcbb1c3bcec067970a502","target":"graph","created_at":"2026-07-05T10:38:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.08083/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ali Hatamizadeh, Jan Kautz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T23:02:45Z","title":"MambaVision: A Hybrid Mamba-Transformer Vision Backbone"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08083","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f92ecf0dcc0d4d000aa9c164897ead9a0612a592a432cd215bfaa3077892a76e","target":"record","created_at":"2026-07-05T10:38:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1dcf9b6e67d76165cd4fa699f3829d5352855fa095195018f98e28cc58f11450","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-10T23:02:45Z","title_canon_sha256":"9f4370c0f15b9a79a8d6ab0a9fcd1aecab40e6662fd8e7dfb2b3d028d79d66ab"},"schema_version":"1.0","source":{"id":"2407.08083","kind":"arxiv","version":2}},"canonical_sha256":"6ec0fbc065e8d0711488305b59dc368065710fc0c2344b8a61c0129d75e141ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ec0fbc065e8d0711488305b59dc368065710fc0c2344b8a61c0129d75e141ab","first_computed_at":"2026-07-05T10:38:34.676145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:34.676145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l4z+UCozWAVDmzAUecYXZJhquBvAauZO9CmXmcDp8zFb8lNcza+SQZt7jPcMlpBDceHLsIC9JyqCwQW2Z3RwAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:34.676640Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.08083","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f92ecf0dcc0d4d000aa9c164897ead9a0612a592a432cd215bfaa3077892a76e","sha256:2168ba28acadf0b2bc8131c15dbc7fcc62c63dc5bc3bcbb1c3bcec067970a502"],"state_sha256":"41ad6b6be794ffab8360d3036873c73dcba3d36420b1d6ab0d53e882b794bd96"}