{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:26PIX5J4F6CNRT2HX4A7LYVMO6","short_pith_number":"pith:26PIX5J4","schema_version":"1.0","canonical_sha256":"d79e8bf53c2f84d8cf47bf01f5e2ac778b6439ce7a3f3129cedb2a2df6ba4e51","source":{"kind":"arxiv","id":"2403.17695","version":2},"attestation_state":"computed","paper":{"title":"PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenhongyi Yang, Elliot J. Crowley, Jiaming Liu, Linus Ericsson, Miguel Espinosa, Zehui Chen, Zhenyu Wang","submitted_at":"2024-03-26T13:35:10Z","abstract_excerpt":"We present PlainMamba: a simple non-hierarchical state space model (SSM) designed for general visual recognition. The recent Mamba model has shown how SSMs can be highly competitive with other architectures on sequential data and initial attempts have been made to apply it to images. In this paper, we further adapt the selective scanning process of Mamba to the visual domain, enhancing its ability to learn features from two-dimensional images by (i) a continuous 2D scanning process that improves spatial continuity by ensuring adjacency of tokens in the scanning sequence, and (ii) direction-awa"},"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":"2403.17695","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-26T13:35:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"51e5f14b0bb14933c2b52c7987f8fd8b858baf5eef71aad030361b79869d2f79","abstract_canon_sha256":"671aec01ef0ee3430f5c5740f10129cfb79bd0b2f1cac62cb129e8d2491efb48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:34.536301Z","signature_b64":"MoD5NQB96TH7KBIrhQ0tIQ+ny0o7IQcQlnyW5m8pWKfLbosq3KZnoQvrk57Dva5y6/yW2owP1/Y+nf+/5IQcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d79e8bf53c2f84d8cf47bf01f5e2ac778b6439ce7a3f3129cedb2a2df6ba4e51","last_reissued_at":"2026-07-05T08:55:34.535879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:34.535879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenhongyi Yang, Elliot J. Crowley, Jiaming Liu, Linus Ericsson, Miguel Espinosa, Zehui Chen, Zhenyu Wang","submitted_at":"2024-03-26T13:35:10Z","abstract_excerpt":"We present PlainMamba: a simple non-hierarchical state space model (SSM) designed for general visual recognition. The recent Mamba model has shown how SSMs can be highly competitive with other architectures on sequential data and initial attempts have been made to apply it to images. In this paper, we further adapt the selective scanning process of Mamba to the visual domain, enhancing its ability to learn features from two-dimensional images by (i) a continuous 2D scanning process that improves spatial continuity by ensuring adjacency of tokens in the scanning sequence, and (ii) direction-awa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17695","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/2403.17695/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":"2403.17695","created_at":"2026-07-05T08:55:34.535936+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17695v2","created_at":"2026-07-05T08:55:34.535936+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17695","created_at":"2026-07-05T08:55:34.535936+00:00"},{"alias_kind":"pith_short_12","alias_value":"26PIX5J4F6CN","created_at":"2026-07-05T08:55:34.535936+00:00"},{"alias_kind":"pith_short_16","alias_value":"26PIX5J4F6CNRT2H","created_at":"2026-07-05T08:55:34.535936+00:00"},{"alias_kind":"pith_short_8","alias_value":"26PIX5J4","created_at":"2026-07-05T08:55:34.535936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26849","citing_title":"Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23126","citing_title":"MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19932","citing_title":"Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14799","citing_title":"Can Visual Mamba Improve AI-Generated Image Detection? An In-Depth Investigation","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00746","citing_title":"Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2408.01129","citing_title":"A Survey of Mamba","ref_index":213,"is_internal_anchor":false},{"citing_arxiv_id":"2501.15461","citing_title":"Mamba-Based Graph Convolutional Networks: Tackling Over-smoothing with Selective State Space","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14062","citing_title":"FractalMamba++: Scaling Vision Mamba Across Resolutions via Hilbert Fractal Geometry","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14926","citing_title":"SCRWKV: Ultra-Compact Structure-Calibrated Vision-RWKV for Topological Crack Segmentation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21308","citing_title":"Deformba: Vision State Space Model with Adaptive State Fusion","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25545","citing_title":"TopoMamba: Topology-Aware Scanning and Fusion for Segmenting Heterogeneous Medical Visual Media","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08038","citing_title":"Beyond Mamba: Enhancing State-space Models with Deformable Dilated Convolutions for Multi-scale Traffic Object Detection","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14724","citing_title":"HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20606","citing_title":"Beyond ZOH: Advanced Discretization Strategies for Vision Mamba","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/26PIX5J4F6CNRT2HX4A7LYVMO6","json":"https://pith.science/pith/26PIX5J4F6CNRT2HX4A7LYVMO6.json","graph_json":"https://pith.science/api/pith-number/26PIX5J4F6CNRT2HX4A7LYVMO6/graph.json","events_json":"https://pith.science/api/pith-number/26PIX5J4F6CNRT2HX4A7LYVMO6/events.json","paper":"https://pith.science/paper/26PIX5J4"},"agent_actions":{"view_html":"https://pith.science/pith/26PIX5J4F6CNRT2HX4A7LYVMO6","download_json":"https://pith.science/pith/26PIX5J4F6CNRT2HX4A7LYVMO6.json","view_paper":"https://pith.science/paper/26PIX5J4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17695&json=true","fetch_graph":"https://pith.science/api/pith-number/26PIX5J4F6CNRT2HX4A7LYVMO6/graph.json","fetch_events":"https://pith.science/api/pith-number/26PIX5J4F6CNRT2HX4A7LYVMO6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26PIX5J4F6CNRT2HX4A7LYVMO6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26PIX5J4F6CNRT2HX4A7LYVMO6/action/storage_attestation","attest_author":"https://pith.science/pith/26PIX5J4F6CNRT2HX4A7LYVMO6/action/author_attestation","sign_citation":"https://pith.science/pith/26PIX5J4F6CNRT2HX4A7LYVMO6/action/citation_signature","submit_replication":"https://pith.science/pith/26PIX5J4F6CNRT2HX4A7LYVMO6/action/replication_record"}},"created_at":"2026-07-05T08:55:34.535936+00:00","updated_at":"2026-07-05T08:55:34.535936+00:00"}