{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MS5L37HLVC74TYPF7CCM7JQENH","short_pith_number":"pith:MS5L37HL","schema_version":"1.0","canonical_sha256":"64babdfceba8bfc9e1e5f884cfa60469cb226030a730fcc3c93aeb3e062344da","source":{"kind":"arxiv","id":"2306.06635","version":1},"attestation_state":"computed","paper":{"title":"2-D SSM: A General Spatial Layer for Visual Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ethan Baron, Itamar Zimerman, Lior Wolf","submitted_at":"2023-06-11T09:41:37Z","abstract_excerpt":"A central objective in computer vision is to design models with appropriate 2-D inductive bias. Desiderata for 2D inductive bias include two-dimensional position awareness, dynamic spatial locality, and translation and permutation invariance. To address these goals, we leverage an expressive variation of the multidimensional State Space Model (SSM). Our approach introduces efficient parameterization, accelerated computation, and a suitable normalization scheme. Empirically, we observe that incorporating our layer at the beginning of each transformer block of Vision Transformers (ViT) significa"},"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":"2306.06635","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-06-11T09:41:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6c96da63f0cf1adc57e99b0a936983c65af67470e008bf0b4d80153d204c7654","abstract_canon_sha256":"7656e1b0d694bc277d9b6762be21749cabcae0b2fe2d37599735dd004afe1a58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:27.118723Z","signature_b64":"8/izp0GbR4dJ5r0mzZbgVQjmM6p+31nyrJ7WagbJFVB9I1s9dn65rJeDZQozscCm54HU2O8eJa4H8cgAi2WRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64babdfceba8bfc9e1e5f884cfa60469cb226030a730fcc3c93aeb3e062344da","last_reissued_at":"2026-07-05T06:19:27.118213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:27.118213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"2-D SSM: A General Spatial Layer for Visual Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Ethan Baron, Itamar Zimerman, Lior Wolf","submitted_at":"2023-06-11T09:41:37Z","abstract_excerpt":"A central objective in computer vision is to design models with appropriate 2-D inductive bias. Desiderata for 2D inductive bias include two-dimensional position awareness, dynamic spatial locality, and translation and permutation invariance. To address these goals, we leverage an expressive variation of the multidimensional State Space Model (SSM). Our approach introduces efficient parameterization, accelerated computation, and a suitable normalization scheme. Empirically, we observe that incorporating our layer at the beginning of each transformer block of Vision Transformers (ViT) significa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.06635","kind":"arxiv","version":1},"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/2306.06635/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":"2306.06635","created_at":"2026-07-05T06:19:27.118276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.06635v1","created_at":"2026-07-05T06:19:27.118276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.06635","created_at":"2026-07-05T06:19:27.118276+00:00"},{"alias_kind":"pith_short_12","alias_value":"MS5L37HLVC74","created_at":"2026-07-05T06:19:27.118276+00:00"},{"alias_kind":"pith_short_16","alias_value":"MS5L37HLVC74TYPF","created_at":"2026-07-05T06:19:27.118276+00:00"},{"alias_kind":"pith_short_8","alias_value":"MS5L37HL","created_at":"2026-07-05T06:19:27.118276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00746","citing_title":"Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2401.09417","citing_title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22177","citing_title":"Uni-Encoder Meets Multi-Encoders: Representation Before Fusion for Brain Tumor Segmentation with Missing Modalities","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08073","citing_title":"EmambaIR: Efficient Visual State Space Model for Event-guided Image Reconstruction","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MS5L37HLVC74TYPF7CCM7JQENH","json":"https://pith.science/pith/MS5L37HLVC74TYPF7CCM7JQENH.json","graph_json":"https://pith.science/api/pith-number/MS5L37HLVC74TYPF7CCM7JQENH/graph.json","events_json":"https://pith.science/api/pith-number/MS5L37HLVC74TYPF7CCM7JQENH/events.json","paper":"https://pith.science/paper/MS5L37HL"},"agent_actions":{"view_html":"https://pith.science/pith/MS5L37HLVC74TYPF7CCM7JQENH","download_json":"https://pith.science/pith/MS5L37HLVC74TYPF7CCM7JQENH.json","view_paper":"https://pith.science/paper/MS5L37HL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.06635&json=true","fetch_graph":"https://pith.science/api/pith-number/MS5L37HLVC74TYPF7CCM7JQENH/graph.json","fetch_events":"https://pith.science/api/pith-number/MS5L37HLVC74TYPF7CCM7JQENH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MS5L37HLVC74TYPF7CCM7JQENH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MS5L37HLVC74TYPF7CCM7JQENH/action/storage_attestation","attest_author":"https://pith.science/pith/MS5L37HLVC74TYPF7CCM7JQENH/action/author_attestation","sign_citation":"https://pith.science/pith/MS5L37HLVC74TYPF7CCM7JQENH/action/citation_signature","submit_replication":"https://pith.science/pith/MS5L37HLVC74TYPF7CCM7JQENH/action/replication_record"}},"created_at":"2026-07-05T06:19:27.118276+00:00","updated_at":"2026-07-05T06:19:27.118276+00:00"}