{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LOGWHXY67HVDN5G6L7TMRS7YLN","short_pith_number":"pith:LOGWHXY6","schema_version":"1.0","canonical_sha256":"5b8d63df1ef9ea36f4de5fe6c8cbf85b42745299968d6d01b0bebc666001f533","source":{"kind":"arxiv","id":"2403.10935","version":1},"attestation_state":"computed","paper":{"title":"Understanding Robustness of Visual State Space Models for Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Xu, Chengbin Du, Yanxi Li","submitted_at":"2024-03-16T14:23:17Z","abstract_excerpt":"Visual State Space Model (VMamba) has recently emerged as a promising architecture, exhibiting remarkable performance in various computer vision tasks. However, its robustness has not yet been thoroughly studied. In this paper, we delve into the robustness of this architecture through comprehensive investigations from multiple perspectives. Firstly, we investigate its robustness to adversarial attacks, employing both whole-image and patch-specific adversarial attacks. Results demonstrate superior adversarial robustness compared to Transformer architectures while revealing scalability weaknesse"},"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":"2403.10935","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-16T14:23:17Z","cross_cats_sorted":[],"title_canon_sha256":"010b18775eba6c11acad743acf6af7526ccb40ac72b90f5dd04551697a044bd7","abstract_canon_sha256":"6c65bc3945bfabc9cbd51ad96283835b6e174d9d93b5adfdeeb7c176abd306e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:09.137702Z","signature_b64":"dPyj3dSCbsXZAYb2Eb2rhkWfJfDKOGaaBSY9fqyOC/OQd1OJFHcBJ4uevN/chrCUjHa928qQ72OIdMAahhpeAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b8d63df1ef9ea36f4de5fe6c8cbf85b42745299968d6d01b0bebc666001f533","last_reissued_at":"2026-07-05T07:57:09.137252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:09.137252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Robustness of Visual State Space Models for Image Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Xu, Chengbin Du, Yanxi Li","submitted_at":"2024-03-16T14:23:17Z","abstract_excerpt":"Visual State Space Model (VMamba) has recently emerged as a promising architecture, exhibiting remarkable performance in various computer vision tasks. However, its robustness has not yet been thoroughly studied. In this paper, we delve into the robustness of this architecture through comprehensive investigations from multiple perspectives. Firstly, we investigate its robustness to adversarial attacks, employing both whole-image and patch-specific adversarial attacks. Results demonstrate superior adversarial robustness compared to Transformer architectures while revealing scalability weaknesse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10935","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/2403.10935/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":"2403.10935","created_at":"2026-07-05T07:57:09.137309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10935v1","created_at":"2026-07-05T07:57:09.137309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10935","created_at":"2026-07-05T07:57:09.137309+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOGWHXY67HVD","created_at":"2026-07-05T07:57:09.137309+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOGWHXY67HVDN5G6","created_at":"2026-07-05T07:57:09.137309+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOGWHXY6","created_at":"2026-07-05T07:57:09.137309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00746","citing_title":"Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LOGWHXY67HVDN5G6L7TMRS7YLN","json":"https://pith.science/pith/LOGWHXY67HVDN5G6L7TMRS7YLN.json","graph_json":"https://pith.science/api/pith-number/LOGWHXY67HVDN5G6L7TMRS7YLN/graph.json","events_json":"https://pith.science/api/pith-number/LOGWHXY67HVDN5G6L7TMRS7YLN/events.json","paper":"https://pith.science/paper/LOGWHXY6"},"agent_actions":{"view_html":"https://pith.science/pith/LOGWHXY67HVDN5G6L7TMRS7YLN","download_json":"https://pith.science/pith/LOGWHXY67HVDN5G6L7TMRS7YLN.json","view_paper":"https://pith.science/paper/LOGWHXY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10935&json=true","fetch_graph":"https://pith.science/api/pith-number/LOGWHXY67HVDN5G6L7TMRS7YLN/graph.json","fetch_events":"https://pith.science/api/pith-number/LOGWHXY67HVDN5G6L7TMRS7YLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOGWHXY67HVDN5G6L7TMRS7YLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOGWHXY67HVDN5G6L7TMRS7YLN/action/storage_attestation","attest_author":"https://pith.science/pith/LOGWHXY67HVDN5G6L7TMRS7YLN/action/author_attestation","sign_citation":"https://pith.science/pith/LOGWHXY67HVDN5G6L7TMRS7YLN/action/citation_signature","submit_replication":"https://pith.science/pith/LOGWHXY67HVDN5G6L7TMRS7YLN/action/replication_record"}},"created_at":"2026-07-05T07:57:09.137309+00:00","updated_at":"2026-07-05T07:57:09.137309+00:00"}