{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EHES2LIOKMW37ZM5SR7JABF4KO","short_pith_number":"pith:EHES2LIO","schema_version":"1.0","canonical_sha256":"21c92d2d0e532dbfe59d947e9004bc53a4a5f4f29d6d1ea1d20cb104609d614f","source":{"kind":"arxiv","id":"2410.10382","version":1},"attestation_state":"computed","paper":{"title":"V2M: Visual 2-Dimensional Mamba for Image Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengkun Wang, Jie Zhou, Jiwen Lu, Wenzhao Zheng, Yuanhui Huang","submitted_at":"2024-10-14T11:11:06Z","abstract_excerpt":"Mamba has garnered widespread attention due to its flexible design and efficient hardware performance to process 1D sequences based on the state space model (SSM). Recent studies have attempted to apply Mamba to the visual domain by flattening 2D images into patches and then regarding them as a 1D sequence. To compensate for the 2D structure information loss (e.g., local similarity) of the original image, most existing methods focus on designing different orders to sequentially process the tokens, which could only alleviate this issue to some extent. In this paper, we propose a Visual 2-Dimens"},"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":"2410.10382","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T11:11:06Z","cross_cats_sorted":[],"title_canon_sha256":"2b807a1baaf71550a167e10800e0679dddd527fd1e30e966d400a666d7dfc3e8","abstract_canon_sha256":"4bfcf9e430ef5c9aae2f789be5f70c4d5624a0a264f3eb94623935cd493c9dec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:15.423443Z","signature_b64":"l+6XnrYEjnrt4QZUBK5+YBNL9iF7eqHcrb3auQFKpI+hpk1uvnOwdbQJDks0Y1gbgYkH/b7Q7m8FJYe786KkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21c92d2d0e532dbfe59d947e9004bc53a4a5f4f29d6d1ea1d20cb104609d614f","last_reissued_at":"2026-07-05T09:20:15.423007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:15.423007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"V2M: Visual 2-Dimensional Mamba for Image Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengkun Wang, Jie Zhou, Jiwen Lu, Wenzhao Zheng, Yuanhui Huang","submitted_at":"2024-10-14T11:11:06Z","abstract_excerpt":"Mamba has garnered widespread attention due to its flexible design and efficient hardware performance to process 1D sequences based on the state space model (SSM). Recent studies have attempted to apply Mamba to the visual domain by flattening 2D images into patches and then regarding them as a 1D sequence. To compensate for the 2D structure information loss (e.g., local similarity) of the original image, most existing methods focus on designing different orders to sequentially process the tokens, which could only alleviate this issue to some extent. In this paper, we propose a Visual 2-Dimens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10382","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/2410.10382/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":"2410.10382","created_at":"2026-07-05T09:20:15.423063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10382v1","created_at":"2026-07-05T09:20:15.423063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10382","created_at":"2026-07-05T09:20:15.423063+00:00"},{"alias_kind":"pith_short_12","alias_value":"EHES2LIOKMW3","created_at":"2026-07-05T09:20:15.423063+00:00"},{"alias_kind":"pith_short_16","alias_value":"EHES2LIOKMW37ZM5","created_at":"2026-07-05T09:20:15.423063+00:00"},{"alias_kind":"pith_short_8","alias_value":"EHES2LIO","created_at":"2026-07-05T09:20:15.423063+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25329","citing_title":"State Space Models Meet Remote Sensing: A Survey","ref_index":199,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11563","citing_title":"TCP-SSM: Efficient Vision State Space Models with Token-Conditioned Poles","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EHES2LIOKMW37ZM5SR7JABF4KO","json":"https://pith.science/pith/EHES2LIOKMW37ZM5SR7JABF4KO.json","graph_json":"https://pith.science/api/pith-number/EHES2LIOKMW37ZM5SR7JABF4KO/graph.json","events_json":"https://pith.science/api/pith-number/EHES2LIOKMW37ZM5SR7JABF4KO/events.json","paper":"https://pith.science/paper/EHES2LIO"},"agent_actions":{"view_html":"https://pith.science/pith/EHES2LIOKMW37ZM5SR7JABF4KO","download_json":"https://pith.science/pith/EHES2LIOKMW37ZM5SR7JABF4KO.json","view_paper":"https://pith.science/paper/EHES2LIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10382&json=true","fetch_graph":"https://pith.science/api/pith-number/EHES2LIOKMW37ZM5SR7JABF4KO/graph.json","fetch_events":"https://pith.science/api/pith-number/EHES2LIOKMW37ZM5SR7JABF4KO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EHES2LIOKMW37ZM5SR7JABF4KO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EHES2LIOKMW37ZM5SR7JABF4KO/action/storage_attestation","attest_author":"https://pith.science/pith/EHES2LIOKMW37ZM5SR7JABF4KO/action/author_attestation","sign_citation":"https://pith.science/pith/EHES2LIOKMW37ZM5SR7JABF4KO/action/citation_signature","submit_replication":"https://pith.science/pith/EHES2LIOKMW37ZM5SR7JABF4KO/action/replication_record"}},"created_at":"2026-07-05T09:20:15.423063+00:00","updated_at":"2026-07-05T09:20:15.423063+00:00"}