{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EDO7Q5KEDLPINGMVBN32CVVY7Q","short_pith_number":"pith:EDO7Q5KE","schema_version":"1.0","canonical_sha256":"20ddf875441ade8699950b77a156b8fc010a8e1eb6f3f2751e4a0d5f65d5e8f5","source":{"kind":"arxiv","id":"2409.18962","version":1},"attestation_state":"computed","paper":{"title":"Exploring Token Pruning in Vision State Space Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hangyu Zheng, Pu Zhao, Stratis Ioannidis, Wei Niu, Xuan Shen, Yanzhi Wang, Yifan Gong, Yushu Wu, Zhenglun Kong, Zheng Zhan, Zichong Meng","submitted_at":"2024-09-27T17:59:50Z","abstract_excerpt":"State Space Models (SSMs) have the advantage of keeping linear computational complexity compared to attention modules in transformers, and have been applied to vision tasks as a new type of powerful vision foundation model. Inspired by the observations that the final prediction in vision transformers (ViTs) is only based on a subset of most informative tokens, we take the novel step of enhancing the efficiency of SSM-based vision models through token-based pruning. However, direct applications of existing token pruning techniques designed for ViTs fail to deliver good performance, even with ex"},"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":"2409.18962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-27T17:59:50Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"adde86372677846b80733fbd34683f0350d9dff995f0bc435da9424bc193f06c","abstract_canon_sha256":"d1bfabf4c438ce0fff0dce18f156b9f7955e3c50303894425d08538f50fe3127"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:50.495472Z","signature_b64":"QysCgol2fV7lDwKWjP7OzXZuzpcWIrijNxBECQIZndq5gamNBGdMOcdgAGx6JFVf8fxtzwSngkNgr8xyRtl8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20ddf875441ade8699950b77a156b8fc010a8e1eb6f3f2751e4a0d5f65d5e8f5","last_reissued_at":"2026-07-05T09:12:50.495052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:50.495052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Token Pruning in Vision State Space Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hangyu Zheng, Pu Zhao, Stratis Ioannidis, Wei Niu, Xuan Shen, Yanzhi Wang, Yifan Gong, Yushu Wu, Zhenglun Kong, Zheng Zhan, Zichong Meng","submitted_at":"2024-09-27T17:59:50Z","abstract_excerpt":"State Space Models (SSMs) have the advantage of keeping linear computational complexity compared to attention modules in transformers, and have been applied to vision tasks as a new type of powerful vision foundation model. Inspired by the observations that the final prediction in vision transformers (ViTs) is only based on a subset of most informative tokens, we take the novel step of enhancing the efficiency of SSM-based vision models through token-based pruning. However, direct applications of existing token pruning techniques designed for ViTs fail to deliver good performance, even with ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18962","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/2409.18962/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":"2409.18962","created_at":"2026-07-05T09:12:50.495105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.18962v1","created_at":"2026-07-05T09:12:50.495105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18962","created_at":"2026-07-05T09:12:50.495105+00:00"},{"alias_kind":"pith_short_12","alias_value":"EDO7Q5KEDLPI","created_at":"2026-07-05T09:12:50.495105+00:00"},{"alias_kind":"pith_short_16","alias_value":"EDO7Q5KEDLPINGMV","created_at":"2026-07-05T09:12:50.495105+00:00"},{"alias_kind":"pith_short_8","alias_value":"EDO7Q5KE","created_at":"2026-07-05T09:12:50.495105+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14042","citing_title":"Training-free Token Reduction for Vision Mamba","ref_index":55,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EDO7Q5KEDLPINGMVBN32CVVY7Q","json":"https://pith.science/pith/EDO7Q5KEDLPINGMVBN32CVVY7Q.json","graph_json":"https://pith.science/api/pith-number/EDO7Q5KEDLPINGMVBN32CVVY7Q/graph.json","events_json":"https://pith.science/api/pith-number/EDO7Q5KEDLPINGMVBN32CVVY7Q/events.json","paper":"https://pith.science/paper/EDO7Q5KE"},"agent_actions":{"view_html":"https://pith.science/pith/EDO7Q5KEDLPINGMVBN32CVVY7Q","download_json":"https://pith.science/pith/EDO7Q5KEDLPINGMVBN32CVVY7Q.json","view_paper":"https://pith.science/paper/EDO7Q5KE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.18962&json=true","fetch_graph":"https://pith.science/api/pith-number/EDO7Q5KEDLPINGMVBN32CVVY7Q/graph.json","fetch_events":"https://pith.science/api/pith-number/EDO7Q5KEDLPINGMVBN32CVVY7Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EDO7Q5KEDLPINGMVBN32CVVY7Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EDO7Q5KEDLPINGMVBN32CVVY7Q/action/storage_attestation","attest_author":"https://pith.science/pith/EDO7Q5KEDLPINGMVBN32CVVY7Q/action/author_attestation","sign_citation":"https://pith.science/pith/EDO7Q5KEDLPINGMVBN32CVVY7Q/action/citation_signature","submit_replication":"https://pith.science/pith/EDO7Q5KEDLPINGMVBN32CVVY7Q/action/replication_record"}},"created_at":"2026-07-05T09:12:50.495105+00:00","updated_at":"2026-07-05T09:12:50.495105+00:00"}