{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:L7G4JCRWB2EPSKZ2JEQFGA7UER","short_pith_number":"pith:L7G4JCRW","schema_version":"1.0","canonical_sha256":"5fcdc48a360e88f92b3a49205303f4247132f13e126fd3e35649ed41eeedbfa7","source":{"kind":"arxiv","id":"2209.13802","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guodong Guo, Tianyi Wu, Xiangcheng Liu","submitted_at":"2022-09-28T03:07:32Z","abstract_excerpt":"Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts that the complexity is quadratic with respect to the token number, and many tokens containing only background regions do not truly contribute to the final prediction. Existing works either rely on additional modules to score the importance of individual tokens, or implement a fixed ratio pruning strategy for different input instances. In this work, we propose "},"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":"2209.13802","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-28T03:07:32Z","cross_cats_sorted":[],"title_canon_sha256":"9a1e609f1e4122362c35375bac4ebac6ed78a6aea480156105a005701b83865b","abstract_canon_sha256":"367fa6b4d5f3d90b2f77d54c98d118abc8f0c70b30551c4191a6c987807f31b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:14.274358Z","signature_b64":"yn9HhrfmX+/bYfvP5Zd6PyPo+3rBGFzwDu/TLsk3TMEC38U9OdLcaI7YSvx7lV4FlCEeRGRw8hlEGrCOpwDNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fcdc48a360e88f92b3a49205303f4247132f13e126fd3e35649ed41eeedbfa7","last_reissued_at":"2026-07-05T06:28:14.273865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:14.273865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guodong Guo, Tianyi Wu, Xiangcheng Liu","submitted_at":"2022-09-28T03:07:32Z","abstract_excerpt":"Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts that the complexity is quadratic with respect to the token number, and many tokens containing only background regions do not truly contribute to the final prediction. Existing works either rely on additional modules to score the importance of individual tokens, or implement a fixed ratio pruning strategy for different input instances. In this work, we propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.13802","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/2209.13802/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":"2209.13802","created_at":"2026-07-05T06:28:14.273920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.13802v2","created_at":"2026-07-05T06:28:14.273920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.13802","created_at":"2026-07-05T06:28:14.273920+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7G4JCRWB2EP","created_at":"2026-07-05T06:28:14.273920+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7G4JCRWB2EPSKZ2","created_at":"2026-07-05T06:28:14.273920+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7G4JCRW","created_at":"2026-07-05T06:28:14.273920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03872","citing_title":"Focus Through Motion: RGB-Event Collaborative Token Sparsification for Efficient Object Detection","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L7G4JCRWB2EPSKZ2JEQFGA7UER","json":"https://pith.science/pith/L7G4JCRWB2EPSKZ2JEQFGA7UER.json","graph_json":"https://pith.science/api/pith-number/L7G4JCRWB2EPSKZ2JEQFGA7UER/graph.json","events_json":"https://pith.science/api/pith-number/L7G4JCRWB2EPSKZ2JEQFGA7UER/events.json","paper":"https://pith.science/paper/L7G4JCRW"},"agent_actions":{"view_html":"https://pith.science/pith/L7G4JCRWB2EPSKZ2JEQFGA7UER","download_json":"https://pith.science/pith/L7G4JCRWB2EPSKZ2JEQFGA7UER.json","view_paper":"https://pith.science/paper/L7G4JCRW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.13802&json=true","fetch_graph":"https://pith.science/api/pith-number/L7G4JCRWB2EPSKZ2JEQFGA7UER/graph.json","fetch_events":"https://pith.science/api/pith-number/L7G4JCRWB2EPSKZ2JEQFGA7UER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7G4JCRWB2EPSKZ2JEQFGA7UER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7G4JCRWB2EPSKZ2JEQFGA7UER/action/storage_attestation","attest_author":"https://pith.science/pith/L7G4JCRWB2EPSKZ2JEQFGA7UER/action/author_attestation","sign_citation":"https://pith.science/pith/L7G4JCRWB2EPSKZ2JEQFGA7UER/action/citation_signature","submit_replication":"https://pith.science/pith/L7G4JCRWB2EPSKZ2JEQFGA7UER/action/replication_record"}},"created_at":"2026-07-05T06:28:14.273920+00:00","updated_at":"2026-07-05T06:28:14.273920+00:00"}