{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QMFSIRQVTWX34POH3MZ6RUY5EQ","short_pith_number":"pith:QMFSIRQV","schema_version":"1.0","canonical_sha256":"830b2446159dafbe3dc7db33e8d31d2417bc718524e1c4162c90757e3c378ec4","source":{"kind":"arxiv","id":"2310.01812","version":3},"attestation_state":"computed","paper":{"title":"PPT: Token Pruning and Pooling for Efficient Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanhu Zeng, Xinghao Chen, Xinjian Wu, Xiudong Wang","submitted_at":"2023-10-03T05:55:11Z","abstract_excerpt":"Vision Transformers (ViTs) have emerged as powerful models in the field of computer vision, delivering superior performance across various vision tasks. However, the high computational complexity poses a significant barrier to their practical applications in real-world scenarios. Motivated by the fact that not all tokens contribute equally to the final predictions and fewer tokens bring less computational cost, reducing redundant tokens has become a prevailing paradigm for accelerating vision transformers. However, we argue that it is not optimal to either only reduce inattentive redundancy by"},"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":"2310.01812","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-03T05:55:11Z","cross_cats_sorted":[],"title_canon_sha256":"9426f94401b75d655de3af43583d18a2bc7a73b95510f628f798c0bdab5aabeb","abstract_canon_sha256":"d3dbdbd242eb3b3e24edfb6643bea978b7b8f4d5bf737b8f3df5003e45f83283"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:57.627911Z","signature_b64":"41BL9ymxhq7Mo73BrHR5Ji1LeNwhFLWLYCCbr8DJt7miYAwV9yjjDQ1BrAG8rVuzdabeuiW91+My7rl7Ja16AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"830b2446159dafbe3dc7db33e8d31d2417bc718524e1c4162c90757e3c378ec4","last_reissued_at":"2026-07-05T07:40:57.627374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:57.627374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PPT: Token Pruning and Pooling for Efficient Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fanhu Zeng, Xinghao Chen, Xinjian Wu, Xiudong Wang","submitted_at":"2023-10-03T05:55:11Z","abstract_excerpt":"Vision Transformers (ViTs) have emerged as powerful models in the field of computer vision, delivering superior performance across various vision tasks. However, the high computational complexity poses a significant barrier to their practical applications in real-world scenarios. Motivated by the fact that not all tokens contribute equally to the final predictions and fewer tokens bring less computational cost, reducing redundant tokens has become a prevailing paradigm for accelerating vision transformers. However, we argue that it is not optimal to either only reduce inattentive redundancy by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01812","kind":"arxiv","version":3},"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/2310.01812/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":"2310.01812","created_at":"2026-07-05T07:40:57.627433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01812v3","created_at":"2026-07-05T07:40:57.627433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01812","created_at":"2026-07-05T07:40:57.627433+00:00"},{"alias_kind":"pith_short_12","alias_value":"QMFSIRQVTWX3","created_at":"2026-07-05T07:40:57.627433+00:00"},{"alias_kind":"pith_short_16","alias_value":"QMFSIRQVTWX34POH","created_at":"2026-07-05T07:40:57.627433+00:00"},{"alias_kind":"pith_short_8","alias_value":"QMFSIRQV","created_at":"2026-07-05T07:40:57.627433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22372","citing_title":"ASAP: Attention Sink Anchored Pruning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2509.14165","citing_title":"Where Do Tokens Go? Understanding Pruning Behaviors in STEP at High Resolutions","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00915","citing_title":"Rethink MAE with Linear Time-Invariant Dynamics","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05718","citing_title":"MPM: Mutual Pair Merging for Efficient Vision Transformers","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QMFSIRQVTWX34POH3MZ6RUY5EQ","json":"https://pith.science/pith/QMFSIRQVTWX34POH3MZ6RUY5EQ.json","graph_json":"https://pith.science/api/pith-number/QMFSIRQVTWX34POH3MZ6RUY5EQ/graph.json","events_json":"https://pith.science/api/pith-number/QMFSIRQVTWX34POH3MZ6RUY5EQ/events.json","paper":"https://pith.science/paper/QMFSIRQV"},"agent_actions":{"view_html":"https://pith.science/pith/QMFSIRQVTWX34POH3MZ6RUY5EQ","download_json":"https://pith.science/pith/QMFSIRQVTWX34POH3MZ6RUY5EQ.json","view_paper":"https://pith.science/paper/QMFSIRQV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01812&json=true","fetch_graph":"https://pith.science/api/pith-number/QMFSIRQVTWX34POH3MZ6RUY5EQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QMFSIRQVTWX34POH3MZ6RUY5EQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QMFSIRQVTWX34POH3MZ6RUY5EQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QMFSIRQVTWX34POH3MZ6RUY5EQ/action/storage_attestation","attest_author":"https://pith.science/pith/QMFSIRQVTWX34POH3MZ6RUY5EQ/action/author_attestation","sign_citation":"https://pith.science/pith/QMFSIRQVTWX34POH3MZ6RUY5EQ/action/citation_signature","submit_replication":"https://pith.science/pith/QMFSIRQVTWX34POH3MZ6RUY5EQ/action/replication_record"}},"created_at":"2026-07-05T07:40:57.627433+00:00","updated_at":"2026-07-05T07:40:57.627433+00:00"}