{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QSGLQVJWTYAZOEOBSE5Z632JQX","short_pith_number":"pith:QSGLQVJW","schema_version":"1.0","canonical_sha256":"848cb855369e019711c1913b9f6f4985edae8972de15239a85d68b32357cfa85","source":{"kind":"arxiv","id":"2405.13337","version":3},"attestation_state":"computed","paper":{"title":"Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaibo Huang, Mingrui Chen, Qihang Fan, Ran He","submitted_at":"2024-05-22T04:49:00Z","abstract_excerpt":"The Vision Transformer (ViT) has gained prominence for its superior relational modeling prowess. However, its global attention mechanism's quadratic complexity poses substantial computational burdens. A common remedy spatially groups tokens for self-attention, reducing computational requirements. Nonetheless, this strategy neglects semantic information in tokens, possibly scattering semantically-linked tokens across distinct groups, thus compromising the efficacy of self-attention intended for modeling inter-token dependencies. Motivated by these insights, we introduce a fast and balanced clus"},"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":"2405.13337","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-22T04:49:00Z","cross_cats_sorted":[],"title_canon_sha256":"8c0b31f71dee4aa342d0ad65801cb58846b71be31ab12495588f7bd311e1ccd4","abstract_canon_sha256":"db9b7aa8fc0899178109de78b10467eaf1524188e31aac5f1f08939eeb330717"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:36.108019Z","signature_b64":"LmTbXmIbL0XJgMwp/2Jvn29fLV3LSuVgKkXZnBcHU/C91D+U5iCqcSL+Xqh3xsaRD1XXCgpLaIxkx/FwSuX7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"848cb855369e019711c1913b9f6f4985edae8972de15239a85d68b32357cfa85","last_reissued_at":"2026-07-05T11:30:36.107535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:36.107535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaibo Huang, Mingrui Chen, Qihang Fan, Ran He","submitted_at":"2024-05-22T04:49:00Z","abstract_excerpt":"The Vision Transformer (ViT) has gained prominence for its superior relational modeling prowess. However, its global attention mechanism's quadratic complexity poses substantial computational burdens. A common remedy spatially groups tokens for self-attention, reducing computational requirements. Nonetheless, this strategy neglects semantic information in tokens, possibly scattering semantically-linked tokens across distinct groups, thus compromising the efficacy of self-attention intended for modeling inter-token dependencies. Motivated by these insights, we introduce a fast and balanced clus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13337","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/2405.13337/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":"2405.13337","created_at":"2026-07-05T11:30:36.107592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13337v3","created_at":"2026-07-05T11:30:36.107592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13337","created_at":"2026-07-05T11:30:36.107592+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSGLQVJWTYAZ","created_at":"2026-07-05T11:30:36.107592+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSGLQVJWTYAZOEOB","created_at":"2026-07-05T11:30:36.107592+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSGLQVJW","created_at":"2026-07-05T11:30:36.107592+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00698","citing_title":"Rectifying Magnitude Neglect in Linear Attention","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QSGLQVJWTYAZOEOBSE5Z632JQX","json":"https://pith.science/pith/QSGLQVJWTYAZOEOBSE5Z632JQX.json","graph_json":"https://pith.science/api/pith-number/QSGLQVJWTYAZOEOBSE5Z632JQX/graph.json","events_json":"https://pith.science/api/pith-number/QSGLQVJWTYAZOEOBSE5Z632JQX/events.json","paper":"https://pith.science/paper/QSGLQVJW"},"agent_actions":{"view_html":"https://pith.science/pith/QSGLQVJWTYAZOEOBSE5Z632JQX","download_json":"https://pith.science/pith/QSGLQVJWTYAZOEOBSE5Z632JQX.json","view_paper":"https://pith.science/paper/QSGLQVJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13337&json=true","fetch_graph":"https://pith.science/api/pith-number/QSGLQVJWTYAZOEOBSE5Z632JQX/graph.json","fetch_events":"https://pith.science/api/pith-number/QSGLQVJWTYAZOEOBSE5Z632JQX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSGLQVJWTYAZOEOBSE5Z632JQX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSGLQVJWTYAZOEOBSE5Z632JQX/action/storage_attestation","attest_author":"https://pith.science/pith/QSGLQVJWTYAZOEOBSE5Z632JQX/action/author_attestation","sign_citation":"https://pith.science/pith/QSGLQVJWTYAZOEOBSE5Z632JQX/action/citation_signature","submit_replication":"https://pith.science/pith/QSGLQVJWTYAZOEOBSE5Z632JQX/action/replication_record"}},"created_at":"2026-07-05T11:30:36.107592+00:00","updated_at":"2026-07-05T11:30:36.107592+00:00"}