{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QSGLQVJWTYAZOEOBSE5Z632JQX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"db9b7aa8fc0899178109de78b10467eaf1524188e31aac5f1f08939eeb330717","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-22T04:49:00Z","title_canon_sha256":"8c0b31f71dee4aa342d0ad65801cb58846b71be31ab12495588f7bd311e1ccd4"},"schema_version":"1.0","source":{"id":"2405.13337","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13337","created_at":"2026-07-05T11:30:36Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13337v3","created_at":"2026-07-05T11:30:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13337","created_at":"2026-07-05T11:30:36Z"},{"alias_kind":"pith_short_12","alias_value":"QSGLQVJWTYAZ","created_at":"2026-07-05T11:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"QSGLQVJWTYAZOEOB","created_at":"2026-07-05T11:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"QSGLQVJW","created_at":"2026-07-05T11:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:78c9f5b4654068e10a5111778fd09bce4695f130d460eb7af7893e596031b248","target":"graph","created_at":"2026-07-05T11:30:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.13337/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Huaibo Huang, Mingrui Chen, Qihang Fan, Ran He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-22T04:49:00Z","title":"Semantic Equitable Clustering: A Simple and Effective Strategy for Clustering Vision Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13337","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:650a4a1abee5fa58745d540e32107d71bed98bd7d9b3db747365682934fd5839","target":"record","created_at":"2026-07-05T11:30:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"db9b7aa8fc0899178109de78b10467eaf1524188e31aac5f1f08939eeb330717","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-22T04:49:00Z","title_canon_sha256":"8c0b31f71dee4aa342d0ad65801cb58846b71be31ab12495588f7bd311e1ccd4"},"schema_version":"1.0","source":{"id":"2405.13337","kind":"arxiv","version":3}},"canonical_sha256":"848cb855369e019711c1913b9f6f4985edae8972de15239a85d68b32357cfa85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"848cb855369e019711c1913b9f6f4985edae8972de15239a85d68b32357cfa85","first_computed_at":"2026-07-05T11:30:36.107535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:36.107535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LmTbXmIbL0XJgMwp/2Jvn29fLV3LSuVgKkXZnBcHU/C91D+U5iCqcSL+Xqh3xsaRD1XXCgpLaIxkx/FwSuX7CA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:36.108019Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.13337","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:650a4a1abee5fa58745d540e32107d71bed98bd7d9b3db747365682934fd5839","sha256:78c9f5b4654068e10a5111778fd09bce4695f130d460eb7af7893e596031b248"],"state_sha256":"404a1a289731480ff9df81848ebf49888156c31c0ad06b855b127c34aeeb4bef"}