{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VVAHNNQLRQON7WYOIU2LDZDAKY","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":"82fc2c61423eb6e315c4e132dc8243911e38450e19b8ce2b300effbf276b308b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-04T05:34:25Z","title_canon_sha256":"f359bad7a566a593f045dbc7387caeded4a0743e2c5e97df13b062d85572ecf4"},"schema_version":"1.0","source":{"id":"2303.02331","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.02331","created_at":"2026-07-05T08:38:32Z"},{"alias_kind":"arxiv_version","alias_value":"2303.02331v2","created_at":"2026-07-05T08:38:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02331","created_at":"2026-07-05T08:38:32Z"},{"alias_kind":"pith_short_12","alias_value":"VVAHNNQLRQON","created_at":"2026-07-05T08:38:32Z"},{"alias_kind":"pith_short_16","alias_value":"VVAHNNQLRQON7WYO","created_at":"2026-07-05T08:38:32Z"},{"alias_kind":"pith_short_8","alias_value":"VVAHNNQL","created_at":"2026-07-05T08:38:32Z"}],"graph_snapshots":[{"event_id":"sha256:75832bd0b9311a0395a37de069ce2a6c015eb20aab2156e7531e6a8cf320487c","target":"graph","created_at":"2026-07-05T08:38:32Z","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/2303.02331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Token merging has emerged as a new paradigm that can accelerate the inference of Vision Transformers (ViTs) without any retraining or fine-tuning. To push the frontier of training-free acceleration in ViTs, we improve token merging by adding the perspectives of 1) activation outliers and 2) hierarchical representations. Through a careful analysis of the attention behavior in ViTs, we characterize a delayed onset of the convergent attention phenomenon, which makes token merging undesirable in the bottom blocks of ViTs. Moreover, we augment token merging with a hierarchical processing scheme to ","authors_text":"Arash Fayyazi, Jung Hwan Heo, Massoud Pedram, Seyedarmin Azizi","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-04T05:34:25Z","title":"Training-Free Acceleration of ViTs with Delayed Spatial Merging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02331","kind":"arxiv","version":2},"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:d53411e4cadd1f59db2e1c0b212ee8079a3812bc5d406e59af3d9c7d96868521","target":"record","created_at":"2026-07-05T08:38:32Z","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":"82fc2c61423eb6e315c4e132dc8243911e38450e19b8ce2b300effbf276b308b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-04T05:34:25Z","title_canon_sha256":"f359bad7a566a593f045dbc7387caeded4a0743e2c5e97df13b062d85572ecf4"},"schema_version":"1.0","source":{"id":"2303.02331","kind":"arxiv","version":2}},"canonical_sha256":"ad4076b60b8c1cdfdb0e4534b1e460562ca5c312a940b5d4011fc0c387b221a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad4076b60b8c1cdfdb0e4534b1e460562ca5c312a940b5d4011fc0c387b221a0","first_computed_at":"2026-07-05T08:38:32.565735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:32.565735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5w0y/kvlukIxK1E5h2gVpYlcTgDacjAsw3rpTp8KsF35cVTy27Mr6JYmAdZuqAUPNBlEFIRfDQsSdJnbEuUWCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:32.566228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.02331","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d53411e4cadd1f59db2e1c0b212ee8079a3812bc5d406e59af3d9c7d96868521","sha256:75832bd0b9311a0395a37de069ce2a6c015eb20aab2156e7531e6a8cf320487c"],"state_sha256":"32ec59064bb6087c9b5703c929418ce44d2eae16f2cd63c59ffbb37ab90cb447"}