{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KFDCFXZOB2AVPLAZ27EDWI33I2","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":"8fc89dcf9bcd4f6680cbd924f5945156002f9a8106dd81cc82df592b8ee75a8c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-27T12:07:21Z","title_canon_sha256":"05526705fbe112beee9d6b823128c2091fb6e539a5aa189023e3d7392345ff90"},"schema_version":"1.0","source":{"id":"2305.17455","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17455","created_at":"2026-07-05T08:31:40Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17455v4","created_at":"2026-07-05T08:31:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17455","created_at":"2026-07-05T08:31:40Z"},{"alias_kind":"pith_short_12","alias_value":"KFDCFXZOB2AV","created_at":"2026-07-05T08:31:40Z"},{"alias_kind":"pith_short_16","alias_value":"KFDCFXZOB2AVPLAZ","created_at":"2026-07-05T08:31:40Z"},{"alias_kind":"pith_short_8","alias_value":"KFDCFXZO","created_at":"2026-07-05T08:31:40Z"}],"graph_snapshots":[{"event_id":"sha256:77ebb313c559b5d6c02e234d48398c3617bf3003b0b17461c385bd2a6b34343d","target":"graph","created_at":"2026-07-05T08:31:40Z","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/2305.17455/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent vision-language models have achieved tremendous advances. However, their computational costs are also escalating dramatically, making model acceleration exceedingly critical. To pursue more efficient vision-language Transformers, this paper introduces Cross-Guided Ensemble of Tokens (CrossGET), a general acceleration framework for vision-language Transformers. This framework adaptively combines tokens in real-time during inference, significantly reducing computational costs while maintaining high performance. CrossGET features two primary innovations: 1) Cross-Guided Matching and Ensemb","authors_text":"Anyi Rao, Chaofan Tao, Chun Yuan, Dachuan Shi, Jiaqi Wang, Zhendong Yang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-27T12:07:21Z","title":"CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17455","kind":"arxiv","version":4},"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:bcb8097df0dee80b37a956e34d1445a9726663c98c87fdcd25968682f3dcaf2a","target":"record","created_at":"2026-07-05T08:31:40Z","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":"8fc89dcf9bcd4f6680cbd924f5945156002f9a8106dd81cc82df592b8ee75a8c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-27T12:07:21Z","title_canon_sha256":"05526705fbe112beee9d6b823128c2091fb6e539a5aa189023e3d7392345ff90"},"schema_version":"1.0","source":{"id":"2305.17455","kind":"arxiv","version":4}},"canonical_sha256":"514622df2e0e8157ac19d7c83b237b4682fd18b21504af976ca5f6452c8584a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"514622df2e0e8157ac19d7c83b237b4682fd18b21504af976ca5f6452c8584a4","first_computed_at":"2026-07-05T08:31:40.113184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:40.113184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wupf0tL8bRb85kzjNuowrsSNxJZmMYH2q3LvGJlEXRRYjeMv97OJfkSJNztxmVM+pt+BAStcMcoAgb0rg0eWCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:40.113690Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17455","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcb8097df0dee80b37a956e34d1445a9726663c98c87fdcd25968682f3dcaf2a","sha256:77ebb313c559b5d6c02e234d48398c3617bf3003b0b17461c385bd2a6b34343d"],"state_sha256":"dd7128ba783c0f5cae0e86e7e81bf6ef514b33ade874c75865e890e4eac6f8c6"}