{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HPYUXF6IAR46MJG4AF53AW5CIA","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":"750e77b05540ccc510b4317222c3349b8a97708288dc539589fac8a0f9feb861","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T11:24:15Z","title_canon_sha256":"f30c35499050b74f14df36218ef2e096957f96b4b22b1c38b642e834dd5bf097"},"schema_version":"1.0","source":{"id":"2406.01210","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01210","created_at":"2026-07-05T08:27:10Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01210v2","created_at":"2026-07-05T08:27:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01210","created_at":"2026-07-05T08:27:10Z"},{"alias_kind":"pith_short_12","alias_value":"HPYUXF6IAR46","created_at":"2026-07-05T08:27:10Z"},{"alias_kind":"pith_short_16","alias_value":"HPYUXF6IAR46MJG4","created_at":"2026-07-05T08:27:10Z"},{"alias_kind":"pith_short_8","alias_value":"HPYUXF6I","created_at":"2026-07-05T08:27:10Z"}],"graph_snapshots":[{"event_id":"sha256:ed15ae81931c3cb91d802dfe5d9d3bb86c7139920ac379cdcf8b4373b11a3cc1","target":"graph","created_at":"2026-07-05T08:27:10Z","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/2406.01210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-modal transformers have demonstrated superiority in various vision tasks by effectively integrating different modalities. This paper first critiques prior token exchange methods which replace less informative tokens with inter-modal features, and demonstrate exchange based methods underperform cross-attention mechanisms, while the computational demand of the latter inevitably restricts its use with longer sequences. To surmount the computational challenges, we propose GeminiFusion, a pixel-wise fusion approach that capitalizes on aligned cross-modal representations. GeminiFusion elegantl","authors_text":"Chang Xu, Chao Zhang, Ding Jia, Han Wu, Jianyuan Guo, Kai Han, Xinghao Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T11:24:15Z","title":"GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01210","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:b95e9a2efa1679dfd1d88864aecd5dfbac13e772a8a1ffc6a6cf45efee8fbda1","target":"record","created_at":"2026-07-05T08:27:10Z","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":"750e77b05540ccc510b4317222c3349b8a97708288dc539589fac8a0f9feb861","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T11:24:15Z","title_canon_sha256":"f30c35499050b74f14df36218ef2e096957f96b4b22b1c38b642e834dd5bf097"},"schema_version":"1.0","source":{"id":"2406.01210","kind":"arxiv","version":2}},"canonical_sha256":"3bf14b97c80479e624dc017bb05ba240088550234fa67d526099385fbd556ba2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3bf14b97c80479e624dc017bb05ba240088550234fa67d526099385fbd556ba2","first_computed_at":"2026-07-05T08:27:10.798182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:10.798182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eUXBrq/FbmUbuum/Zc58XRfuMj5gtKrKl6mNVm46fH2dNDZksRK729BV6262GuBETIOlX/PB3YbbCIn46hQCAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:10.798606Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01210","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b95e9a2efa1679dfd1d88864aecd5dfbac13e772a8a1ffc6a6cf45efee8fbda1","sha256:ed15ae81931c3cb91d802dfe5d9d3bb86c7139920ac379cdcf8b4373b11a3cc1"],"state_sha256":"4ad995fada801c94db5e957fc13f84d9c0520943a1dd0dab90d0d01436f1ac5c"}