{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HPYUXF6IAR46MJG4AF53AW5CIA","short_pith_number":"pith:HPYUXF6I","canonical_record":{"source":{"id":"2406.01210","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T11:24:15Z","cross_cats_sorted":[],"title_canon_sha256":"f30c35499050b74f14df36218ef2e096957f96b4b22b1c38b642e834dd5bf097","abstract_canon_sha256":"750e77b05540ccc510b4317222c3349b8a97708288dc539589fac8a0f9feb861"},"schema_version":"1.0"},"canonical_sha256":"3bf14b97c80479e624dc017bb05ba240088550234fa67d526099385fbd556ba2","source":{"kind":"arxiv","id":"2406.01210","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HPYUXF6IAR46MJG4AF53AW5CIA","target":"record","payload":{"canonical_record":{"source":{"id":"2406.01210","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T11:24:15Z","cross_cats_sorted":[],"title_canon_sha256":"f30c35499050b74f14df36218ef2e096957f96b4b22b1c38b642e834dd5bf097","abstract_canon_sha256":"750e77b05540ccc510b4317222c3349b8a97708288dc539589fac8a0f9feb861"},"schema_version":"1.0"},"canonical_sha256":"3bf14b97c80479e624dc017bb05ba240088550234fa67d526099385fbd556ba2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:10.798606Z","signature_b64":"eUXBrq/FbmUbuum/Zc58XRfuMj5gtKrKl6mNVm46fH2dNDZksRK729BV6262GuBETIOlX/PB3YbbCIn46hQCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bf14b97c80479e624dc017bb05ba240088550234fa67d526099385fbd556ba2","last_reissued_at":"2026-07-05T08:27:10.798182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:10.798182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.01210","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:27:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Lz33nY8CgoypbAmmF5O3OrWh1K3YJHe7qx2l2cDmotKbs6UKopN/SA32vInxSyhuOWeceR5fU+GIyhGmb5kDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:12:58.147035Z"},"content_sha256":"b95e9a2efa1679dfd1d88864aecd5dfbac13e772a8a1ffc6a6cf45efee8fbda1","schema_version":"1.0","event_id":"sha256:b95e9a2efa1679dfd1d88864aecd5dfbac13e772a8a1ffc6a6cf45efee8fbda1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HPYUXF6IAR46MJG4AF53AW5CIA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Xu, Chao Zhang, Ding Jia, Han Wu, Jianyuan Guo, Kai Han, Xinghao Chen","submitted_at":"2024-06-03T11:24:15Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01210","kind":"arxiv","version":2},"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/2406.01210/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:27:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BIzQlu0wcaepWegrOnGuQd2Hm9P0yjoxk8IDC7NxHtJNaKrrri8ZQsyNIuLOtVIv8v8renZmJfcVnYpzoaN2Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:12:58.149324Z"},"content_sha256":"ed15ae81931c3cb91d802dfe5d9d3bb86c7139920ac379cdcf8b4373b11a3cc1","schema_version":"1.0","event_id":"sha256:ed15ae81931c3cb91d802dfe5d9d3bb86c7139920ac379cdcf8b4373b11a3cc1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HPYUXF6IAR46MJG4AF53AW5CIA/bundle.json","state_url":"https://pith.science/pith/HPYUXF6IAR46MJG4AF53AW5CIA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HPYUXF6IAR46MJG4AF53AW5CIA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T13:12:58Z","links":{"resolver":"https://pith.science/pith/HPYUXF6IAR46MJG4AF53AW5CIA","bundle":"https://pith.science/pith/HPYUXF6IAR46MJG4AF53AW5CIA/bundle.json","state":"https://pith.science/pith/HPYUXF6IAR46MJG4AF53AW5CIA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HPYUXF6IAR46MJG4AF53AW5CIA/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bDm3btJZg9lP5/Jj0Ase+NqT1oLxAG07TxEt490rD4/YgFPFMoo8fztJ/tOgbFP0e64GjiN2nzEglxGcSujTBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:12:58.160040Z","bundle_sha256":"747fed061d358c5e08ab2ae9d6b1aaf5ed23d50b7a7b901f2aba4472a47b093a"}}