{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KF5QD37NZORVRRZVK5UQUOLGO3","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":"ca447869dfdf6650409d240b42fc7f15e978c2aa2dd4c8fc8d4deba63eab0f96","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-19T07:47:50Z","title_canon_sha256":"a7d4fbfbf6be53e4c64e363df0fdf1fa99b85cb118093cad8f74b37facc571bb"},"schema_version":"1.0","source":{"id":"2204.08721","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.08721","created_at":"2026-07-05T04:40:26Z"},{"alias_kind":"arxiv_version","alias_value":"2204.08721v2","created_at":"2026-07-05T04:40:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.08721","created_at":"2026-07-05T04:40:26Z"},{"alias_kind":"pith_short_12","alias_value":"KF5QD37NZORV","created_at":"2026-07-05T04:40:26Z"},{"alias_kind":"pith_short_16","alias_value":"KF5QD37NZORVRRZV","created_at":"2026-07-05T04:40:26Z"},{"alias_kind":"pith_short_8","alias_value":"KF5QD37N","created_at":"2026-07-05T04:40:26Z"}],"graph_snapshots":[{"event_id":"sha256:a62f6cc16dca09fa3e20b8b90561b8210de7581e2a46f261e244de9897504072","target":"graph","created_at":"2026-07-05T04:40:26Z","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/2204.08721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many adaptations of transformers have emerged to address the single-modal vision tasks, where self-attention modules are stacked to handle input sources like images. Intuitively, feeding multiple modalities of data to vision transformers could improve the performance, yet the inner-modal attentive weights may also be diluted, which could thus undermine the final performance. In this paper, we propose a multimodal token fusion method (TokenFusion), tailored for transformer-based vision tasks. To effectively fuse multiple modalities, TokenFusion dynamically detects uninformative tokens and subst","authors_text":"Fuchun Sun, Lele Cao, Wenbing Huang, Xinghao Chen, Yikai Wang, Yunhe Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-19T07:47:50Z","title":"Multimodal Token Fusion for Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.08721","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:b8d7f86dfc0e94f2921c3e5770bdc366e2fc16a944f579a66bbf8a3257efea14","target":"record","created_at":"2026-07-05T04:40:26Z","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":"ca447869dfdf6650409d240b42fc7f15e978c2aa2dd4c8fc8d4deba63eab0f96","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-19T07:47:50Z","title_canon_sha256":"a7d4fbfbf6be53e4c64e363df0fdf1fa99b85cb118093cad8f74b37facc571bb"},"schema_version":"1.0","source":{"id":"2204.08721","kind":"arxiv","version":2}},"canonical_sha256":"517b01efedcba358c73557690a396676e56cd446f920d82851998812bfabee98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"517b01efedcba358c73557690a396676e56cd446f920d82851998812bfabee98","first_computed_at":"2026-07-05T04:40:26.948662Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:26.948662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jgsbrHu5fRTMFpiPINxmt0sIRe4UROjH5j/zO6aFMbB6ktRHtrMYw+wnrREuvwP2q57oC52vdIsxViuqTLpVBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:26.949130Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.08721","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8d7f86dfc0e94f2921c3e5770bdc366e2fc16a944f579a66bbf8a3257efea14","sha256:a62f6cc16dca09fa3e20b8b90561b8210de7581e2a46f261e244de9897504072"],"state_sha256":"88aaa97be5cab70ffd6d129a57ad87605e29c1ab78e4bc006015dc6969f50f02"}