{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QHMSR3A34XTU6U6CFTXLLTCLKI","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":"01a8de2882647f7239bcd29483aba898a19263560cb5c64af03f593439160e82","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-13T21:36:09Z","title_canon_sha256":"5b65c0382545db88c2f80ff363dc6be256bd0fb929b5590de4190cd78f4e68c2"},"schema_version":"1.0","source":{"id":"2206.06488","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.06488","created_at":"2026-07-05T06:08:51Z"},{"alias_kind":"arxiv_version","alias_value":"2206.06488v2","created_at":"2026-07-05T06:08:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06488","created_at":"2026-07-05T06:08:51Z"},{"alias_kind":"pith_short_12","alias_value":"QHMSR3A34XTU","created_at":"2026-07-05T06:08:51Z"},{"alias_kind":"pith_short_16","alias_value":"QHMSR3A34XTU6U6C","created_at":"2026-07-05T06:08:51Z"},{"alias_kind":"pith_short_8","alias_value":"QHMSR3A3","created_at":"2026-07-05T06:08:51Z"}],"graph_snapshots":[{"event_id":"sha256:819bc2a3219013acbd4c29e806c8318a6a7651671e7c6ee16aea99ad084f27cf","target":"graph","created_at":"2026-07-05T06:08:51Z","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/2206.06488/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer is a promising neural network learner, and has achieved great success in various machine learning tasks. Thanks to the recent prevalence of multimodal applications and big data, Transformer-based multimodal learning has become a hot topic in AI research. This paper presents a comprehensive survey of Transformer techniques oriented at multimodal data. The main contents of this survey include: (1) a background of multimodal learning, Transformer ecosystem, and the multimodal big data era, (2) a theoretical review of Vanilla Transformer, Vision Transformer, and multimodal Transformers","authors_text":"David A. Clifton, Peng Xu, Xiatian Zhu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-13T21:36:09Z","title":"Multimodal Learning with Transformers: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06488","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:dce5387d226f5b2c78b3b406c6ba79a9ac11a779ea8dbf2c5011b2a87b6ff006","target":"record","created_at":"2026-07-05T06:08:51Z","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":"01a8de2882647f7239bcd29483aba898a19263560cb5c64af03f593439160e82","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-06-13T21:36:09Z","title_canon_sha256":"5b65c0382545db88c2f80ff363dc6be256bd0fb929b5590de4190cd78f4e68c2"},"schema_version":"1.0","source":{"id":"2206.06488","kind":"arxiv","version":2}},"canonical_sha256":"81d928ec1be5e74f53c22ceeb5cc4b5207f3ae843420f0d60f25ea7cbbabffd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81d928ec1be5e74f53c22ceeb5cc4b5207f3ae843420f0d60f25ea7cbbabffd4","first_computed_at":"2026-07-05T06:08:51.377030Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:08:51.377030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pz7B8VklmhUSmc68mReS5b0t838WilrrpHGjmg+Ip/IUGRjf6K/xaOj30ovD0iRlr7HfeRWaXLwNBgVOxb1DCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:08:51.377605Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.06488","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dce5387d226f5b2c78b3b406c6ba79a9ac11a779ea8dbf2c5011b2a87b6ff006","sha256:819bc2a3219013acbd4c29e806c8318a6a7651671e7c6ee16aea99ad084f27cf"],"state_sha256":"62c29309cf30cce9642ce3fb26e27e8dd18b44d9fb8bf274a4dcbace55e88559"}