{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QGYNBJY2MFV6HQJDCY2EI2TC25","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":"1971519404a6c2858dbc6a1ccb161b1918cfc86777f94ba40e9646417faf2c9c","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-20T12:10:29Z","title_canon_sha256":"4f6198f57f2568f824855782b0d9de01c8f99cb3a15fd61df877d974232aad06"},"schema_version":"1.0","source":{"id":"2307.10802","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.10802","created_at":"2026-07-05T06:33:10Z"},{"alias_kind":"arxiv_version","alias_value":"2307.10802v1","created_at":"2026-07-05T06:33:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10802","created_at":"2026-07-05T06:33:10Z"},{"alias_kind":"pith_short_12","alias_value":"QGYNBJY2MFV6","created_at":"2026-07-05T06:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"QGYNBJY2MFV6HQJD","created_at":"2026-07-05T06:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"QGYNBJY2","created_at":"2026-07-05T06:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:2048dcb97f579673d077b68fe93f0f1eca28d9c73f74c8ef18efbfdcc79cee72","target":"graph","created_at":"2026-07-05T06:33:10Z","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/2307.10802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this field, it still remains challenging to design a unified network for processing various modalities ($\\textit{e.g.}$ natural language, 2D images, 3D point clouds, audio, video, time series, tabular data) due to the inherent gaps among them. In this work, we propose a framework, named Meta-Transformer, that leverages a $\\textbf{frozen}$ encoder to perform multimodal perception without any paired multimodal training data. In Meta-Transformer, the raw input","authors_text":"Hongsheng Li, Kaipeng Zhang, Kaixiong Gong, Wanli Ouyang, Xiangyu Yue, Yiyuan Zhang, Yu Qiao","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-20T12:10:29Z","title":"Meta-Transformer: A Unified Framework for Multimodal Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10802","kind":"arxiv","version":1},"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":"sha256:089076073cb3b5400bbf418ec3e307eaf7b04222e7522179eefd497dea56d32e","target":"record","created_at":"2026-07-05T06:33:10Z","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":"1971519404a6c2858dbc6a1ccb161b1918cfc86777f94ba40e9646417faf2c9c","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-20T12:10:29Z","title_canon_sha256":"4f6198f57f2568f824855782b0d9de01c8f99cb3a15fd61df877d974232aad06"},"schema_version":"1.0","source":{"id":"2307.10802","kind":"arxiv","version":1}},"canonical_sha256":"81b0d0a71a616be3c1231634446a62d764799f9585059aae50724d866fe831bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81b0d0a71a616be3c1231634446a62d764799f9585059aae50724d866fe831bf","first_computed_at":"2026-07-05T06:33:10.276962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:33:10.276962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OhPBhSk9PAQEc2gPXzRrg/S2y/W3HUSowi6bSd/dJeL6yaKQR5fx0yhSnRYJu0tViIL0JxaWPKzfhoeJI8YrCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:33:10.277386Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.10802","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:089076073cb3b5400bbf418ec3e307eaf7b04222e7522179eefd497dea56d32e","sha256:2048dcb97f579673d077b68fe93f0f1eca28d9c73f74c8ef18efbfdcc79cee72"],"state_sha256":"69035e4dad3fd9b4bca30e6391e665db6bb1ce92caacf66a39828dac6ab2f3ce"}