{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2CUKB5GN76GXOA4C4SLCOA7K27","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":"90e7a5930654c287e532173ba08db5e513ddacc927016c388b1536747e8e6b5c","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-22T17:07:41Z","title_canon_sha256":"723966a6d8647792a9ce1631471f9295068c6b9a223bd066cba0d4121ca2d9c6"},"schema_version":"1.0","source":{"id":"2104.11178","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.11178","created_at":"2026-07-05T03:38:18Z"},{"alias_kind":"arxiv_version","alias_value":"2104.11178v3","created_at":"2026-07-05T03:38:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.11178","created_at":"2026-07-05T03:38:18Z"},{"alias_kind":"pith_short_12","alias_value":"2CUKB5GN76GX","created_at":"2026-07-05T03:38:18Z"},{"alias_kind":"pith_short_16","alias_value":"2CUKB5GN76GXOA4C","created_at":"2026-07-05T03:38:18Z"},{"alias_kind":"pith_short_8","alias_value":"2CUKB5GN","created_at":"2026-07-05T03:38:18Z"}],"graph_snapshots":[{"event_id":"sha256:6b6a83b13ca67bd2f57a4b6166e025702b9b1450f96f3f0bf88cb0fe944f3843","target":"graph","created_at":"2026-07-05T03:38:18Z","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/2104.11178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a framework for learning multimodal representations from unlabeled data using convolution-free Transformer architectures. Specifically, our Video-Audio-Text Transformer (VATT) takes raw signals as inputs and extracts multimodal representations that are rich enough to benefit a variety of downstream tasks. We train VATT end-to-end from scratch using multimodal contrastive losses and evaluate its performance by the downstream tasks of video action recognition, audio event classification, image classification, and text-to-video retrieval. Furthermore, we study a modality-agnostic, sing","authors_text":"Boqing Gong, Hassan Akbari, Liangzhe Yuan, Rui Qian, Shih-Fu Chang, Wei-Hong Chuang, Yin Cui","cross_cats":["cs.AI","cs.LG","cs.MM","eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-22T17:07:41Z","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.11178","kind":"arxiv","version":3},"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":"sha256:244585285e8afbddd03657069cacad38db03f37330ab307157644b5a73c88562","target":"record","created_at":"2026-07-05T03:38:18Z","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":"90e7a5930654c287e532173ba08db5e513ddacc927016c388b1536747e8e6b5c","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-22T17:07:41Z","title_canon_sha256":"723966a6d8647792a9ce1631471f9295068c6b9a223bd066cba0d4121ca2d9c6"},"schema_version":"1.0","source":{"id":"2104.11178","kind":"arxiv","version":3}},"canonical_sha256":"d0a8a0f4cdff8d770382e4962703ead7eac620c7b730221d9cfc917f9fd5c2a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0a8a0f4cdff8d770382e4962703ead7eac620c7b730221d9cfc917f9fd5c2a3","first_computed_at":"2026-07-05T03:38:18.200719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:38:18.200719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XueY2Tq6gOtxgnlZcCkXPMfrJKfDUePdN/RR8x/q/Bapj6oekLZntrkzJlYTftURg3QNIJYnSyhYpVN8OF4ICA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:38:18.201202Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.11178","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:244585285e8afbddd03657069cacad38db03f37330ab307157644b5a73c88562","sha256:6b6a83b13ca67bd2f57a4b6166e025702b9b1450f96f3f0bf88cb0fe944f3843"],"state_sha256":"cacb1278d5a69f9f3c9b88fde6d951d9a4ea55401fd469040d4ec252dd8ab88a"}