{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2CUKB5GN76GXOA4C4SLCOA7K27","short_pith_number":"pith:2CUKB5GN","canonical_record":{"source":{"id":"2104.11178","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-22T17:07:41Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.IV"],"title_canon_sha256":"723966a6d8647792a9ce1631471f9295068c6b9a223bd066cba0d4121ca2d9c6","abstract_canon_sha256":"90e7a5930654c287e532173ba08db5e513ddacc927016c388b1536747e8e6b5c"},"schema_version":"1.0"},"canonical_sha256":"d0a8a0f4cdff8d770382e4962703ead7eac620c7b730221d9cfc917f9fd5c2a3","source":{"kind":"arxiv","id":"2104.11178","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2CUKB5GN76GXOA4C4SLCOA7K27","target":"record","payload":{"canonical_record":{"source":{"id":"2104.11178","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-22T17:07:41Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","eess.IV"],"title_canon_sha256":"723966a6d8647792a9ce1631471f9295068c6b9a223bd066cba0d4121ca2d9c6","abstract_canon_sha256":"90e7a5930654c287e532173ba08db5e513ddacc927016c388b1536747e8e6b5c"},"schema_version":"1.0"},"canonical_sha256":"d0a8a0f4cdff8d770382e4962703ead7eac620c7b730221d9cfc917f9fd5c2a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:18.201202Z","signature_b64":"XueY2Tq6gOtxgnlZcCkXPMfrJKfDUePdN/RR8x/q/Bapj6oekLZntrkzJlYTftURg3QNIJYnSyhYpVN8OF4ICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0a8a0f4cdff8d770382e4962703ead7eac620c7b730221d9cfc917f9fd5c2a3","last_reissued_at":"2026-07-05T03:38:18.200719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:18.200719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.11178","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:38:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wMjt4u6dQ3OUxpWLJU+1r9vxJkZTPXvKg7Znz7XvxuZ9PLpmm38McUKPZ9ouLUdPhRl36y+dlwK01FncrO3pBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T23:07:58.221741Z"},"content_sha256":"244585285e8afbddd03657069cacad38db03f37330ab307157644b5a73c88562","schema_version":"1.0","event_id":"sha256:244585285e8afbddd03657069cacad38db03f37330ab307157644b5a73c88562"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2CUKB5GN76GXOA4C4SLCOA7K27","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM","eess.IV"],"primary_cat":"cs.CV","authors_text":"Boqing Gong, Hassan Akbari, Liangzhe Yuan, Rui Qian, Shih-Fu Chang, Wei-Hong Chuang, Yin Cui","submitted_at":"2021-04-22T17:07:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.11178","kind":"arxiv","version":3},"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/2104.11178/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":"2026-07-05T03:38:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n2dvQUlJJ3DPbml0ofiQVtxXyQECsEedqj3US4eB81skdDtteEO58GKCCgjGYvUP6E12K423JcwKgFETbJ98AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T23:07:58.222118Z"},"content_sha256":"6b6a83b13ca67bd2f57a4b6166e025702b9b1450f96f3f0bf88cb0fe944f3843","schema_version":"1.0","event_id":"sha256:6b6a83b13ca67bd2f57a4b6166e025702b9b1450f96f3f0bf88cb0fe944f3843"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2CUKB5GN76GXOA4C4SLCOA7K27/bundle.json","state_url":"https://pith.science/pith/2CUKB5GN76GXOA4C4SLCOA7K27/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2CUKB5GN76GXOA4C4SLCOA7K27/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":"2026-07-27T23:07:58Z","links":{"resolver":"https://pith.science/pith/2CUKB5GN76GXOA4C4SLCOA7K27","bundle":"https://pith.science/pith/2CUKB5GN76GXOA4C4SLCOA7K27/bundle.json","state":"https://pith.science/pith/2CUKB5GN76GXOA4C4SLCOA7K27/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2CUKB5GN76GXOA4C4SLCOA7K27/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"21vLgnNNutzc4M1XRHQ3jrInmQA9JNPRgV8+eYa9vWM2QD1ViBpETE6HWST6eKrsi9SDj8gGvX8QlZgUCIDGBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T23:07:58.224601Z","bundle_sha256":"fa4ce3977062bcd43cb9225c0dfad322d6791f8444367adcece52c55433953b6"}}