{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:46EOPEULG5JSRKNZB5FW54MXAW","short_pith_number":"pith:46EOPEUL","canonical_record":{"source":{"id":"2209.14156","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-28T15:08:03Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ff7d339f08f1decf6c19cc294a01f9986d0e1dc33ea4aeec5f8adbd73918f80c","abstract_canon_sha256":"8f014f1d585372c5d940588382a01fb38c9261ef10de161a69d38c4a5ecc03b2"},"schema_version":"1.0"},"canonical_sha256":"e788e7928b375328a9b90f4b6ef1970594dc878c2b3fef43ef9744a692439f32","source":{"kind":"arxiv","id":"2209.14156","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14156","created_at":"2026-07-05T05:12:44Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14156v2","created_at":"2026-07-05T05:12:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14156","created_at":"2026-07-05T05:12:44Z"},{"alias_kind":"pith_short_12","alias_value":"46EOPEULG5JS","created_at":"2026-07-05T05:12:44Z"},{"alias_kind":"pith_short_16","alias_value":"46EOPEULG5JSRKNZ","created_at":"2026-07-05T05:12:44Z"},{"alias_kind":"pith_short_8","alias_value":"46EOPEUL","created_at":"2026-07-05T05:12:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:46EOPEULG5JSRKNZB5FW54MXAW","target":"record","payload":{"canonical_record":{"source":{"id":"2209.14156","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-28T15:08:03Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ff7d339f08f1decf6c19cc294a01f9986d0e1dc33ea4aeec5f8adbd73918f80c","abstract_canon_sha256":"8f014f1d585372c5d940588382a01fb38c9261ef10de161a69d38c4a5ecc03b2"},"schema_version":"1.0"},"canonical_sha256":"e788e7928b375328a9b90f4b6ef1970594dc878c2b3fef43ef9744a692439f32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:44.543899Z","signature_b64":"tiguprbiPMxDihpm9DbupYFFdLSAtLNpSZ0kEIgfWFRSZqEO8KGnYBEwpBp1uq77zIbauzDtXmte5jqp4wAwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e788e7928b375328a9b90f4b6ef1970594dc878c2b3fef43ef9744a692439f32","last_reissued_at":"2026-07-05T05:12:44.543401Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:44.543401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.14156","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:12:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QqEbmwbuUUzMoE9Roa/UKl6UwcGtB6HaVoR2cHtYf6gfzuK3EM3uTyrzNe0CEkNi1xvW7jyziXB09epFkSTtCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T18:54:16.377467Z"},"content_sha256":"534722921117d7fa0efe0da03de4a91bacfa370222e93e2ce4b8afa96ba3aa77","schema_version":"1.0","event_id":"sha256:534722921117d7fa0efe0da03de4a91bacfa370222e93e2ce4b8afa96ba3aa77"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:46EOPEULG5JSRKNZB5FW54MXAW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TVLT: Textless Vision-Language Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jaemin Cho, Mohit Bansal, Yixin Nie, Zineng Tang","submitted_at":"2022-09-28T15:08:03Z","abstract_excerpt":"In this work, we present the Textless Vision-Language Transformer (TVLT), where homogeneous transformer blocks take raw visual and audio inputs for vision-and-language representation learning with minimal modality-specific design, and do not use text-specific modules such as tokenization or automatic speech recognition (ASR). TVLT is trained by reconstructing masked patches of continuous video frames and audio spectrograms (masked autoencoding) and contrastive modeling to align video and audio. TVLT attains performance comparable to its text-based counterpart on various multimodal tasks, such "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14156","kind":"arxiv","version":2},"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/2209.14156/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":"2026-07-05T05:12:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J91+gs2cgvaNTOc1TbzZl86VXAfCqE+CWV+S3wz0yHSfIeyYTK5kXYZk8L9hHGaVQQTxeo/5vueBDirgmkCXDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T18:54:16.378416Z"},"content_sha256":"b8b5b3e6db283c89018b826cef563e4791378702e46bd1143e3d8f1cba37bfcc","schema_version":"1.0","event_id":"sha256:b8b5b3e6db283c89018b826cef563e4791378702e46bd1143e3d8f1cba37bfcc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/46EOPEULG5JSRKNZB5FW54MXAW/bundle.json","state_url":"https://pith.science/pith/46EOPEULG5JSRKNZB5FW54MXAW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/46EOPEULG5JSRKNZB5FW54MXAW/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":"2026-08-19T18:54:16Z","links":{"resolver":"https://pith.science/pith/46EOPEULG5JSRKNZB5FW54MXAW","bundle":"https://pith.science/pith/46EOPEULG5JSRKNZB5FW54MXAW/bundle.json","state":"https://pith.science/pith/46EOPEULG5JSRKNZB5FW54MXAW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/46EOPEULG5JSRKNZB5FW54MXAW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:46EOPEULG5JSRKNZB5FW54MXAW","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":"8f014f1d585372c5d940588382a01fb38c9261ef10de161a69d38c4a5ecc03b2","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-28T15:08:03Z","title_canon_sha256":"ff7d339f08f1decf6c19cc294a01f9986d0e1dc33ea4aeec5f8adbd73918f80c"},"schema_version":"1.0","source":{"id":"2209.14156","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14156","created_at":"2026-07-05T05:12:44Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14156v2","created_at":"2026-07-05T05:12:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14156","created_at":"2026-07-05T05:12:44Z"},{"alias_kind":"pith_short_12","alias_value":"46EOPEULG5JS","created_at":"2026-07-05T05:12:44Z"},{"alias_kind":"pith_short_16","alias_value":"46EOPEULG5JSRKNZ","created_at":"2026-07-05T05:12:44Z"},{"alias_kind":"pith_short_8","alias_value":"46EOPEUL","created_at":"2026-07-05T05:12:44Z"}],"graph_snapshots":[{"event_id":"sha256:b8b5b3e6db283c89018b826cef563e4791378702e46bd1143e3d8f1cba37bfcc","target":"graph","created_at":"2026-07-05T05:12:44Z","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/2209.14156/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we present the Textless Vision-Language Transformer (TVLT), where homogeneous transformer blocks take raw visual and audio inputs for vision-and-language representation learning with minimal modality-specific design, and do not use text-specific modules such as tokenization or automatic speech recognition (ASR). TVLT is trained by reconstructing masked patches of continuous video frames and audio spectrograms (masked autoencoding) and contrastive modeling to align video and audio. TVLT attains performance comparable to its text-based counterpart on various multimodal tasks, such ","authors_text":"Jaemin Cho, Mohit Bansal, Yixin Nie, Zineng Tang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-28T15:08:03Z","title":"TVLT: Textless Vision-Language Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14156","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":"sha256:534722921117d7fa0efe0da03de4a91bacfa370222e93e2ce4b8afa96ba3aa77","target":"record","created_at":"2026-07-05T05:12:44Z","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":"8f014f1d585372c5d940588382a01fb38c9261ef10de161a69d38c4a5ecc03b2","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-28T15:08:03Z","title_canon_sha256":"ff7d339f08f1decf6c19cc294a01f9986d0e1dc33ea4aeec5f8adbd73918f80c"},"schema_version":"1.0","source":{"id":"2209.14156","kind":"arxiv","version":2}},"canonical_sha256":"e788e7928b375328a9b90f4b6ef1970594dc878c2b3fef43ef9744a692439f32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e788e7928b375328a9b90f4b6ef1970594dc878c2b3fef43ef9744a692439f32","first_computed_at":"2026-07-05T05:12:44.543401Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:12:44.543401Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tiguprbiPMxDihpm9DbupYFFdLSAtLNpSZ0kEIgfWFRSZqEO8KGnYBEwpBp1uq77zIbauzDtXmte5jqp4wAwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:12:44.543899Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.14156","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:534722921117d7fa0efe0da03de4a91bacfa370222e93e2ce4b8afa96ba3aa77","sha256:b8b5b3e6db283c89018b826cef563e4791378702e46bd1143e3d8f1cba37bfcc"],"state_sha256":"da88517d05ccbcae3b2c4446f9370a354cc550f938ab1c49d64a5941ffb0e794"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FGyg0zUvPJxI9hdUX5XBBP4uV53tmI1wUSw1GeOAdvRS9Dx+P+SHvoB+4IVIs7/AeJqUWpW2gmckRH4dheM8BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T18:54:16.390566Z","bundle_sha256":"c0e221c4adea78a424a33511d74195b24ad524f4e937e1c6d5b2922394ced6fd"}}