{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4Q7IAPHI4YE7LDMEZHU3IBIBHT","short_pith_number":"pith:4Q7IAPHI","schema_version":"1.0","canonical_sha256":"e43e803ce8e609f58d84c9e9b405013cf3f87616e4d4c311ecdbd31b52f04aaf","source":{"kind":"arxiv","id":"1904.01766","version":2},"attestation_state":"computed","paper":{"title":"VideoBERT: A Joint Model for Video and Language Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Austin Myers, Carl Vondrick, Chen Sun, Cordelia Schmid, Kevin Murphy","submitted_at":"2019-04-03T04:40:16Z","abstract_excerpt":"Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint visual-linguistic model to learn high-level features without any explicit supervision. In particular, inspired by its recent success in language modeling, we build upon the BERT model to learn bidirectional joint distributions over sequences of visual and linguistic tokens, derived from vector quantization of video data and off-the-shelf speech recognition outputs, respect"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1904.01766","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-03T04:40:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9aa82ca3226372674cb640a09ca42bc340d2c405bc87bc54ddb08d73ddf419e0","abstract_canon_sha256":"1e2e448e4a3d91bb15fbf25bd0eedd44b781f6d7cdd5e4195481d2873cbee5e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:07.918493Z","signature_b64":"bm3ah24HDBTRP8mBnsYWOum+at6vPro5Dal+5B99RJMKk/MP35g0YHlX8a9VsmGIOSSF2R3OVDfRLD7rzO7tCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e43e803ce8e609f58d84c9e9b405013cf3f87616e4d4c311ecdbd31b52f04aaf","last_reissued_at":"2026-07-05T00:04:07.918059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:07.918059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoBERT: A Joint Model for Video and Language Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Austin Myers, Carl Vondrick, Chen Sun, Cordelia Schmid, Kevin Murphy","submitted_at":"2019-04-03T04:40:16Z","abstract_excerpt":"Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint visual-linguistic model to learn high-level features without any explicit supervision. In particular, inspired by its recent success in language modeling, we build upon the BERT model to learn bidirectional joint distributions over sequences of visual and linguistic tokens, derived from vector quantization of video data and off-the-shelf speech recognition outputs, respect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01766","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/1904.01766/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1904.01766","created_at":"2026-07-05T00:04:07.918108+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.01766v2","created_at":"2026-07-05T00:04:07.918108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01766","created_at":"2026-07-05T00:04:07.918108+00:00"},{"alias_kind":"pith_short_12","alias_value":"4Q7IAPHI4YE7","created_at":"2026-07-05T00:04:07.918108+00:00"},{"alias_kind":"pith_short_16","alias_value":"4Q7IAPHI4YE7LDME","created_at":"2026-07-05T00:04:07.918108+00:00"},{"alias_kind":"pith_short_8","alias_value":"4Q7IAPHI","created_at":"2026-07-05T00:04:07.918108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1908.03557","citing_title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2002.08155","citing_title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4Q7IAPHI4YE7LDMEZHU3IBIBHT","json":"https://pith.science/pith/4Q7IAPHI4YE7LDMEZHU3IBIBHT.json","graph_json":"https://pith.science/api/pith-number/4Q7IAPHI4YE7LDMEZHU3IBIBHT/graph.json","events_json":"https://pith.science/api/pith-number/4Q7IAPHI4YE7LDMEZHU3IBIBHT/events.json","paper":"https://pith.science/paper/4Q7IAPHI"},"agent_actions":{"view_html":"https://pith.science/pith/4Q7IAPHI4YE7LDMEZHU3IBIBHT","download_json":"https://pith.science/pith/4Q7IAPHI4YE7LDMEZHU3IBIBHT.json","view_paper":"https://pith.science/paper/4Q7IAPHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.01766&json=true","fetch_graph":"https://pith.science/api/pith-number/4Q7IAPHI4YE7LDMEZHU3IBIBHT/graph.json","fetch_events":"https://pith.science/api/pith-number/4Q7IAPHI4YE7LDMEZHU3IBIBHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4Q7IAPHI4YE7LDMEZHU3IBIBHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4Q7IAPHI4YE7LDMEZHU3IBIBHT/action/storage_attestation","attest_author":"https://pith.science/pith/4Q7IAPHI4YE7LDMEZHU3IBIBHT/action/author_attestation","sign_citation":"https://pith.science/pith/4Q7IAPHI4YE7LDMEZHU3IBIBHT/action/citation_signature","submit_replication":"https://pith.science/pith/4Q7IAPHI4YE7LDMEZHU3IBIBHT/action/replication_record"}},"created_at":"2026-07-05T00:04:07.918108+00:00","updated_at":"2026-07-05T00:04:07.918108+00:00"}