{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FSC2B5U3FPHSKOXJMECSQEW6LR","short_pith_number":"pith:FSC2B5U3","schema_version":"1.0","canonical_sha256":"2c85a0f69b2bcf253ae961052812de5c65378f6d1dee1e17384e237f29139041","source":{"kind":"arxiv","id":"2002.06353","version":3},"attestation_state":"computed","paper":{"title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS","eess.IV"],"primary_cat":"cs.CV","authors_text":"Botian Shi, Haoyang Huang, Huaishao Luo, Jason Li, Lei Ji, Ming Zhou, Nan Duan, Taroon Bharti, Tianrui Li","submitted_at":"2020-02-15T10:03:25Z","abstract_excerpt":"With the recent success of the pre-training technique for NLP and image-linguistic tasks, some video-linguistic pre-training works are gradually developed to improve video-text related downstream tasks. However, most of the existing multimodal models are pre-trained for understanding tasks, leading to a pretrain-finetune discrepancy for generation tasks. This paper proposes UniVL: a Unified Video and Language pre-training model for both multimodal understanding and generation. It comprises four components, including two single-modal encoders, a cross encoder, and a decoder with the Transformer"},"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":"2002.06353","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-15T10:03:25Z","cross_cats_sorted":["cs.CL","cs.LG","eess.AS","eess.IV"],"title_canon_sha256":"eb272caaf0fb4145d60929f913544031cfff08dd779727b8e66f2514df1105a3","abstract_canon_sha256":"f8406ad3c0b6b3d204035dbd6cad99525ff44a2d762278d5deccf1c8a9402562"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:35:28.662709Z","signature_b64":"KgVv3H8lhytUsxtrSGUZpVVC/6zfwapxI+qIsSIRwSxybNWzHSlYQ/rlpt5NRKt5cn4U9RgQbu8iZ81OlAJpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c85a0f69b2bcf253ae961052812de5c65378f6d1dee1e17384e237f29139041","last_reissued_at":"2026-07-05T01:35:28.662190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:35:28.662190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","eess.AS","eess.IV"],"primary_cat":"cs.CV","authors_text":"Botian Shi, Haoyang Huang, Huaishao Luo, Jason Li, Lei Ji, Ming Zhou, Nan Duan, Taroon Bharti, Tianrui Li","submitted_at":"2020-02-15T10:03:25Z","abstract_excerpt":"With the recent success of the pre-training technique for NLP and image-linguistic tasks, some video-linguistic pre-training works are gradually developed to improve video-text related downstream tasks. However, most of the existing multimodal models are pre-trained for understanding tasks, leading to a pretrain-finetune discrepancy for generation tasks. This paper proposes UniVL: a Unified Video and Language pre-training model for both multimodal understanding and generation. It comprises four components, including two single-modal encoders, a cross encoder, and a decoder with the Transformer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06353","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/2002.06353/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":"2002.06353","created_at":"2026-07-05T01:35:28.662252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.06353v3","created_at":"2026-07-05T01:35:28.662252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06353","created_at":"2026-07-05T01:35:28.662252+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSC2B5U3FPHS","created_at":"2026-07-05T01:35:28.662252+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSC2B5U3FPHSKOXJ","created_at":"2026-07-05T01:35:28.662252+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSC2B5U3","created_at":"2026-07-05T01:35:28.662252+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.07388","citing_title":"Recent Advances in Multimodal Affective Computing: An NLP Perspective","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2503.13821","citing_title":"Stitch-a-Demo: Video Demonstrations from Multistep Descriptions","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01852","citing_title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","ref_index":186,"is_internal_anchor":false},{"citing_arxiv_id":"2205.14100","citing_title":"GIT: A Generative Image-to-text Transformer for Vision and Language","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16671","citing_title":"Demystifying CLIP Data","ref_index":182,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":206,"is_internal_anchor":false},{"citing_arxiv_id":"2204.14198","citing_title":"Flamingo: a Visual Language Model for Few-Shot Learning","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08762","citing_title":"InstrAct: Towards Action-Centric Understanding in Instructional Videos","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FSC2B5U3FPHSKOXJMECSQEW6LR","json":"https://pith.science/pith/FSC2B5U3FPHSKOXJMECSQEW6LR.json","graph_json":"https://pith.science/api/pith-number/FSC2B5U3FPHSKOXJMECSQEW6LR/graph.json","events_json":"https://pith.science/api/pith-number/FSC2B5U3FPHSKOXJMECSQEW6LR/events.json","paper":"https://pith.science/paper/FSC2B5U3"},"agent_actions":{"view_html":"https://pith.science/pith/FSC2B5U3FPHSKOXJMECSQEW6LR","download_json":"https://pith.science/pith/FSC2B5U3FPHSKOXJMECSQEW6LR.json","view_paper":"https://pith.science/paper/FSC2B5U3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.06353&json=true","fetch_graph":"https://pith.science/api/pith-number/FSC2B5U3FPHSKOXJMECSQEW6LR/graph.json","fetch_events":"https://pith.science/api/pith-number/FSC2B5U3FPHSKOXJMECSQEW6LR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSC2B5U3FPHSKOXJMECSQEW6LR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSC2B5U3FPHSKOXJMECSQEW6LR/action/storage_attestation","attest_author":"https://pith.science/pith/FSC2B5U3FPHSKOXJMECSQEW6LR/action/author_attestation","sign_citation":"https://pith.science/pith/FSC2B5U3FPHSKOXJMECSQEW6LR/action/citation_signature","submit_replication":"https://pith.science/pith/FSC2B5U3FPHSKOXJMECSQEW6LR/action/replication_record"}},"created_at":"2026-07-05T01:35:28.662252+00:00","updated_at":"2026-07-05T01:35:28.662252+00:00"}