{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FSC2B5U3FPHSKOXJMECSQEW6LR","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":"f8406ad3c0b6b3d204035dbd6cad99525ff44a2d762278d5deccf1c8a9402562","cross_cats_sorted":["cs.CL","cs.LG","eess.AS","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-15T10:03:25Z","title_canon_sha256":"eb272caaf0fb4145d60929f913544031cfff08dd779727b8e66f2514df1105a3"},"schema_version":"1.0","source":{"id":"2002.06353","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06353","created_at":"2026-07-05T01:35:28Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06353v3","created_at":"2026-07-05T01:35:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06353","created_at":"2026-07-05T01:35:28Z"},{"alias_kind":"pith_short_12","alias_value":"FSC2B5U3FPHS","created_at":"2026-07-05T01:35:28Z"},{"alias_kind":"pith_short_16","alias_value":"FSC2B5U3FPHSKOXJ","created_at":"2026-07-05T01:35:28Z"},{"alias_kind":"pith_short_8","alias_value":"FSC2B5U3","created_at":"2026-07-05T01:35:28Z"}],"graph_snapshots":[{"event_id":"sha256:4e4056542c096f7861832116b44740e6a9d6efa56b8ee3b04c483b02db12219e","target":"graph","created_at":"2026-07-05T01:35:28Z","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/2002.06353/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Botian Shi, Haoyang Huang, Huaishao Luo, Jason Li, Lei Ji, Ming Zhou, Nan Duan, Taroon Bharti, Tianrui Li","cross_cats":["cs.CL","cs.LG","eess.AS","eess.IV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-15T10:03:25Z","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06353","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:ea3c9a1a6340bb75eee7d0ba009c43c028992b40bea9b981bac482bf6d7fd04e","target":"record","created_at":"2026-07-05T01:35:28Z","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":"f8406ad3c0b6b3d204035dbd6cad99525ff44a2d762278d5deccf1c8a9402562","cross_cats_sorted":["cs.CL","cs.LG","eess.AS","eess.IV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-15T10:03:25Z","title_canon_sha256":"eb272caaf0fb4145d60929f913544031cfff08dd779727b8e66f2514df1105a3"},"schema_version":"1.0","source":{"id":"2002.06353","kind":"arxiv","version":3}},"canonical_sha256":"2c85a0f69b2bcf253ae961052812de5c65378f6d1dee1e17384e237f29139041","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c85a0f69b2bcf253ae961052812de5c65378f6d1dee1e17384e237f29139041","first_computed_at":"2026-07-05T01:35:28.662190Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:35:28.662190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KgVv3H8lhytUsxtrSGUZpVVC/6zfwapxI+qIsSIRwSxybNWzHSlYQ/rlpt5NRKt5cn4U9RgQbu8iZ81OlAJpDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:35:28.662709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.06353","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea3c9a1a6340bb75eee7d0ba009c43c028992b40bea9b981bac482bf6d7fd04e","sha256:4e4056542c096f7861832116b44740e6a9d6efa56b8ee3b04c483b02db12219e"],"state_sha256":"97b825915de614931c053107937a1a5fd35a2349c0bbdf294ed92d05ad1cbfd5"}