{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7GSVLARAQPGPNSPN6WKYJ3KXP2","short_pith_number":"pith:7GSVLARA","schema_version":"1.0","canonical_sha256":"f9a555822083ccf6c9edf59584ed577ea280046e0f6fc8bbce9400ee521ab920","source":{"kind":"arxiv","id":"2309.15818","version":3},"attestation_state":"computed","paper":{"title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Junhao Zhang, Difei Gao, Jay Zhangjie Wu, Jia-Wei Liu, Lingmin Ran, Mike Zheng Shou, Rui Zhao, Yuchao Gu","submitted_at":"2023-09-27T17:44:18Z","abstract_excerpt":"Significant advancements have been achieved in the realm of large-scale pre-trained text-to-video Diffusion Models (VDMs). However, previous methods either rely solely on pixel-based VDMs, which come with high computational costs, or on latent-based VDMs, which often struggle with precise text-video alignment. In this paper, we are the first to propose a hybrid model, dubbed as Show-1, which marries pixel-based and latent-based VDMs for text-to-video generation. Our model first uses pixel-based VDMs to produce a low-resolution video of strong text-video correlation. After that, we propose a no"},"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":"2309.15818","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-27T17:44:18Z","cross_cats_sorted":[],"title_canon_sha256":"35ad0ca0654236df5f00576f93af9f2cc0e7ae790782f69871291db367171a38","abstract_canon_sha256":"353626f0b47dbee9199084e2da642e35827f07fdcf381ae107229f72ccd02614"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:15.855638Z","signature_b64":"dauFgsJ3kYRaihndTYQQ6X/rwM69b6/ZG8iLZzsN5WvCvBQo8WnOtkqvZsxE23fqUMwlhsXPT6EqJFj0c9RzCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9a555822083ccf6c9edf59584ed577ea280046e0f6fc8bbce9400ee521ab920","last_reissued_at":"2026-07-05T11:12:15.855057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:15.855057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Junhao Zhang, Difei Gao, Jay Zhangjie Wu, Jia-Wei Liu, Lingmin Ran, Mike Zheng Shou, Rui Zhao, Yuchao Gu","submitted_at":"2023-09-27T17:44:18Z","abstract_excerpt":"Significant advancements have been achieved in the realm of large-scale pre-trained text-to-video Diffusion Models (VDMs). However, previous methods either rely solely on pixel-based VDMs, which come with high computational costs, or on latent-based VDMs, which often struggle with precise text-video alignment. In this paper, we are the first to propose a hybrid model, dubbed as Show-1, which marries pixel-based and latent-based VDMs for text-to-video generation. Our model first uses pixel-based VDMs to produce a low-resolution video of strong text-video correlation. After that, we propose a no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.15818","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/2309.15818/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":"2309.15818","created_at":"2026-07-05T11:12:15.855129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.15818v3","created_at":"2026-07-05T11:12:15.855129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.15818","created_at":"2026-07-05T11:12:15.855129+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GSVLARAQPGP","created_at":"2026-07-05T11:12:15.855129+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GSVLARAQPGPNSPN","created_at":"2026-07-05T11:12:15.855129+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GSVLARA","created_at":"2026-07-05T11:12:15.855129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.14169","citing_title":"Autoregressive Video Generation without Vector Quantization","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2312.14125","citing_title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2407.02371","citing_title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21755","citing_title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15564","citing_title":"Show-o2: Improved Native Unified Multimodal Models","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2409.18869","citing_title":"Emu3: Next-Token Prediction is All You Need","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07402","citing_title":"Accelerating Training of Autoregressive Video Generation Models via Local Optimization with Representation Continuity","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2408.06072","citing_title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","ref_index":110,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7GSVLARAQPGPNSPN6WKYJ3KXP2","json":"https://pith.science/pith/7GSVLARAQPGPNSPN6WKYJ3KXP2.json","graph_json":"https://pith.science/api/pith-number/7GSVLARAQPGPNSPN6WKYJ3KXP2/graph.json","events_json":"https://pith.science/api/pith-number/7GSVLARAQPGPNSPN6WKYJ3KXP2/events.json","paper":"https://pith.science/paper/7GSVLARA"},"agent_actions":{"view_html":"https://pith.science/pith/7GSVLARAQPGPNSPN6WKYJ3KXP2","download_json":"https://pith.science/pith/7GSVLARAQPGPNSPN6WKYJ3KXP2.json","view_paper":"https://pith.science/paper/7GSVLARA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.15818&json=true","fetch_graph":"https://pith.science/api/pith-number/7GSVLARAQPGPNSPN6WKYJ3KXP2/graph.json","fetch_events":"https://pith.science/api/pith-number/7GSVLARAQPGPNSPN6WKYJ3KXP2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GSVLARAQPGPNSPN6WKYJ3KXP2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GSVLARAQPGPNSPN6WKYJ3KXP2/action/storage_attestation","attest_author":"https://pith.science/pith/7GSVLARAQPGPNSPN6WKYJ3KXP2/action/author_attestation","sign_citation":"https://pith.science/pith/7GSVLARAQPGPNSPN6WKYJ3KXP2/action/citation_signature","submit_replication":"https://pith.science/pith/7GSVLARAQPGPNSPN6WKYJ3KXP2/action/replication_record"}},"created_at":"2026-07-05T11:12:15.855129+00:00","updated_at":"2026-07-05T11:12:15.855129+00:00"}