{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KO55Y7GS2JZDDQDNLO4EVFQN7K","short_pith_number":"pith:KO55Y7GS","schema_version":"1.0","canonical_sha256":"53bbdc7cd2d27231c06d5bb84a960dfab57b3dae25bda2947b8ec93c1e3c2a5a","source":{"kind":"arxiv","id":"1907.06571","version":2},"attestation_state":"computed","paper":{"title":"Adversarial Video Generation on Complex Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Aidan Clark, Jeff Donahue, Karen Simonyan","submitted_at":"2019-07-15T16:27:04Z","abstract_excerpt":"Generative models of natural images have progressed towards high fidelity samples by the strong leveraging of scale. We attempt to carry this success to the field of video modeling by showing that large Generative Adversarial Networks trained on the complex Kinetics-600 dataset are able to produce video samples of substantially higher complexity and fidelity than previous work. Our proposed model, Dual Video Discriminator GAN (DVD-GAN), scales to longer and higher resolution videos by leveraging a computationally efficient decomposition of its discriminator. We evaluate on the related tasks of"},"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":"1907.06571","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-15T16:27:04Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"cedb963026e632f8477f4401484c119b8526d8edd0fa44dbe7864df0d44787b6","abstract_canon_sha256":"881f7b91eb5cdecde8c8f91a0b1d6c4e0c396a368bfcfab3464a4e9e6db120ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:17.541779Z","signature_b64":"ucmBAjk27mqWAOjcm7RAKJV9Z6j/A9jYobg1m3utGHrKSrikq+gAzbVYcVaV+JXW8mlzWJpIqd0T8NDommbZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53bbdc7cd2d27231c06d5bb84a960dfab57b3dae25bda2947b8ec93c1e3c2a5a","last_reissued_at":"2026-07-05T00:07:17.541171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:17.541171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Video Generation on Complex Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Aidan Clark, Jeff Donahue, Karen Simonyan","submitted_at":"2019-07-15T16:27:04Z","abstract_excerpt":"Generative models of natural images have progressed towards high fidelity samples by the strong leveraging of scale. We attempt to carry this success to the field of video modeling by showing that large Generative Adversarial Networks trained on the complex Kinetics-600 dataset are able to produce video samples of substantially higher complexity and fidelity than previous work. Our proposed model, Dual Video Discriminator GAN (DVD-GAN), scales to longer and higher resolution videos by leveraging a computationally efficient decomposition of its discriminator. We evaluate on the related tasks of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.06571","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/1907.06571/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":"1907.06571","created_at":"2026-07-05T00:07:17.541222+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.06571v2","created_at":"2026-07-05T00:07:17.541222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.06571","created_at":"2026-07-05T00:07:17.541222+00:00"},{"alias_kind":"pith_short_12","alias_value":"KO55Y7GS2JZD","created_at":"2026-07-05T00:07:17.541222+00:00"},{"alias_kind":"pith_short_16","alias_value":"KO55Y7GS2JZDDQDN","created_at":"2026-07-05T00:07:17.541222+00:00"},{"alias_kind":"pith_short_8","alias_value":"KO55Y7GS","created_at":"2026-07-05T00:07:17.541222+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18156","citing_title":"ReAge3D: Re-Aging 3D Faces with View Consistency","ref_index":165,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28026","citing_title":"EMOSH: Expressive Motion and Shape Disentanglement for Human Animation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29194","citing_title":"Stochastic Lifting for Generating Trajectories of Stochastic Physical Systems","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00793","citing_title":"MBench: A Comprehensive Benchmark on Memory Capability for Video World Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":160,"is_internal_anchor":false},{"citing_arxiv_id":"2507.13942","citing_title":"Frozen Forecasting: A Unified Evaluation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2210.02399","citing_title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2211.11018","citing_title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2310.05737","citing_title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2204.03458","citing_title":"Video Diffusion Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2205.15868","citing_title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09168","citing_title":"ELT: Elastic Looped Transformers for Visual Generation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06339","citing_title":"Evolution of Video Generative Foundations","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KO55Y7GS2JZDDQDNLO4EVFQN7K","json":"https://pith.science/pith/KO55Y7GS2JZDDQDNLO4EVFQN7K.json","graph_json":"https://pith.science/api/pith-number/KO55Y7GS2JZDDQDNLO4EVFQN7K/graph.json","events_json":"https://pith.science/api/pith-number/KO55Y7GS2JZDDQDNLO4EVFQN7K/events.json","paper":"https://pith.science/paper/KO55Y7GS"},"agent_actions":{"view_html":"https://pith.science/pith/KO55Y7GS2JZDDQDNLO4EVFQN7K","download_json":"https://pith.science/pith/KO55Y7GS2JZDDQDNLO4EVFQN7K.json","view_paper":"https://pith.science/paper/KO55Y7GS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.06571&json=true","fetch_graph":"https://pith.science/api/pith-number/KO55Y7GS2JZDDQDNLO4EVFQN7K/graph.json","fetch_events":"https://pith.science/api/pith-number/KO55Y7GS2JZDDQDNLO4EVFQN7K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KO55Y7GS2JZDDQDNLO4EVFQN7K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KO55Y7GS2JZDDQDNLO4EVFQN7K/action/storage_attestation","attest_author":"https://pith.science/pith/KO55Y7GS2JZDDQDNLO4EVFQN7K/action/author_attestation","sign_citation":"https://pith.science/pith/KO55Y7GS2JZDDQDNLO4EVFQN7K/action/citation_signature","submit_replication":"https://pith.science/pith/KO55Y7GS2JZDDQDNLO4EVFQN7K/action/replication_record"}},"created_at":"2026-07-05T00:07:17.541222+00:00","updated_at":"2026-07-05T00:07:17.541222+00:00"}