{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:34XB6TJBRL6YQOYBMQL46MSBQ3","short_pith_number":"pith:34XB6TJB","schema_version":"1.0","canonical_sha256":"df2e1f4d218afd883b016417cf324186e1a09928c843fba028ab5aaff4ae6139","source":{"kind":"arxiv","id":"2401.09047","version":1},"attestation_state":"computed","paper":{"title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Weng, Haoxin Chen, Menghan Xia, Xiaodong Cun, Xintao Wang, Ying Shan, Yong Zhang","submitted_at":"2024-01-17T08:30:32Z","abstract_excerpt":"Text-to-video generation aims to produce a video based on a given prompt. Recently, several commercial video models have been able to generate plausible videos with minimal noise, excellent details, and high aesthetic scores. However, these models rely on large-scale, well-filtered, high-quality videos that are not accessible to the community. Many existing research works, which train models using the low-quality WebVid-10M dataset, struggle to generate high-quality videos because the models are optimized to fit WebVid-10M. In this work, we explore the training scheme of video models extended "},"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":"2401.09047","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-17T08:30:32Z","cross_cats_sorted":[],"title_canon_sha256":"ea88f873525b178fd13417ee988aec5d02a674b99e35b7e5011dc4a538cc2bf6","abstract_canon_sha256":"cfa25d94ee8b15160451c3bc762b3243070c77481ff09563d16f7bfc04215ac4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:34:38.746362Z","signature_b64":"XCqPd6+lNWdozgrqRnuMojJ/Ba0Ol/rYw+zd5wPShQJA2+vWDC0YR5yCOHwEzlkaLvV5FjmP3wOQbvCMkLbOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df2e1f4d218afd883b016417cf324186e1a09928c843fba028ab5aaff4ae6139","last_reissued_at":"2026-07-05T07:34:38.745927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:34:38.745927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Weng, Haoxin Chen, Menghan Xia, Xiaodong Cun, Xintao Wang, Ying Shan, Yong Zhang","submitted_at":"2024-01-17T08:30:32Z","abstract_excerpt":"Text-to-video generation aims to produce a video based on a given prompt. Recently, several commercial video models have been able to generate plausible videos with minimal noise, excellent details, and high aesthetic scores. However, these models rely on large-scale, well-filtered, high-quality videos that are not accessible to the community. Many existing research works, which train models using the low-quality WebVid-10M dataset, struggle to generate high-quality videos because the models are optimized to fit WebVid-10M. In this work, we explore the training scheme of video models extended "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.09047","kind":"arxiv","version":1},"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/2401.09047/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":"2401.09047","created_at":"2026-07-05T07:34:38.745973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.09047v1","created_at":"2026-07-05T07:34:38.745973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.09047","created_at":"2026-07-05T07:34:38.745973+00:00"},{"alias_kind":"pith_short_12","alias_value":"34XB6TJBRL6Y","created_at":"2026-07-05T07:34:38.745973+00:00"},{"alias_kind":"pith_short_16","alias_value":"34XB6TJBRL6YQOYB","created_at":"2026-07-05T07:34:38.745973+00:00"},{"alias_kind":"pith_short_8","alias_value":"34XB6TJB","created_at":"2026-07-05T07:34:38.745973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00567","citing_title":"Activation Concentration: Characterizing Column-Level Output Sparsity Across Diffusion Model Architectures","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2602.05202","citing_title":"GT-SVJ: Generative-Transformer-Based Self-Supervised Video Judge For Efficient Video Reward Modeling","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15115","citing_title":"Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17184","citing_title":"Substantial, Decomposable, and Invisible: Visual Context Misalignment in Instructional Videos for Physical Tasks","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2406.03520","citing_title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07982","citing_title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24702","citing_title":"Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28064","citing_title":"3D Reconstruction Techniques in the Manufacturing Domain: Applications, Research Opportunities and Use Cases","ref_index":194,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07348","citing_title":"MoRight: Motion Control Done Right","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16987","citing_title":"DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19473","citing_title":"TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/34XB6TJBRL6YQOYBMQL46MSBQ3","json":"https://pith.science/pith/34XB6TJBRL6YQOYBMQL46MSBQ3.json","graph_json":"https://pith.science/api/pith-number/34XB6TJBRL6YQOYBMQL46MSBQ3/graph.json","events_json":"https://pith.science/api/pith-number/34XB6TJBRL6YQOYBMQL46MSBQ3/events.json","paper":"https://pith.science/paper/34XB6TJB"},"agent_actions":{"view_html":"https://pith.science/pith/34XB6TJBRL6YQOYBMQL46MSBQ3","download_json":"https://pith.science/pith/34XB6TJBRL6YQOYBMQL46MSBQ3.json","view_paper":"https://pith.science/paper/34XB6TJB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.09047&json=true","fetch_graph":"https://pith.science/api/pith-number/34XB6TJBRL6YQOYBMQL46MSBQ3/graph.json","fetch_events":"https://pith.science/api/pith-number/34XB6TJBRL6YQOYBMQL46MSBQ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/34XB6TJBRL6YQOYBMQL46MSBQ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/34XB6TJBRL6YQOYBMQL46MSBQ3/action/storage_attestation","attest_author":"https://pith.science/pith/34XB6TJBRL6YQOYBMQL46MSBQ3/action/author_attestation","sign_citation":"https://pith.science/pith/34XB6TJBRL6YQOYBMQL46MSBQ3/action/citation_signature","submit_replication":"https://pith.science/pith/34XB6TJBRL6YQOYBMQL46MSBQ3/action/replication_record"}},"created_at":"2026-07-05T07:34:38.745973+00:00","updated_at":"2026-07-05T07:34:38.745973+00:00"}