{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JLWZISH5CJH4Q5EWPSTVMRECF2","short_pith_number":"pith:JLWZISH5","schema_version":"1.0","canonical_sha256":"4aed9448fd124fc874967ca75644822ea38e479006636da663c55f1a5776c047","source":{"kind":"arxiv","id":"2410.05227","version":2},"attestation_state":"computed","paper":{"title":"The Dawn of Video Generation: Preliminary Explorations with SORA-like Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Weidong Chen, Wei Liu, Yuhang Yang","submitted_at":"2024-10-07T17:35:10Z","abstract_excerpt":"High-quality video generation, encompassing text-to-video (T2V), image-to-video (I2V), and video-to-video (V2V) generation, holds considerable significance in content creation to benefit anyone express their inherent creativity in new ways and world simulation to modeling and understanding the world. Models like SORA have advanced generating videos with higher resolution, more natural motion, better vision-language alignment, and increased controllability, particularly for long video sequences. These improvements have been driven by the evolution of model architectures, shifting from UNet to m"},"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":"2410.05227","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-07T17:35:10Z","cross_cats_sorted":[],"title_canon_sha256":"15479eae2730903aa061d533cc84364eb953b120720f70336c98ac24bd8d4edb","abstract_canon_sha256":"d964fd908d910fc4ef30572e212c40a640492194d2efd580054f0db318f91bf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:31.088843Z","signature_b64":"Ww7uHqMEggPzTUnHCxbq8Pkr8qYt8Kc8BeVsIZtxdedZIET21DW0JAKL8XJSlkZfYBiWEwvkKtyH7mBREgy3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4aed9448fd124fc874967ca75644822ea38e479006636da663c55f1a5776c047","last_reissued_at":"2026-07-05T09:18:31.088379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:31.088379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Dawn of Video Generation: Preliminary Explorations with SORA-like Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Weidong Chen, Wei Liu, Yuhang Yang","submitted_at":"2024-10-07T17:35:10Z","abstract_excerpt":"High-quality video generation, encompassing text-to-video (T2V), image-to-video (I2V), and video-to-video (V2V) generation, holds considerable significance in content creation to benefit anyone express their inherent creativity in new ways and world simulation to modeling and understanding the world. Models like SORA have advanced generating videos with higher resolution, more natural motion, better vision-language alignment, and increased controllability, particularly for long video sequences. These improvements have been driven by the evolution of model architectures, shifting from UNet to m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05227","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/2410.05227/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":"2410.05227","created_at":"2026-07-05T09:18:31.088430+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.05227v2","created_at":"2026-07-05T09:18:31.088430+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05227","created_at":"2026-07-05T09:18:31.088430+00:00"},{"alias_kind":"pith_short_12","alias_value":"JLWZISH5CJH4","created_at":"2026-07-05T09:18:31.088430+00:00"},{"alias_kind":"pith_short_16","alias_value":"JLWZISH5CJH4Q5EW","created_at":"2026-07-05T09:18:31.088430+00:00"},{"alias_kind":"pith_short_8","alias_value":"JLWZISH5","created_at":"2026-07-05T09:18:31.088430+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.04068","citing_title":"Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2601.04068","citing_title":"Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13918","citing_title":"Improving Video Generation with Human Feedback","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05922","citing_title":"Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07823","citing_title":"LPM 1.0: Video-based Character Performance Model","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JLWZISH5CJH4Q5EWPSTVMRECF2","json":"https://pith.science/pith/JLWZISH5CJH4Q5EWPSTVMRECF2.json","graph_json":"https://pith.science/api/pith-number/JLWZISH5CJH4Q5EWPSTVMRECF2/graph.json","events_json":"https://pith.science/api/pith-number/JLWZISH5CJH4Q5EWPSTVMRECF2/events.json","paper":"https://pith.science/paper/JLWZISH5"},"agent_actions":{"view_html":"https://pith.science/pith/JLWZISH5CJH4Q5EWPSTVMRECF2","download_json":"https://pith.science/pith/JLWZISH5CJH4Q5EWPSTVMRECF2.json","view_paper":"https://pith.science/paper/JLWZISH5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.05227&json=true","fetch_graph":"https://pith.science/api/pith-number/JLWZISH5CJH4Q5EWPSTVMRECF2/graph.json","fetch_events":"https://pith.science/api/pith-number/JLWZISH5CJH4Q5EWPSTVMRECF2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JLWZISH5CJH4Q5EWPSTVMRECF2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JLWZISH5CJH4Q5EWPSTVMRECF2/action/storage_attestation","attest_author":"https://pith.science/pith/JLWZISH5CJH4Q5EWPSTVMRECF2/action/author_attestation","sign_citation":"https://pith.science/pith/JLWZISH5CJH4Q5EWPSTVMRECF2/action/citation_signature","submit_replication":"https://pith.science/pith/JLWZISH5CJH4Q5EWPSTVMRECF2/action/replication_record"}},"created_at":"2026-07-05T09:18:31.088430+00:00","updated_at":"2026-07-05T09:18:31.088430+00:00"}