{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O2N5HQLWSSSIJ3ENSDTANMBS67","short_pith_number":"pith:O2N5HQLW","schema_version":"1.0","canonical_sha256":"769bd3c17694a484ec8d90e606b032f7fbfc061ac35bdd31165a176bed929808","source":{"kind":"arxiv","id":"2403.13501","version":2},"attestation_state":"computed","paper":{"title":"VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Anna Khoreva, Dan Zhang, Margret Keuper, William Beluch, Yumeng Li","submitted_at":"2024-03-20T10:58:58Z","abstract_excerpt":"Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolving content. They tend to synthesize quasi-static videos, ignoring the necessary visual change-over-time implied in the text prompt. At the same time, scaling these models to enable longer, more dynamic video synthesis often remains computationally intractable. To address this challenge, we introduce the concept of Generative Temporal Nursing (GTN), where we aim to alter the generative process on the fly during inferen"},"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":"2403.13501","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T10:58:58Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM"],"title_canon_sha256":"fed67a8ed42ff69f5529c15eee8a03ed3ddcf6b8a978bc0b3b013f5b9747ae59","abstract_canon_sha256":"f1d88af3b88dd2863c9c28aec01854b63c39170ec204b131b2658f3df830530a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:32.589008Z","signature_b64":"5HFG6WJ53jZKJcSMoQGDFX6219F+O8274iz3XpobLAbQUskTyzx/SJeBUB0ClTWicPUjvrGZFXm1kmJGtlnnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"769bd3c17694a484ec8d90e606b032f7fbfc061ac35bdd31165a176bed929808","last_reissued_at":"2026-07-05T10:33:32.588039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:32.588039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Anna Khoreva, Dan Zhang, Margret Keuper, William Beluch, Yumeng Li","submitted_at":"2024-03-20T10:58:58Z","abstract_excerpt":"Despite tremendous progress in the field of text-to-video (T2V) synthesis, open-sourced T2V diffusion models struggle to generate longer videos with dynamically varying and evolving content. They tend to synthesize quasi-static videos, ignoring the necessary visual change-over-time implied in the text prompt. At the same time, scaling these models to enable longer, more dynamic video synthesis often remains computationally intractable. To address this challenge, we introduce the concept of Generative Temporal Nursing (GTN), where we aim to alter the generative process on the fly during inferen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13501","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/2403.13501/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":"2403.13501","created_at":"2026-07-05T10:33:32.588163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13501v2","created_at":"2026-07-05T10:33:32.588163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13501","created_at":"2026-07-05T10:33:32.588163+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2N5HQLWSSSI","created_at":"2026-07-05T10:33:32.588163+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2N5HQLWSSSIJ3EN","created_at":"2026-07-05T10:33:32.588163+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2N5HQLW","created_at":"2026-07-05T10:33:32.588163+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17749","citing_title":"Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2N5HQLWSSSIJ3ENSDTANMBS67","json":"https://pith.science/pith/O2N5HQLWSSSIJ3ENSDTANMBS67.json","graph_json":"https://pith.science/api/pith-number/O2N5HQLWSSSIJ3ENSDTANMBS67/graph.json","events_json":"https://pith.science/api/pith-number/O2N5HQLWSSSIJ3ENSDTANMBS67/events.json","paper":"https://pith.science/paper/O2N5HQLW"},"agent_actions":{"view_html":"https://pith.science/pith/O2N5HQLWSSSIJ3ENSDTANMBS67","download_json":"https://pith.science/pith/O2N5HQLWSSSIJ3ENSDTANMBS67.json","view_paper":"https://pith.science/paper/O2N5HQLW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13501&json=true","fetch_graph":"https://pith.science/api/pith-number/O2N5HQLWSSSIJ3ENSDTANMBS67/graph.json","fetch_events":"https://pith.science/api/pith-number/O2N5HQLWSSSIJ3ENSDTANMBS67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2N5HQLWSSSIJ3ENSDTANMBS67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2N5HQLWSSSIJ3ENSDTANMBS67/action/storage_attestation","attest_author":"https://pith.science/pith/O2N5HQLWSSSIJ3ENSDTANMBS67/action/author_attestation","sign_citation":"https://pith.science/pith/O2N5HQLWSSSIJ3ENSDTANMBS67/action/citation_signature","submit_replication":"https://pith.science/pith/O2N5HQLWSSSIJ3ENSDTANMBS67/action/replication_record"}},"created_at":"2026-07-05T10:33:32.588163+00:00","updated_at":"2026-07-05T10:33:32.588163+00:00"}