{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N7QOKKKVV3OGJQNXOBZLHYCKD5","short_pith_number":"pith:N7QOKKKV","schema_version":"1.0","canonical_sha256":"6fe0e52955aedc64c1b77072b3e04a1f5d8387c8f746e628696be94b5ebe63a2","source":{"kind":"arxiv","id":"2503.06053","version":1},"attestation_state":"computed","paper":{"title":"DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baoyu Fan, Cong Xu, Guoguang Du, Jingjing Wang, Liang Jin, Lu Liu, Qi Jia, RenGang Li, Runze Zhang, Xiaochuan Li, Xiaoli Gong, YaQian Zhao, Zhenhua Guo","submitted_at":"2025-03-08T04:37:38Z","abstract_excerpt":"Spatio-temporal consistency is a critical research topic in video generation. A qualified generated video segment must ensure plot plausibility and coherence while maintaining visual consistency of objects and scenes across varying viewpoints. Prior research, especially in open-source projects, primarily focuses on either temporal or spatial consistency, or their basic combination, such as appending a description of a camera movement after a prompt without constraining the outcomes of this movement. However, camera movement may introduce new objects to the scene or eliminate existing ones, the"},"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":"2503.06053","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-08T04:37:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a3992c81e59ec4c16820e582d1fbf345bed730217418f9fb8b5c6dbd0f1096db","abstract_canon_sha256":"a965b0fe0f9dae42cc1027565a42d6fce0d99d682a4aa8b1a6fe616b969ab78f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:52.801406Z","signature_b64":"uZtMMAYbKFKgpGSuL/q+HUr3qenUaUl3kP3TnlNBWfj9iY3nyScj3vhbLEba/bJMHEL54QRtOI8InhSrzTnXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fe0e52955aedc64c1b77072b3e04a1f5d8387c8f746e628696be94b5ebe63a2","last_reissued_at":"2026-07-05T10:26:52.800895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:52.800895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Baoyu Fan, Cong Xu, Guoguang Du, Jingjing Wang, Liang Jin, Lu Liu, Qi Jia, RenGang Li, Runze Zhang, Xiaochuan Li, Xiaoli Gong, YaQian Zhao, Zhenhua Guo","submitted_at":"2025-03-08T04:37:38Z","abstract_excerpt":"Spatio-temporal consistency is a critical research topic in video generation. A qualified generated video segment must ensure plot plausibility and coherence while maintaining visual consistency of objects and scenes across varying viewpoints. Prior research, especially in open-source projects, primarily focuses on either temporal or spatial consistency, or their basic combination, such as appending a description of a camera movement after a prompt without constraining the outcomes of this movement. However, camera movement may introduce new objects to the scene or eliminate existing ones, the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06053","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/2503.06053/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":"2503.06053","created_at":"2026-07-05T10:26:52.800959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06053v1","created_at":"2026-07-05T10:26:52.800959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06053","created_at":"2026-07-05T10:26:52.800959+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7QOKKKVV3OG","created_at":"2026-07-05T10:26:52.800959+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7QOKKKVV3OGJQNX","created_at":"2026-07-05T10:26:52.800959+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7QOKKKV","created_at":"2026-07-05T10:26:52.800959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20470","citing_title":"Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7QOKKKVV3OGJQNXOBZLHYCKD5","json":"https://pith.science/pith/N7QOKKKVV3OGJQNXOBZLHYCKD5.json","graph_json":"https://pith.science/api/pith-number/N7QOKKKVV3OGJQNXOBZLHYCKD5/graph.json","events_json":"https://pith.science/api/pith-number/N7QOKKKVV3OGJQNXOBZLHYCKD5/events.json","paper":"https://pith.science/paper/N7QOKKKV"},"agent_actions":{"view_html":"https://pith.science/pith/N7QOKKKVV3OGJQNXOBZLHYCKD5","download_json":"https://pith.science/pith/N7QOKKKVV3OGJQNXOBZLHYCKD5.json","view_paper":"https://pith.science/paper/N7QOKKKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06053&json=true","fetch_graph":"https://pith.science/api/pith-number/N7QOKKKVV3OGJQNXOBZLHYCKD5/graph.json","fetch_events":"https://pith.science/api/pith-number/N7QOKKKVV3OGJQNXOBZLHYCKD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7QOKKKVV3OGJQNXOBZLHYCKD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7QOKKKVV3OGJQNXOBZLHYCKD5/action/storage_attestation","attest_author":"https://pith.science/pith/N7QOKKKVV3OGJQNXOBZLHYCKD5/action/author_attestation","sign_citation":"https://pith.science/pith/N7QOKKKVV3OGJQNXOBZLHYCKD5/action/citation_signature","submit_replication":"https://pith.science/pith/N7QOKKKVV3OGJQNXOBZLHYCKD5/action/replication_record"}},"created_at":"2026-07-05T10:26:52.800959+00:00","updated_at":"2026-07-05T10:26:52.800959+00:00"}