{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J4GHEOQUGZL24JMZQDBGMWDW7J","short_pith_number":"pith:J4GHEOQU","schema_version":"1.0","canonical_sha256":"4f0c723a143657ae259980c2665876fa437268476bcbc2609f3304b9c734f468","source":{"kind":"arxiv","id":"2606.19495","version":1},"attestation_state":"computed","paper":{"title":"LooseControlVideo: Directorial Video Control using Spatial Blocking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kalyan Sunkavalli, Niloy J. Mitra, Shariq Farooq Bhat","submitted_at":"2026-06-17T18:32:13Z","abstract_excerpt":"Precise 3D spatial orchestration in text-to-video generation remains a significant challenge, particularly for multi-object scenes where semantic layout and temporal dynamics are often entangled. While existing depth-conditioned models achieve good structural fidelity, they necessitate dense, frame-accurate guidance that is labor-intensive to author for dynamic events involving deformable objects. We present LooseControlVideo, a framework that enables intuitive and expressive control by using sparse, oriented 3D boxes as a \"blocking\" proxy. This allows users to author high-level layout and tra"},"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":"2606.19495","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-17T18:32:13Z","cross_cats_sorted":[],"title_canon_sha256":"1310578185b45c87f95ff80172418749201a32a3dbd9ed14fba71c726966089f","abstract_canon_sha256":"36bfc43b3c231da29e421640c08c08d45da014f21d6073294c71e27258f9e84c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:27.231945Z","signature_b64":"mC7LZKF7rYDD2Y3RbeVEWl2bGH9VoyAiaIAspQDsf/fo1zQ6PNL9Sl0DdeNWKLfBDl2c7X/WeoMbiwsB7fsFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f0c723a143657ae259980c2665876fa437268476bcbc2609f3304b9c734f468","last_reissued_at":"2026-06-19T16:12:27.231595Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:27.231595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LooseControlVideo: Directorial Video Control using Spatial Blocking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kalyan Sunkavalli, Niloy J. Mitra, Shariq Farooq Bhat","submitted_at":"2026-06-17T18:32:13Z","abstract_excerpt":"Precise 3D spatial orchestration in text-to-video generation remains a significant challenge, particularly for multi-object scenes where semantic layout and temporal dynamics are often entangled. While existing depth-conditioned models achieve good structural fidelity, they necessitate dense, frame-accurate guidance that is labor-intensive to author for dynamic events involving deformable objects. We present LooseControlVideo, a framework that enables intuitive and expressive control by using sparse, oriented 3D boxes as a \"blocking\" proxy. This allows users to author high-level layout and tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19495","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/2606.19495/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":"2606.19495","created_at":"2026-06-19T16:12:27.231658+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19495v1","created_at":"2026-06-19T16:12:27.231658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19495","created_at":"2026-06-19T16:12:27.231658+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4GHEOQUGZL2","created_at":"2026-06-19T16:12:27.231658+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4GHEOQUGZL24JMZ","created_at":"2026-06-19T16:12:27.231658+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4GHEOQU","created_at":"2026-06-19T16:12:27.231658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J4GHEOQUGZL24JMZQDBGMWDW7J","json":"https://pith.science/pith/J4GHEOQUGZL24JMZQDBGMWDW7J.json","graph_json":"https://pith.science/api/pith-number/J4GHEOQUGZL24JMZQDBGMWDW7J/graph.json","events_json":"https://pith.science/api/pith-number/J4GHEOQUGZL24JMZQDBGMWDW7J/events.json","paper":"https://pith.science/paper/J4GHEOQU"},"agent_actions":{"view_html":"https://pith.science/pith/J4GHEOQUGZL24JMZQDBGMWDW7J","download_json":"https://pith.science/pith/J4GHEOQUGZL24JMZQDBGMWDW7J.json","view_paper":"https://pith.science/paper/J4GHEOQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19495&json=true","fetch_graph":"https://pith.science/api/pith-number/J4GHEOQUGZL24JMZQDBGMWDW7J/graph.json","fetch_events":"https://pith.science/api/pith-number/J4GHEOQUGZL24JMZQDBGMWDW7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4GHEOQUGZL24JMZQDBGMWDW7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4GHEOQUGZL24JMZQDBGMWDW7J/action/storage_attestation","attest_author":"https://pith.science/pith/J4GHEOQUGZL24JMZQDBGMWDW7J/action/author_attestation","sign_citation":"https://pith.science/pith/J4GHEOQUGZL24JMZQDBGMWDW7J/action/citation_signature","submit_replication":"https://pith.science/pith/J4GHEOQUGZL24JMZQDBGMWDW7J/action/replication_record"}},"created_at":"2026-06-19T16:12:27.231658+00:00","updated_at":"2026-06-19T16:12:27.231658+00:00"}