{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2UI56N6ORVY2X5J7ECAWJEDZV6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"587d4bbde06cf75e49751d648c8f541228af64d971e1f932abac2699af16b9de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T17:47:33Z","title_canon_sha256":"7a0be3187336308fb8ef8217f909a391278e354f78795642f28525c6b5097e8d"},"schema_version":"1.0","source":{"id":"2312.02919","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.02919","created_at":"2026-07-05T07:20:44Z"},{"alias_kind":"arxiv_version","alias_value":"2312.02919v1","created_at":"2026-07-05T07:20:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.02919","created_at":"2026-07-05T07:20:44Z"},{"alias_kind":"pith_short_12","alias_value":"2UI56N6ORVY2","created_at":"2026-07-05T07:20:44Z"},{"alias_kind":"pith_short_16","alias_value":"2UI56N6ORVY2X5J7","created_at":"2026-07-05T07:20:44Z"},{"alias_kind":"pith_short_8","alias_value":"2UI56N6O","created_at":"2026-07-05T07:20:44Z"}],"graph_snapshots":[{"event_id":"sha256:0b766e873abffde4439655aaf3d2ffe00fa5cfa249359400efe1432e464a2e08","target":"graph","created_at":"2026-07-05T07:20:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.02919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-video generation has shown promising results. However, by taking only natural languages as input, users often face difficulties in providing detailed information to precisely control the model's output. In this work, we propose fine-grained controllable video generation (FACTOR) to achieve detailed control. Specifically, FACTOR aims to control objects' appearances and context, including their location and category, in conjunction with the text prompt. To achieve detailed control, we propose a unified framework to jointly inject control signals into the existing text-to-video model. Our","authors_text":"Deqing Sun, Hsin-Ping Huang, Lu Jiang, Ming-Hsuan Yang, Xuhui Jia, Yu-Chuan Su, Yukun Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T17:47:33Z","title":"Fine-grained Controllable Video Generation via Object Appearance and Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.02919","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cde00eb10bfa8e379f2a67827e5440e01b55f075aadc9b9e171919220295f0bc","target":"record","created_at":"2026-07-05T07:20:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"587d4bbde06cf75e49751d648c8f541228af64d971e1f932abac2699af16b9de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T17:47:33Z","title_canon_sha256":"7a0be3187336308fb8ef8217f909a391278e354f78795642f28525c6b5097e8d"},"schema_version":"1.0","source":{"id":"2312.02919","kind":"arxiv","version":1}},"canonical_sha256":"d511df37ce8d71abf53f2081649079af912bf3df029e1a010cfd870d56c21b2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d511df37ce8d71abf53f2081649079af912bf3df029e1a010cfd870d56c21b2c","first_computed_at":"2026-07-05T07:20:44.625641Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:20:44.625641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wbeId17mSE89H7rtiRvEZy3aWXV0KAgYWLjmHJCJxTiW9dfPmwm6lLGiHt6hPj1BNc5utiutC0oUEUdpdThADg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:20:44.626132Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.02919","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cde00eb10bfa8e379f2a67827e5440e01b55f075aadc9b9e171919220295f0bc","sha256:0b766e873abffde4439655aaf3d2ffe00fa5cfa249359400efe1432e464a2e08"],"state_sha256":"26c3463f5654fd3a07429dceef2485140ceefc574d4e05b6defccb8be9894b44"}