{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VMD47GQQOIDX3PRRAAYRCZT3Z3","short_pith_number":"pith:VMD47GQQ","schema_version":"1.0","canonical_sha256":"ab07cf9a1072077dbe31003111667bcefb8fee06aa725e8fe958be255984e926","source":{"kind":"arxiv","id":"2508.13104","version":1},"attestation_state":"computed","paper":{"title":"Precise Action-to-Video Generation Through Visual Action Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Chao Wen, Haoyu Guo, Hujun Bao, Minghan Qin, Ruizhen Hu, Sida Peng, Xiaowei Zhou, Yuang Wang","submitted_at":"2025-08-18T17:12:28Z","abstract_excerpt":"We present visual action prompts, a unified action representation for action-to-video generation of complex high-DoF interactions while maintaining transferable visual dynamics across domains. Action-driven video generation faces a precision-generality trade-off: existing methods using text, primitive actions, or coarse masks offer generality but lack precision, while agent-centric action signals provide precision at the cost of cross-domain transferability. To balance action precision and dynamic transferability, we propose to \"render\" actions into precise visual prompts as domain-agnostic re"},"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":"2508.13104","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-18T17:12:28Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"a42ff050845ac063fe242a4981a6c9816bde07e00f6292210552f1f80fa46328","abstract_canon_sha256":"aa457f81a58a8c30e7580b50bb84a3641a066864d0d9c031fae96058b023e4d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:32.521155Z","signature_b64":"SBmspNpAHnbq2HEGfLIT/xagklbvnrVNiP+85H20N9IBkOcuW/L4JimC6xOeCHbNqg7/tB9EN8RZ9cB86cL/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab07cf9a1072077dbe31003111667bcefb8fee06aa725e8fe958be255984e926","last_reissued_at":"2026-07-05T11:55:32.520671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:32.520671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Precise Action-to-Video Generation Through Visual Action Prompts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Chao Wen, Haoyu Guo, Hujun Bao, Minghan Qin, Ruizhen Hu, Sida Peng, Xiaowei Zhou, Yuang Wang","submitted_at":"2025-08-18T17:12:28Z","abstract_excerpt":"We present visual action prompts, a unified action representation for action-to-video generation of complex high-DoF interactions while maintaining transferable visual dynamics across domains. Action-driven video generation faces a precision-generality trade-off: existing methods using text, primitive actions, or coarse masks offer generality but lack precision, while agent-centric action signals provide precision at the cost of cross-domain transferability. To balance action precision and dynamic transferability, we propose to \"render\" actions into precise visual prompts as domain-agnostic re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13104","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/2508.13104/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":"2508.13104","created_at":"2026-07-05T11:55:32.520726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13104v1","created_at":"2026-07-05T11:55:32.520726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13104","created_at":"2026-07-05T11:55:32.520726+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMD47GQQOIDX","created_at":"2026-07-05T11:55:32.520726+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMD47GQQOIDX3PRR","created_at":"2026-07-05T11:55:32.520726+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMD47GQQ","created_at":"2026-07-05T11:55:32.520726+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26694","citing_title":"PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26694","citing_title":"PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2603.11755","citing_title":"Controllable Egocentric Video Generation via Occlusion-Aware Sparse 3D Hand Joints","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VMD47GQQOIDX3PRRAAYRCZT3Z3","json":"https://pith.science/pith/VMD47GQQOIDX3PRRAAYRCZT3Z3.json","graph_json":"https://pith.science/api/pith-number/VMD47GQQOIDX3PRRAAYRCZT3Z3/graph.json","events_json":"https://pith.science/api/pith-number/VMD47GQQOIDX3PRRAAYRCZT3Z3/events.json","paper":"https://pith.science/paper/VMD47GQQ"},"agent_actions":{"view_html":"https://pith.science/pith/VMD47GQQOIDX3PRRAAYRCZT3Z3","download_json":"https://pith.science/pith/VMD47GQQOIDX3PRRAAYRCZT3Z3.json","view_paper":"https://pith.science/paper/VMD47GQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13104&json=true","fetch_graph":"https://pith.science/api/pith-number/VMD47GQQOIDX3PRRAAYRCZT3Z3/graph.json","fetch_events":"https://pith.science/api/pith-number/VMD47GQQOIDX3PRRAAYRCZT3Z3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMD47GQQOIDX3PRRAAYRCZT3Z3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMD47GQQOIDX3PRRAAYRCZT3Z3/action/storage_attestation","attest_author":"https://pith.science/pith/VMD47GQQOIDX3PRRAAYRCZT3Z3/action/author_attestation","sign_citation":"https://pith.science/pith/VMD47GQQOIDX3PRRAAYRCZT3Z3/action/citation_signature","submit_replication":"https://pith.science/pith/VMD47GQQOIDX3PRRAAYRCZT3Z3/action/replication_record"}},"created_at":"2026-07-05T11:55:32.520726+00:00","updated_at":"2026-07-05T11:55:32.520726+00:00"}