{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PCNSM6GEURITXEFUJBWE52RYDK","short_pith_number":"pith:PCNSM6GE","schema_version":"1.0","canonical_sha256":"789b2678c4a4513b90b4486c4eea381abb63c70bde4d3107ecf8f1884f7d1fae","source":{"kind":"arxiv","id":"2411.02394","version":1},"attestation_state":"computed","paper":{"title":"AutoVFX: Physically Realistic Video Editing from Natural Language Instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Zhai, Hao-Yu Hsu, Hongchi Xia, Shenlong Wang, Zhi-Hao Lin","submitted_at":"2024-11-04T18:59:05Z","abstract_excerpt":"Modern visual effects (VFX) software has made it possible for skilled artists to create imagery of virtually anything. However, the creation process remains laborious, complex, and largely inaccessible to everyday users. In this work, we present AutoVFX, a framework that automatically creates realistic and dynamic VFX videos from a single video and natural language instructions. By carefully integrating neural scene modeling, LLM-based code generation, and physical simulation, AutoVFX is able to provide physically-grounded, photorealistic editing effects that can be controlled directly using n"},"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":"2411.02394","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-04T18:59:05Z","cross_cats_sorted":[],"title_canon_sha256":"724340d865feb6e4ea704cbd6f7dd995ca3764976c8c469b825d98f4aa6b3b37","abstract_canon_sha256":"216740757f4afd4cdd37b3efc0f14343590170567ca3fec95cbf14bcf8400b93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:53.029540Z","signature_b64":"vN525o2l/fZRUVaNdQUNz19HwP2204hqDY/ggcq8PhM918d3NLccXx8dWM1I1tZX+pGOrzQRsgTiLI4J+guKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"789b2678c4a4513b90b4486c4eea381abb63c70bde4d3107ecf8f1884f7d1fae","last_reissued_at":"2026-07-05T09:30:53.029003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:53.029003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoVFX: Physically Realistic Video Editing from Natural Language Instructions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Albert Zhai, Hao-Yu Hsu, Hongchi Xia, Shenlong Wang, Zhi-Hao Lin","submitted_at":"2024-11-04T18:59:05Z","abstract_excerpt":"Modern visual effects (VFX) software has made it possible for skilled artists to create imagery of virtually anything. However, the creation process remains laborious, complex, and largely inaccessible to everyday users. In this work, we present AutoVFX, a framework that automatically creates realistic and dynamic VFX videos from a single video and natural language instructions. By carefully integrating neural scene modeling, LLM-based code generation, and physical simulation, AutoVFX is able to provide physically-grounded, photorealistic editing effects that can be controlled directly using n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02394","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/2411.02394/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":"2411.02394","created_at":"2026-07-05T09:30:53.029063+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.02394v1","created_at":"2026-07-05T09:30:53.029063+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02394","created_at":"2026-07-05T09:30:53.029063+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCNSM6GEURIT","created_at":"2026-07-05T09:30:53.029063+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCNSM6GEURITXEFU","created_at":"2026-07-05T09:30:53.029063+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCNSM6GE","created_at":"2026-07-05T09:30:53.029063+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07508","citing_title":"Streaming Video Generation with Streaming Force Control","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04945","citing_title":"STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00499","citing_title":"OptiWorld: Optimal Control for Video World Generation under Physical Constraints","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2503.20654","citing_title":"AccidentSim: Generating Vehicle Collision Videos with Physically Realistic Collision Trajectories from Real-World Accident Reports","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00177","citing_title":"FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting","ref_index":96,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCNSM6GEURITXEFUJBWE52RYDK","json":"https://pith.science/pith/PCNSM6GEURITXEFUJBWE52RYDK.json","graph_json":"https://pith.science/api/pith-number/PCNSM6GEURITXEFUJBWE52RYDK/graph.json","events_json":"https://pith.science/api/pith-number/PCNSM6GEURITXEFUJBWE52RYDK/events.json","paper":"https://pith.science/paper/PCNSM6GE"},"agent_actions":{"view_html":"https://pith.science/pith/PCNSM6GEURITXEFUJBWE52RYDK","download_json":"https://pith.science/pith/PCNSM6GEURITXEFUJBWE52RYDK.json","view_paper":"https://pith.science/paper/PCNSM6GE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.02394&json=true","fetch_graph":"https://pith.science/api/pith-number/PCNSM6GEURITXEFUJBWE52RYDK/graph.json","fetch_events":"https://pith.science/api/pith-number/PCNSM6GEURITXEFUJBWE52RYDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCNSM6GEURITXEFUJBWE52RYDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCNSM6GEURITXEFUJBWE52RYDK/action/storage_attestation","attest_author":"https://pith.science/pith/PCNSM6GEURITXEFUJBWE52RYDK/action/author_attestation","sign_citation":"https://pith.science/pith/PCNSM6GEURITXEFUJBWE52RYDK/action/citation_signature","submit_replication":"https://pith.science/pith/PCNSM6GEURITXEFUJBWE52RYDK/action/replication_record"}},"created_at":"2026-07-05T09:30:53.029063+00:00","updated_at":"2026-07-05T09:30:53.029063+00:00"}