{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QNA7BFDHTGVKPDG3BNIBN62DJC","short_pith_number":"pith:QNA7BFDH","schema_version":"1.0","canonical_sha256":"8341f0946799aaa78cdb0b5016fb43489268ab6775095f2c262cdfec677f4c8f","source":{"kind":"arxiv","id":"2605.25077","version":1},"attestation_state":"computed","paper":{"title":"WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Zhao, Bohai Gu, Dazhao Du, Jian Liu, Jie Zhang, Jinxiang Lai, Shuai Yang, Song Guo, Taiyi Wu, Xiaocheng Lu, Xiaotong Zhao, Yueyang Yuan","submitted_at":"2026-05-24T13:40:42Z","abstract_excerpt":"Recent video-based world models have made pixel-space environments interactive at the camera level: users can navigate viewpoints while the model generates coherent visual continuations. Yet their action spaces remain incomplete: users can move the camera, but cannot act on individual objects. Since real-world interaction is inherently object-centric, such models remain closer to passive scene observers than truly manipulable environments. We present WorldCraft, a framework that expands interactive video world models from camera navigation to object-level trajectory actions. Given a user click"},"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":"2605.25077","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T13:40:42Z","cross_cats_sorted":[],"title_canon_sha256":"7894c9b997acc99c2263ef5821b503aa72a12bb1245df87dd089d6d5531e36fa","abstract_canon_sha256":"153f39f9a7d26526d0e82d8fef42b1007cea7b37ea0591edeae9f7524c319768"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:03:38.945413Z","signature_b64":"X6OQDkjZV39jPjK1tX0kA046u4TuBdqR3ylN1c5xuKlizM5rRMtMv0RjMs9vPrNG+MinqpAISotO8M/bvsZeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8341f0946799aaa78cdb0b5016fb43489268ab6775095f2c262cdfec677f4c8f","last_reissued_at":"2026-05-26T02:03:38.944623Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:03:38.944623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WorldCraft: From Camera Navigation to Object Manipulation in Interactive Video World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Zhao, Bohai Gu, Dazhao Du, Jian Liu, Jie Zhang, Jinxiang Lai, Shuai Yang, Song Guo, Taiyi Wu, Xiaocheng Lu, Xiaotong Zhao, Yueyang Yuan","submitted_at":"2026-05-24T13:40:42Z","abstract_excerpt":"Recent video-based world models have made pixel-space environments interactive at the camera level: users can navigate viewpoints while the model generates coherent visual continuations. Yet their action spaces remain incomplete: users can move the camera, but cannot act on individual objects. Since real-world interaction is inherently object-centric, such models remain closer to passive scene observers than truly manipulable environments. We present WorldCraft, a framework that expands interactive video world models from camera navigation to object-level trajectory actions. Given a user click"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25077","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/2605.25077/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":"2605.25077","created_at":"2026-05-26T02:03:38.944754+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25077v1","created_at":"2026-05-26T02:03:38.944754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25077","created_at":"2026-05-26T02:03:38.944754+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNA7BFDHTGVK","created_at":"2026-05-26T02:03:38.944754+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNA7BFDHTGVKPDG3","created_at":"2026-05-26T02:03:38.944754+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNA7BFDH","created_at":"2026-05-26T02:03:38.944754+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/QNA7BFDHTGVKPDG3BNIBN62DJC","json":"https://pith.science/pith/QNA7BFDHTGVKPDG3BNIBN62DJC.json","graph_json":"https://pith.science/api/pith-number/QNA7BFDHTGVKPDG3BNIBN62DJC/graph.json","events_json":"https://pith.science/api/pith-number/QNA7BFDHTGVKPDG3BNIBN62DJC/events.json","paper":"https://pith.science/paper/QNA7BFDH"},"agent_actions":{"view_html":"https://pith.science/pith/QNA7BFDHTGVKPDG3BNIBN62DJC","download_json":"https://pith.science/pith/QNA7BFDHTGVKPDG3BNIBN62DJC.json","view_paper":"https://pith.science/paper/QNA7BFDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25077&json=true","fetch_graph":"https://pith.science/api/pith-number/QNA7BFDHTGVKPDG3BNIBN62DJC/graph.json","fetch_events":"https://pith.science/api/pith-number/QNA7BFDHTGVKPDG3BNIBN62DJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNA7BFDHTGVKPDG3BNIBN62DJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNA7BFDHTGVKPDG3BNIBN62DJC/action/storage_attestation","attest_author":"https://pith.science/pith/QNA7BFDHTGVKPDG3BNIBN62DJC/action/author_attestation","sign_citation":"https://pith.science/pith/QNA7BFDHTGVKPDG3BNIBN62DJC/action/citation_signature","submit_replication":"https://pith.science/pith/QNA7BFDHTGVKPDG3BNIBN62DJC/action/replication_record"}},"created_at":"2026-05-26T02:03:38.944754+00:00","updated_at":"2026-05-26T02:03:38.944754+00:00"}