{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZQAR5GPPFTV6C5SPYHUAEYD3TP","short_pith_number":"pith:ZQAR5GPP","schema_version":"1.0","canonical_sha256":"cc011e99ef2cebe1764fc1e802607b9bd0d05f618f42d7f58bfdbbf0fe949b07","source":{"kind":"arxiv","id":"2602.22960","version":2},"attestation_state":"computed","paper":{"title":"UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bang Zhang, Guangyuan Wang, Li Hu, Peng Zhang, Songhai Zhang, Tianxing Xu, Zhongyi Zhang, Zixuan Wang","submitted_at":"2026-02-26T12:54:46Z","abstract_excerpt":"World models based on video generation demonstrate remarkable potential for simulating interactive environments yet suffer from persistent difficulties in two key areas: maintaining long-term content consistency when scenes are revisited and enabling precise camera control from user-specified inputs. Existing methods based on explicit 3D reconstruction often compromise flexibility in unbounded scenarios and struggle to preserve fine-grained structures. Alternative methods rely directly on previously generated frames without establishing explicit spatial correspondence, thereby limiting control"},"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":"2602.22960","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-26T12:54:46Z","cross_cats_sorted":[],"title_canon_sha256":"bd21f7ae7e3ccb7b519d61e06b44a7cbd5e9fde9aa98f8b3812531a06ef59943","abstract_canon_sha256":"1458e5838fe933cccb65ab7441a17d9176ead5601b068157cc99b2f605df0ebe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:16.995412Z","signature_b64":"ZLai9L3Y9skji+dE8TPGXbE48zfZURU8wcwCddZCfjydhOhLQ/OG1aIvUPStEAflGCiRyuOl7DkgEjY8qWeGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc011e99ef2cebe1764fc1e802607b9bd0d05f618f42d7f58bfdbbf0fe949b07","last_reissued_at":"2026-06-30T02:17:16.994619Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:16.994619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bang Zhang, Guangyuan Wang, Li Hu, Peng Zhang, Songhai Zhang, Tianxing Xu, Zhongyi Zhang, Zixuan Wang","submitted_at":"2026-02-26T12:54:46Z","abstract_excerpt":"World models based on video generation demonstrate remarkable potential for simulating interactive environments yet suffer from persistent difficulties in two key areas: maintaining long-term content consistency when scenes are revisited and enabling precise camera control from user-specified inputs. Existing methods based on explicit 3D reconstruction often compromise flexibility in unbounded scenarios and struggle to preserve fine-grained structures. Alternative methods rely directly on previously generated frames without establishing explicit spatial correspondence, thereby limiting control"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.22960","kind":"arxiv","version":2},"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/2602.22960/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":"2602.22960","created_at":"2026-06-30T02:17:16.994714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.22960v2","created_at":"2026-06-30T02:17:16.994714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.22960","created_at":"2026-06-30T02:17:16.994714+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQAR5GPPFTV6","created_at":"2026-06-30T02:17:16.994714+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQAR5GPPFTV6C5SP","created_at":"2026-06-30T02:17:16.994714+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQAR5GPP","created_at":"2026-06-30T02:17:16.994714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2606.09803","citing_title":"Echo-Memory: A Controlled Study of Memory in Action World Models","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02436","citing_title":"Geometry-Aware Implicit Memory for Video World Models","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15178","citing_title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQAR5GPPFTV6C5SPYHUAEYD3TP","json":"https://pith.science/pith/ZQAR5GPPFTV6C5SPYHUAEYD3TP.json","graph_json":"https://pith.science/api/pith-number/ZQAR5GPPFTV6C5SPYHUAEYD3TP/graph.json","events_json":"https://pith.science/api/pith-number/ZQAR5GPPFTV6C5SPYHUAEYD3TP/events.json","paper":"https://pith.science/paper/ZQAR5GPP"},"agent_actions":{"view_html":"https://pith.science/pith/ZQAR5GPPFTV6C5SPYHUAEYD3TP","download_json":"https://pith.science/pith/ZQAR5GPPFTV6C5SPYHUAEYD3TP.json","view_paper":"https://pith.science/paper/ZQAR5GPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.22960&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQAR5GPPFTV6C5SPYHUAEYD3TP/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQAR5GPPFTV6C5SPYHUAEYD3TP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQAR5GPPFTV6C5SPYHUAEYD3TP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQAR5GPPFTV6C5SPYHUAEYD3TP/action/storage_attestation","attest_author":"https://pith.science/pith/ZQAR5GPPFTV6C5SPYHUAEYD3TP/action/author_attestation","sign_citation":"https://pith.science/pith/ZQAR5GPPFTV6C5SPYHUAEYD3TP/action/citation_signature","submit_replication":"https://pith.science/pith/ZQAR5GPPFTV6C5SPYHUAEYD3TP/action/replication_record"}},"created_at":"2026-06-30T02:17:16.994714+00:00","updated_at":"2026-06-30T02:17:16.994714+00:00"}