{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D5DZ64FR56QJWDBKLXE2DV4U7X","short_pith_number":"pith:D5DZ64FR","schema_version":"1.0","canonical_sha256":"1f479f70b1efa09b0c2a5dc9a1d794fdeb93986ac34d9cc1a330cb5ee9b3e0b1","source":{"kind":"arxiv","id":"2508.15720","version":1},"attestation_state":"computed","paper":{"title":"WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angtian Wang, Linjie Yang, Mengzhao Chen, Mingfei Han, Ping Luo, Qiushan Guo, Shoufa Chen, Xueqing Deng, Zeyue Xue, Zhiheng Liu","submitted_at":"2025-08-21T16:57:33Z","abstract_excerpt":"Generative video modeling has made significant strides, yet ensuring structural and temporal consistency over long sequences remains a challenge. Current methods predominantly rely on RGB signals, leading to accumulated errors in object structure and motion over extended durations. To address these issues, we introduce WorldWeaver, a robust framework for long video generation that jointly models RGB frames and perceptual conditions within a unified long-horizon modeling scheme. Our training framework offers three key advantages. First, by jointly predicting perceptual conditions and color info"},"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":"2508.15720","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-21T16:57:33Z","cross_cats_sorted":[],"title_canon_sha256":"6b8fcf4da85d566db55f6d259f8cb2a490215d437fb0d5e46afc08d5489187f2","abstract_canon_sha256":"712dbb855b372b912511ae8ed0b3252d16682da50757f89272aa3acc6719c909"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:17.612896Z","signature_b64":"PxHvjq77Lf5YZ9HNHhzlA2MyEjkgCjI1OXf90Il/j05B8cG5s9usw9DtduKzK0Smpj/pIEvaEPdAlCefVk2hDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f479f70b1efa09b0c2a5dc9a1d794fdeb93986ac34d9cc1a330cb5ee9b3e0b1","last_reissued_at":"2026-07-05T11:57:17.612456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:17.612456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angtian Wang, Linjie Yang, Mengzhao Chen, Mingfei Han, Ping Luo, Qiushan Guo, Shoufa Chen, Xueqing Deng, Zeyue Xue, Zhiheng Liu","submitted_at":"2025-08-21T16:57:33Z","abstract_excerpt":"Generative video modeling has made significant strides, yet ensuring structural and temporal consistency over long sequences remains a challenge. Current methods predominantly rely on RGB signals, leading to accumulated errors in object structure and motion over extended durations. To address these issues, we introduce WorldWeaver, a robust framework for long video generation that jointly models RGB frames and perceptual conditions within a unified long-horizon modeling scheme. Our training framework offers three key advantages. First, by jointly predicting perceptual conditions and color info"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15720","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/2508.15720/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":"2508.15720","created_at":"2026-07-05T11:57:17.612531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.15720v1","created_at":"2026-07-05T11:57:17.612531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15720","created_at":"2026-07-05T11:57:17.612531+00:00"},{"alias_kind":"pith_short_12","alias_value":"D5DZ64FR56QJ","created_at":"2026-07-05T11:57:17.612531+00:00"},{"alias_kind":"pith_short_16","alias_value":"D5DZ64FR56QJWDBK","created_at":"2026-07-05T11:57:17.612531+00:00"},{"alias_kind":"pith_short_8","alias_value":"D5DZ64FR","created_at":"2026-07-05T11:57:17.612531+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13289","citing_title":"HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers","ref_index":250,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01896","citing_title":"Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31590","citing_title":"TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2509.25161","citing_title":"Rolling Forcing: Autoregressive Long Video Diffusion in Real Time","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2510.02283","citing_title":"Self-Forcing++: Towards Minute-Scale High-Quality Video Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09442","citing_title":"SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01896","citing_title":"Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D5DZ64FR56QJWDBKLXE2DV4U7X","json":"https://pith.science/pith/D5DZ64FR56QJWDBKLXE2DV4U7X.json","graph_json":"https://pith.science/api/pith-number/D5DZ64FR56QJWDBKLXE2DV4U7X/graph.json","events_json":"https://pith.science/api/pith-number/D5DZ64FR56QJWDBKLXE2DV4U7X/events.json","paper":"https://pith.science/paper/D5DZ64FR"},"agent_actions":{"view_html":"https://pith.science/pith/D5DZ64FR56QJWDBKLXE2DV4U7X","download_json":"https://pith.science/pith/D5DZ64FR56QJWDBKLXE2DV4U7X.json","view_paper":"https://pith.science/paper/D5DZ64FR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.15720&json=true","fetch_graph":"https://pith.science/api/pith-number/D5DZ64FR56QJWDBKLXE2DV4U7X/graph.json","fetch_events":"https://pith.science/api/pith-number/D5DZ64FR56QJWDBKLXE2DV4U7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D5DZ64FR56QJWDBKLXE2DV4U7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D5DZ64FR56QJWDBKLXE2DV4U7X/action/storage_attestation","attest_author":"https://pith.science/pith/D5DZ64FR56QJWDBKLXE2DV4U7X/action/author_attestation","sign_citation":"https://pith.science/pith/D5DZ64FR56QJWDBKLXE2DV4U7X/action/citation_signature","submit_replication":"https://pith.science/pith/D5DZ64FR56QJWDBKLXE2DV4U7X/action/replication_record"}},"created_at":"2026-07-05T11:57:17.612531+00:00","updated_at":"2026-07-05T11:57:17.612531+00:00"}