{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GLSPWZHVLPDK7O4ESJDCPB32HB","short_pith_number":"pith:GLSPWZHV","schema_version":"1.0","canonical_sha256":"32e4fb64f55bc6afbb84924627877a384234a2549c21028f6bae5dddd62f558f","source":{"kind":"arxiv","id":"2508.15761","version":2},"attestation_state":"computed","paper":{"title":"Waver: Wave Your Way to Lifelike Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyue Peng, Chuang Lin, Fengda Zhu, Hao Yang, Xiaofeng Mei, Yifei Hu, Yifu Zhang, Yi Jiang, Yuqi Zhang, Zehuan Yuan","submitted_at":"2025-08-21T17:56:10Z","abstract_excerpt":"We present Waver, a high-performance foundation model for unified image and video generation. Waver can directly generate videos with durations ranging from 5 to 10 seconds at a native resolution of 720p, which are subsequently upscaled to 1080p. The model simultaneously supports text-to-video (T2V), image-to-video (I2V), and text-to-image (T2I) generation within a single, integrated framework. We introduce a Hybrid Stream DiT architecture to enhance modality alignment and accelerate training convergence. To ensure training data quality, we establish a comprehensive data curation pipeline and "},"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":"2508.15761","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-21T17:56:10Z","cross_cats_sorted":[],"title_canon_sha256":"866ebf021220b086371e034b1d13147916ef6ff4846aecf8f7d7d8732ac6671a","abstract_canon_sha256":"e9d265afc07d1f78f4c50e1180d64080d5b26ca178d2ada625594f8b9837dfa4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:20.522880Z","signature_b64":"VkXqKXeD8eKFDO1dqd3WJyudHxWOWIu8ZkwZNglekHzxc1FrsHntdjU/u9HpeE0Wrg1EA2WXmIBlgoEzHspnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32e4fb64f55bc6afbb84924627877a384234a2549c21028f6bae5dddd62f558f","last_reissued_at":"2026-07-05T11:59:20.522280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:20.522280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Waver: Wave Your Way to Lifelike Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingyue Peng, Chuang Lin, Fengda Zhu, Hao Yang, Xiaofeng Mei, Yifei Hu, Yifu Zhang, Yi Jiang, Yuqi Zhang, Zehuan Yuan","submitted_at":"2025-08-21T17:56:10Z","abstract_excerpt":"We present Waver, a high-performance foundation model for unified image and video generation. Waver can directly generate videos with durations ranging from 5 to 10 seconds at a native resolution of 720p, which are subsequently upscaled to 1080p. The model simultaneously supports text-to-video (T2V), image-to-video (I2V), and text-to-image (T2I) generation within a single, integrated framework. We introduce a Hybrid Stream DiT architecture to enhance modality alignment and accelerate training convergence. To ensure training data quality, we establish a comprehensive data curation pipeline and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15761","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/2508.15761/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":"2508.15761","created_at":"2026-07-05T11:59:20.522359+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.15761v2","created_at":"2026-07-05T11:59:20.522359+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15761","created_at":"2026-07-05T11:59:20.522359+00:00"},{"alias_kind":"pith_short_12","alias_value":"GLSPWZHVLPDK","created_at":"2026-07-05T11:59:20.522359+00:00"},{"alias_kind":"pith_short_16","alias_value":"GLSPWZHVLPDK7O4E","created_at":"2026-07-05T11:59:20.522359+00:00"},{"alias_kind":"pith_short_8","alias_value":"GLSPWZHV","created_at":"2026-07-05T11:59:20.522359+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07675","citing_title":"Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence","ref_index":126,"is_internal_anchor":true},{"citing_arxiv_id":"2607.02508","citing_title":"From SRA to Self-Flow: Data Augmentation or Self-Supervision?","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11969","citing_title":"SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09803","citing_title":"Echo-Memory: A Controlled Study of Memory in Action World Models","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09150","citing_title":"Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25801","citing_title":"PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolution","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22344","citing_title":"Bernini: Latent Semantic Planning for Video Diffusion","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16503","citing_title":"Motif-Video 2B: Technical Report","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17248","citing_title":"Image-to-Video Diffusion: From Foundations to Open Frontiers","ref_index":170,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20540","citing_title":"Advancing Open-source World Models","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11424","citing_title":"VidSplat: Gaussian Splatting Reconstruction with Geometry-Guided Video Diffusion Priors","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00062","citing_title":"World Simulation with Video Foundation Models for Physical AI","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27975","citing_title":"TransVLM: A Vision-Language Framework and Benchmark for Detecting Any Shot Transitions","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22699","citing_title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11804","citing_title":"OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13030","citing_title":"Generative Refinement Networks for Visual Synthesis","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16503","citing_title":"Motif-Video 2B: Technical Report","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10103","citing_title":"Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09057","citing_title":"Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07966","citing_title":"Lighting-grounded Video Generation with Renderer-based Agent Reasoning","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GLSPWZHVLPDK7O4ESJDCPB32HB","json":"https://pith.science/pith/GLSPWZHVLPDK7O4ESJDCPB32HB.json","graph_json":"https://pith.science/api/pith-number/GLSPWZHVLPDK7O4ESJDCPB32HB/graph.json","events_json":"https://pith.science/api/pith-number/GLSPWZHVLPDK7O4ESJDCPB32HB/events.json","paper":"https://pith.science/paper/GLSPWZHV"},"agent_actions":{"view_html":"https://pith.science/pith/GLSPWZHVLPDK7O4ESJDCPB32HB","download_json":"https://pith.science/pith/GLSPWZHVLPDK7O4ESJDCPB32HB.json","view_paper":"https://pith.science/paper/GLSPWZHV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.15761&json=true","fetch_graph":"https://pith.science/api/pith-number/GLSPWZHVLPDK7O4ESJDCPB32HB/graph.json","fetch_events":"https://pith.science/api/pith-number/GLSPWZHVLPDK7O4ESJDCPB32HB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GLSPWZHVLPDK7O4ESJDCPB32HB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GLSPWZHVLPDK7O4ESJDCPB32HB/action/storage_attestation","attest_author":"https://pith.science/pith/GLSPWZHVLPDK7O4ESJDCPB32HB/action/author_attestation","sign_citation":"https://pith.science/pith/GLSPWZHVLPDK7O4ESJDCPB32HB/action/citation_signature","submit_replication":"https://pith.science/pith/GLSPWZHVLPDK7O4ESJDCPB32HB/action/replication_record"}},"created_at":"2026-07-05T11:59:20.522359+00:00","updated_at":"2026-07-05T11:59:20.522359+00:00"}