{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RCW5BV4F6MUQHJR77TPDAOWUJA","short_pith_number":"pith:RCW5BV4F","schema_version":"1.0","canonical_sha256":"88add0d785f32903a63ffcde303ad44804eec876bd4045beb9228c8e54da8971","source":{"kind":"arxiv","id":"2505.10584","version":1},"attestation_state":"computed","paper":{"title":"Aquarius: A Family of Industry-Level Video Generation Models for Marketing Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Liu, Cheng Chen, Huafeng Shi, Jianzhong Liang, Rongchang Xie, Xian Wu","submitted_at":"2025-05-14T13:39:53Z","abstract_excerpt":"This report introduces Aquarius, a family of industry-level video generation models for marketing scenarios designed for thousands-xPU clusters and models with hundreds of billions of parameters. Leveraging efficient engineering architecture and algorithmic innovation, Aquarius demonstrates exceptional performance in high-fidelity, multi-aspect-ratio, and long-duration video synthesis. By disclosing the framework's design details, we aim to demystify industrial-scale video generation systems and catalyze advancements in the generative video community. The Aquarius framework consists of five co"},"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":"2505.10584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-14T13:39:53Z","cross_cats_sorted":[],"title_canon_sha256":"5bcdc759e683107f1f602d7bbd01184d4ac477f0112463454824d82fc0517bfb","abstract_canon_sha256":"d3e6b0957dabca4a5d0b8faab4c7f148a8de5aff315fd29284fb05adfe61a30b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:01.916282Z","signature_b64":"VNROCjcnhNXECFybXmyoNHXSijHI7U56SD/sTwCJq/iKHXPVq+5hQEHkPMH4PPmsn/d1zV6TM6oFh/KFaTe3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88add0d785f32903a63ffcde303ad44804eec876bd4045beb9228c8e54da8971","last_reissued_at":"2026-07-05T11:04:01.915833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:01.915833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aquarius: A Family of Industry-Level Video Generation Models for Marketing Scenarios","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Liu, Cheng Chen, Huafeng Shi, Jianzhong Liang, Rongchang Xie, Xian Wu","submitted_at":"2025-05-14T13:39:53Z","abstract_excerpt":"This report introduces Aquarius, a family of industry-level video generation models for marketing scenarios designed for thousands-xPU clusters and models with hundreds of billions of parameters. Leveraging efficient engineering architecture and algorithmic innovation, Aquarius demonstrates exceptional performance in high-fidelity, multi-aspect-ratio, and long-duration video synthesis. By disclosing the framework's design details, we aim to demystify industrial-scale video generation systems and catalyze advancements in the generative video community. The Aquarius framework consists of five co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10584","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/2505.10584/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":"2505.10584","created_at":"2026-07-05T11:04:01.915891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.10584v1","created_at":"2026-07-05T11:04:01.915891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10584","created_at":"2026-07-05T11:04:01.915891+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCW5BV4F6MUQ","created_at":"2026-07-05T11:04:01.915891+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCW5BV4F6MUQHJR7","created_at":"2026-07-05T11:04:01.915891+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCW5BV4F","created_at":"2026-07-05T11:04:01.915891+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02641","citing_title":"Mamoda2.5: Enhancing Unified Multimodal Model with DiT-MoE","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCW5BV4F6MUQHJR77TPDAOWUJA","json":"https://pith.science/pith/RCW5BV4F6MUQHJR77TPDAOWUJA.json","graph_json":"https://pith.science/api/pith-number/RCW5BV4F6MUQHJR77TPDAOWUJA/graph.json","events_json":"https://pith.science/api/pith-number/RCW5BV4F6MUQHJR77TPDAOWUJA/events.json","paper":"https://pith.science/paper/RCW5BV4F"},"agent_actions":{"view_html":"https://pith.science/pith/RCW5BV4F6MUQHJR77TPDAOWUJA","download_json":"https://pith.science/pith/RCW5BV4F6MUQHJR77TPDAOWUJA.json","view_paper":"https://pith.science/paper/RCW5BV4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.10584&json=true","fetch_graph":"https://pith.science/api/pith-number/RCW5BV4F6MUQHJR77TPDAOWUJA/graph.json","fetch_events":"https://pith.science/api/pith-number/RCW5BV4F6MUQHJR77TPDAOWUJA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCW5BV4F6MUQHJR77TPDAOWUJA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCW5BV4F6MUQHJR77TPDAOWUJA/action/storage_attestation","attest_author":"https://pith.science/pith/RCW5BV4F6MUQHJR77TPDAOWUJA/action/author_attestation","sign_citation":"https://pith.science/pith/RCW5BV4F6MUQHJR77TPDAOWUJA/action/citation_signature","submit_replication":"https://pith.science/pith/RCW5BV4F6MUQHJR77TPDAOWUJA/action/replication_record"}},"created_at":"2026-07-05T11:04:01.915891+00:00","updated_at":"2026-07-05T11:04:01.915891+00:00"}