{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VAD4KTHQY4UJYP6Y3V5YX6XFRP","short_pith_number":"pith:VAD4KTHQ","schema_version":"1.0","canonical_sha256":"a807c54cf0c7289c3fd8dd7b8bfae58bc3b15ff1286e090130fa0fbeecede019","source":{"kind":"arxiv","id":"2403.13248","version":3},"attestation_state":"computed","paper":{"title":"Mora: Enabling Generalist Video Generation via A Multi-Agent Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Lin, Chi Wang, Haolong Jia, Lichao Sun, Lifang He, Li Yuan, Ruoxi Chen, Weixiang Sun, Yanfang Ye, Yihan Cao, Yixin Liu, Zhaoxu Li, Zhengqing Yuan","submitted_at":"2024-03-20T02:19:21Z","abstract_excerpt":"Text-to-video generation has made significant strides, but replicating the capabilities of advanced systems like OpenAI Sora remains challenging due to their closed-source nature. Existing open-source methods struggle to achieve comparable performance, often hindered by ineffective agent collaboration and inadequate training data quality. In this paper, we introduce Mora, a novel multi-agent framework that leverages existing open-source modules to replicate Sora functionalities. We address these fundamental limitations by proposing three key techniques: (1) multi-agent fine-tuning with a self-"},"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":"2403.13248","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-20T02:19:21Z","cross_cats_sorted":[],"title_canon_sha256":"965adabc14396bc9a23a22f2abe4829a48ccccfaf2021900332d49e6682cfff7","abstract_canon_sha256":"e1f5b7714a8d975dd430b5323716ed8960de7d5543f64c769a781c9d3f472f16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:30.776047Z","signature_b64":"Evh9ikOJZqzbxnKt7keGXq/NJD6D0PgCJ7nuIW8LdGKOUPlyox8QUWtMSaRy+IIlqqmwwnSE2rPPCrqRAH2OAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a807c54cf0c7289c3fd8dd7b8bfae58bc3b15ff1286e090130fa0fbeecede019","last_reissued_at":"2026-07-05T09:15:30.774466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:30.774466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mora: Enabling Generalist Video Generation via A Multi-Agent Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Lin, Chi Wang, Haolong Jia, Lichao Sun, Lifang He, Li Yuan, Ruoxi Chen, Weixiang Sun, Yanfang Ye, Yihan Cao, Yixin Liu, Zhaoxu Li, Zhengqing Yuan","submitted_at":"2024-03-20T02:19:21Z","abstract_excerpt":"Text-to-video generation has made significant strides, but replicating the capabilities of advanced systems like OpenAI Sora remains challenging due to their closed-source nature. Existing open-source methods struggle to achieve comparable performance, often hindered by ineffective agent collaboration and inadequate training data quality. In this paper, we introduce Mora, a novel multi-agent framework that leverages existing open-source modules to replicate Sora functionalities. We address these fundamental limitations by proposing three key techniques: (1) multi-agent fine-tuning with a self-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13248","kind":"arxiv","version":3},"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/2403.13248/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":"2403.13248","created_at":"2026-07-05T09:15:30.775516+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13248v3","created_at":"2026-07-05T09:15:30.775516+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13248","created_at":"2026-07-05T09:15:30.775516+00:00"},{"alias_kind":"pith_short_12","alias_value":"VAD4KTHQY4UJ","created_at":"2026-07-05T09:15:30.775516+00:00"},{"alias_kind":"pith_short_16","alias_value":"VAD4KTHQY4UJYP6Y","created_at":"2026-07-05T09:15:30.775516+00:00"},{"alias_kind":"pith_short_8","alias_value":"VAD4KTHQ","created_at":"2026-07-05T09:15:30.775516+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24649","citing_title":"Agentic Collaborative Cognition for Zero-Shot 3D Understanding","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24649","citing_title":"Agentic Collaborative Cognition for Zero-Shot 3D Understanding","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16716","citing_title":"When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00101","citing_title":"CoCoVideo: The High-Quality Commercial-Model-Based Contrastive Benchmark for AI-Generated Video Detection","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18748","citing_title":"Aurora: Unified Video Editing with a Tool-Using Agent","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16716","citing_title":"When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2602.23452","citing_title":"CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09442","citing_title":"SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05895","citing_title":"Detecting AI-Generated Videos with Spiking Neural Networks","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04875","citing_title":"DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VAD4KTHQY4UJYP6Y3V5YX6XFRP","json":"https://pith.science/pith/VAD4KTHQY4UJYP6Y3V5YX6XFRP.json","graph_json":"https://pith.science/api/pith-number/VAD4KTHQY4UJYP6Y3V5YX6XFRP/graph.json","events_json":"https://pith.science/api/pith-number/VAD4KTHQY4UJYP6Y3V5YX6XFRP/events.json","paper":"https://pith.science/paper/VAD4KTHQ"},"agent_actions":{"view_html":"https://pith.science/pith/VAD4KTHQY4UJYP6Y3V5YX6XFRP","download_json":"https://pith.science/pith/VAD4KTHQY4UJYP6Y3V5YX6XFRP.json","view_paper":"https://pith.science/paper/VAD4KTHQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13248&json=true","fetch_graph":"https://pith.science/api/pith-number/VAD4KTHQY4UJYP6Y3V5YX6XFRP/graph.json","fetch_events":"https://pith.science/api/pith-number/VAD4KTHQY4UJYP6Y3V5YX6XFRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VAD4KTHQY4UJYP6Y3V5YX6XFRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VAD4KTHQY4UJYP6Y3V5YX6XFRP/action/storage_attestation","attest_author":"https://pith.science/pith/VAD4KTHQY4UJYP6Y3V5YX6XFRP/action/author_attestation","sign_citation":"https://pith.science/pith/VAD4KTHQY4UJYP6Y3V5YX6XFRP/action/citation_signature","submit_replication":"https://pith.science/pith/VAD4KTHQY4UJYP6Y3V5YX6XFRP/action/replication_record"}},"created_at":"2026-07-05T09:15:30.775516+00:00","updated_at":"2026-07-05T09:15:30.775516+00:00"}