{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PJODTOYPVLU65CRLCKC47FU2RG","short_pith_number":"pith:PJODTOYP","schema_version":"1.0","canonical_sha256":"7a5c39bb0faae9ee8a2b1285cf969a899417e02db306c6be8c3b3be1663b4d7a","source":{"kind":"arxiv","id":"2405.10674","version":1},"attestation_state":"computed","paper":{"title":"From Sora What We Can See: A Survey of Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Wei, Haoran Duan, Jiahao Sun, Rajiv Ranjan, Rui Sun, Shuoying Zhang, Tejal Shah, Wenqi Li, Yumin Zhang","submitted_at":"2024-05-17T10:09:09Z","abstract_excerpt":"With impressive achievements made, artificial intelligence is on the path forward to artificial general intelligence. Sora, developed by OpenAI, which is capable of minute-level world-simulative abilities can be considered as a milestone on this developmental path. However, despite its notable successes, Sora still encounters various obstacles that need to be resolved. In this survey, we embark from the perspective of disassembling Sora in text-to-video generation, and conducting a comprehensive review of literature, trying to answer the question, \\textit{From Sora What We Can See}. Specifical"},"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":"2405.10674","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-17T10:09:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"85ade3203acb63eb55ca865d2ba40e05c8abaf3307952493e136f1264d85433e","abstract_canon_sha256":"c5aa28046ada418ce0edfc2457759054a43936f76ac53b3c2d1a49b23e3c754a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:15.345857Z","signature_b64":"0IUZVPWP19XnzbsXXO+ca8UlZfPvdkaZSEmypw8rDbz0cUIw69tM+JtmErMyucCSgiwgBqDgeCiX9DJoEGO8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a5c39bb0faae9ee8a2b1285cf969a899417e02db306c6be8c3b3be1663b4d7a","last_reissued_at":"2026-07-05T08:20:15.345328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:15.345328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Sora What We Can See: A Survey of Text-to-Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Wei, Haoran Duan, Jiahao Sun, Rajiv Ranjan, Rui Sun, Shuoying Zhang, Tejal Shah, Wenqi Li, Yumin Zhang","submitted_at":"2024-05-17T10:09:09Z","abstract_excerpt":"With impressive achievements made, artificial intelligence is on the path forward to artificial general intelligence. Sora, developed by OpenAI, which is capable of minute-level world-simulative abilities can be considered as a milestone on this developmental path. However, despite its notable successes, Sora still encounters various obstacles that need to be resolved. In this survey, we embark from the perspective of disassembling Sora in text-to-video generation, and conducting a comprehensive review of literature, trying to answer the question, \\textit{From Sora What We Can See}. Specifical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10674","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/2405.10674/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":"2405.10674","created_at":"2026-07-05T08:20:15.345392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10674v1","created_at":"2026-07-05T08:20:15.345392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10674","created_at":"2026-07-05T08:20:15.345392+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJODTOYPVLU6","created_at":"2026-07-05T08:20:15.345392+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJODTOYPVLU65CRL","created_at":"2026-07-05T08:20:15.345392+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJODTOYP","created_at":"2026-07-05T08:20:15.345392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16716","citing_title":"MAVEN A Multi-Agent Framework for Multicultural Text-to-Video Generation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16716","citing_title":"MAVEN A Multi-Agent Framework for Multicultural Text-to-Video Generation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PJODTOYPVLU65CRLCKC47FU2RG","json":"https://pith.science/pith/PJODTOYPVLU65CRLCKC47FU2RG.json","graph_json":"https://pith.science/api/pith-number/PJODTOYPVLU65CRLCKC47FU2RG/graph.json","events_json":"https://pith.science/api/pith-number/PJODTOYPVLU65CRLCKC47FU2RG/events.json","paper":"https://pith.science/paper/PJODTOYP"},"agent_actions":{"view_html":"https://pith.science/pith/PJODTOYPVLU65CRLCKC47FU2RG","download_json":"https://pith.science/pith/PJODTOYPVLU65CRLCKC47FU2RG.json","view_paper":"https://pith.science/paper/PJODTOYP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10674&json=true","fetch_graph":"https://pith.science/api/pith-number/PJODTOYPVLU65CRLCKC47FU2RG/graph.json","fetch_events":"https://pith.science/api/pith-number/PJODTOYPVLU65CRLCKC47FU2RG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJODTOYPVLU65CRLCKC47FU2RG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJODTOYPVLU65CRLCKC47FU2RG/action/storage_attestation","attest_author":"https://pith.science/pith/PJODTOYPVLU65CRLCKC47FU2RG/action/author_attestation","sign_citation":"https://pith.science/pith/PJODTOYPVLU65CRLCKC47FU2RG/action/citation_signature","submit_replication":"https://pith.science/pith/PJODTOYPVLU65CRLCKC47FU2RG/action/replication_record"}},"created_at":"2026-07-05T08:20:15.345392+00:00","updated_at":"2026-07-05T08:20:15.345392+00:00"}