{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:U6FFAMIGGPHPZ2X42Y2D7PQAHB","short_pith_number":"pith:U6FFAMIG","schema_version":"1.0","canonical_sha256":"a78a50310633cefceafcd6343fbe003847cf3b28b6aae3bd8bb2f212debdd29a","source":{"kind":"arxiv","id":"2407.21705","version":4},"attestation_state":"computed","paper":{"title":"Tora: Trajectory-oriented Diffusion Transformer for Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingxue Qiu, Junchao Liao, Long Qin, Menghao Li, Siyu Zhu, Weizhi Wang, Zhenghao Zhang, Zuozhuo Dai","submitted_at":"2024-07-31T15:53:20Z","abstract_excerpt":"Recent advancements in Diffusion Transformer (DiT) have demonstrated remarkable proficiency in producing high-quality video content. Nonetheless, the potential of transformer-based diffusion models for effectively generating videos with controllable motion remains an area of limited exploration. This paper introduces Tora, the first trajectory-oriented DiT framework that concurrently integrates textual, visual, and trajectory conditions, thereby enabling scalable video generation with effective motion guidance. Specifically, Tora consists of a Trajectory Extractor (TE), a Spatial-Temporal DiT,"},"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":"2407.21705","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T15:53:20Z","cross_cats_sorted":[],"title_canon_sha256":"8f23c2f0255540dce337b30e8715dbe3a6b4d339bc95727f19b9188db6dd40d9","abstract_canon_sha256":"dbeca8d4bf36111e97ccda7ede8892d3a23707fa10cf80e19218ed944c9b79c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:55.598282Z","signature_b64":"rqUwt9UXvCzeFHiBkqcAVfLBDq6YIlK+GZjdpiYP4/dEDilsClReByjrsZbmFdG83Z53HnzTd5Lx1dS1HxKmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a78a50310633cefceafcd6343fbe003847cf3b28b6aae3bd8bb2f212debdd29a","last_reissued_at":"2026-07-05T10:30:55.596786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:55.596786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tora: Trajectory-oriented Diffusion Transformer for Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingxue Qiu, Junchao Liao, Long Qin, Menghao Li, Siyu Zhu, Weizhi Wang, Zhenghao Zhang, Zuozhuo Dai","submitted_at":"2024-07-31T15:53:20Z","abstract_excerpt":"Recent advancements in Diffusion Transformer (DiT) have demonstrated remarkable proficiency in producing high-quality video content. Nonetheless, the potential of transformer-based diffusion models for effectively generating videos with controllable motion remains an area of limited exploration. This paper introduces Tora, the first trajectory-oriented DiT framework that concurrently integrates textual, visual, and trajectory conditions, thereby enabling scalable video generation with effective motion guidance. Specifically, Tora consists of a Trajectory Extractor (TE), a Spatial-Temporal DiT,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21705","kind":"arxiv","version":4},"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/2407.21705/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":"2407.21705","created_at":"2026-07-05T10:30:55.597447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.21705v4","created_at":"2026-07-05T10:30:55.597447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21705","created_at":"2026-07-05T10:30:55.597447+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6FFAMIGGPHP","created_at":"2026-07-05T10:30:55.597447+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6FFAMIGGPHPZ2X4","created_at":"2026-07-05T10:30:55.597447+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6FFAMIG","created_at":"2026-07-05T10:30:55.597447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02075","citing_title":"HandsOnWorld: Unconstrained Egocentric Video Generation with Camera-Disentangled Hand Control","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02000","citing_title":"Towards 3D-Aware Video Diffusion Models: Render-Free Human Motion Control with Mesh Tokenization","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U6FFAMIGGPHPZ2X42Y2D7PQAHB","json":"https://pith.science/pith/U6FFAMIGGPHPZ2X42Y2D7PQAHB.json","graph_json":"https://pith.science/api/pith-number/U6FFAMIGGPHPZ2X42Y2D7PQAHB/graph.json","events_json":"https://pith.science/api/pith-number/U6FFAMIGGPHPZ2X42Y2D7PQAHB/events.json","paper":"https://pith.science/paper/U6FFAMIG"},"agent_actions":{"view_html":"https://pith.science/pith/U6FFAMIGGPHPZ2X42Y2D7PQAHB","download_json":"https://pith.science/pith/U6FFAMIGGPHPZ2X42Y2D7PQAHB.json","view_paper":"https://pith.science/paper/U6FFAMIG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.21705&json=true","fetch_graph":"https://pith.science/api/pith-number/U6FFAMIGGPHPZ2X42Y2D7PQAHB/graph.json","fetch_events":"https://pith.science/api/pith-number/U6FFAMIGGPHPZ2X42Y2D7PQAHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6FFAMIGGPHPZ2X42Y2D7PQAHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6FFAMIGGPHPZ2X42Y2D7PQAHB/action/storage_attestation","attest_author":"https://pith.science/pith/U6FFAMIGGPHPZ2X42Y2D7PQAHB/action/author_attestation","sign_citation":"https://pith.science/pith/U6FFAMIGGPHPZ2X42Y2D7PQAHB/action/citation_signature","submit_replication":"https://pith.science/pith/U6FFAMIGGPHPZ2X42Y2D7PQAHB/action/replication_record"}},"created_at":"2026-07-05T10:30:55.597447+00:00","updated_at":"2026-07-05T10:30:55.597447+00:00"}