{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:U6FFAMIGGPHPZ2X42Y2D7PQAHB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dbeca8d4bf36111e97ccda7ede8892d3a23707fa10cf80e19218ed944c9b79c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T15:53:20Z","title_canon_sha256":"8f23c2f0255540dce337b30e8715dbe3a6b4d339bc95727f19b9188db6dd40d9"},"schema_version":"1.0","source":{"id":"2407.21705","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.21705","created_at":"2026-07-05T10:30:55Z"},{"alias_kind":"arxiv_version","alias_value":"2407.21705v4","created_at":"2026-07-05T10:30:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.21705","created_at":"2026-07-05T10:30:55Z"},{"alias_kind":"pith_short_12","alias_value":"U6FFAMIGGPHP","created_at":"2026-07-05T10:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"U6FFAMIGGPHPZ2X4","created_at":"2026-07-05T10:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"U6FFAMIG","created_at":"2026-07-05T10:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:0c45a0b716757cbec594ee8710ac6d73b894af82d119144ec9e0d73bcdeee0be","target":"graph","created_at":"2026-07-05T10:30:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.21705/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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,","authors_text":"Bingxue Qiu, Junchao Liao, Long Qin, Menghao Li, Siyu Zhu, Weizhi Wang, Zhenghao Zhang, Zuozhuo Dai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T15:53:20Z","title":"Tora: Trajectory-oriented Diffusion Transformer for Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.21705","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8b423edab0879eb09825d69c02fc8bb8c09ea87fdde45554b42147d0cdf1e483","target":"record","created_at":"2026-07-05T10:30:55Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dbeca8d4bf36111e97ccda7ede8892d3a23707fa10cf80e19218ed944c9b79c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-31T15:53:20Z","title_canon_sha256":"8f23c2f0255540dce337b30e8715dbe3a6b4d339bc95727f19b9188db6dd40d9"},"schema_version":"1.0","source":{"id":"2407.21705","kind":"arxiv","version":4}},"canonical_sha256":"a78a50310633cefceafcd6343fbe003847cf3b28b6aae3bd8bb2f212debdd29a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a78a50310633cefceafcd6343fbe003847cf3b28b6aae3bd8bb2f212debdd29a","first_computed_at":"2026-07-05T10:30:55.596786Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:55.596786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rqUwt9UXvCzeFHiBkqcAVfLBDq6YIlK+GZjdpiYP4/dEDilsClReByjrsZbmFdG83Z53HnzTd5Lx1dS1HxKmCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:55.598282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.21705","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b423edab0879eb09825d69c02fc8bb8c09ea87fdde45554b42147d0cdf1e483","sha256:0c45a0b716757cbec594ee8710ac6d73b894af82d119144ec9e0d73bcdeee0be"],"state_sha256":"c084bd6c24ce1085f890042586996983c740b65294b5de1e9dc3639483aa0e20"}