{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V4QXIXJOXDCL4ESWRJA5SJC3LT","short_pith_number":"pith:V4QXIXJO","schema_version":"1.0","canonical_sha256":"af21745d2eb8c4be12568a41d9245b5cc594d423abff93b5e6fae6cc75a7b74f","source":{"kind":"arxiv","id":"2401.00896","version":2},"attestation_state":"computed","paper":{"title":"TrailBlazer: Trajectory Control for Diffusion-Based Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"J.P. Lewis, Wan-Duo Kurt Ma, W. Bastiaan Kleijn","submitted_at":"2023-12-31T10:51:52Z","abstract_excerpt":"Within recent approaches to text-to-video (T2V) generation, achieving controllability in the synthesized video is often a challenge. Typically, this issue is addressed by providing low-level per-frame guidance in the form of edge maps, depth maps, or an existing video to be altered. However, the process of obtaining such guidance can be labor-intensive. This paper focuses on enhancing controllability in video synthesis by employing straightforward bounding boxes to guide the subject in various ways, all without the need for neural network training, finetuning, optimization at inference time, o"},"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":"2401.00896","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-31T10:51:52Z","cross_cats_sorted":[],"title_canon_sha256":"fcc96202775280ae2eede9f76871b833a17e12a0eb383bfade05041efc4ae9a7","abstract_canon_sha256":"ef12f6319dcfb8cd01a739186856915eb6ae447907fab4d8bbd8cc669c9b6b01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:55.115428Z","signature_b64":"O5Ava34x7PzUdhHJoLGMArLyWkroWf/56hJLTuVAYWjPQ96cEcSGyPfs86Ew6DJDWR54H9DJo15ewV+Rzx1oDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af21745d2eb8c4be12568a41d9245b5cc594d423abff93b5e6fae6cc75a7b74f","last_reissued_at":"2026-07-05T08:05:55.114948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:55.114948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TrailBlazer: Trajectory Control for Diffusion-Based Video Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"J.P. Lewis, Wan-Duo Kurt Ma, W. Bastiaan Kleijn","submitted_at":"2023-12-31T10:51:52Z","abstract_excerpt":"Within recent approaches to text-to-video (T2V) generation, achieving controllability in the synthesized video is often a challenge. Typically, this issue is addressed by providing low-level per-frame guidance in the form of edge maps, depth maps, or an existing video to be altered. However, the process of obtaining such guidance can be labor-intensive. This paper focuses on enhancing controllability in video synthesis by employing straightforward bounding boxes to guide the subject in various ways, all without the need for neural network training, finetuning, optimization at inference time, o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00896","kind":"arxiv","version":2},"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/2401.00896/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":"2401.00896","created_at":"2026-07-05T08:05:55.115006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.00896v2","created_at":"2026-07-05T08:05:55.115006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00896","created_at":"2026-07-05T08:05:55.115006+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4QXIXJOXDCL","created_at":"2026-07-05T08:05:55.115006+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4QXIXJOXDCL4ESW","created_at":"2026-07-05T08:05:55.115006+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4QXIXJO","created_at":"2026-07-05T08:05:55.115006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31529","citing_title":"SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25449","citing_title":"Pantheon360: Taming Digital Twin Generation via 3D-Aware 360{\\deg} Video Diffusion","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31529","citing_title":"SVI-Bench: A Dynamic Microworld for Strategic Video Intelligence","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07348","citing_title":"MoRight: Motion Control Done Right","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V4QXIXJOXDCL4ESWRJA5SJC3LT","json":"https://pith.science/pith/V4QXIXJOXDCL4ESWRJA5SJC3LT.json","graph_json":"https://pith.science/api/pith-number/V4QXIXJOXDCL4ESWRJA5SJC3LT/graph.json","events_json":"https://pith.science/api/pith-number/V4QXIXJOXDCL4ESWRJA5SJC3LT/events.json","paper":"https://pith.science/paper/V4QXIXJO"},"agent_actions":{"view_html":"https://pith.science/pith/V4QXIXJOXDCL4ESWRJA5SJC3LT","download_json":"https://pith.science/pith/V4QXIXJOXDCL4ESWRJA5SJC3LT.json","view_paper":"https://pith.science/paper/V4QXIXJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.00896&json=true","fetch_graph":"https://pith.science/api/pith-number/V4QXIXJOXDCL4ESWRJA5SJC3LT/graph.json","fetch_events":"https://pith.science/api/pith-number/V4QXIXJOXDCL4ESWRJA5SJC3LT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4QXIXJOXDCL4ESWRJA5SJC3LT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4QXIXJOXDCL4ESWRJA5SJC3LT/action/storage_attestation","attest_author":"https://pith.science/pith/V4QXIXJOXDCL4ESWRJA5SJC3LT/action/author_attestation","sign_citation":"https://pith.science/pith/V4QXIXJOXDCL4ESWRJA5SJC3LT/action/citation_signature","submit_replication":"https://pith.science/pith/V4QXIXJOXDCL4ESWRJA5SJC3LT/action/replication_record"}},"created_at":"2026-07-05T08:05:55.115006+00:00","updated_at":"2026-07-05T08:05:55.115006+00:00"}