{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3RE22VVZ65T3YEND3HOFUD2YDW","short_pith_number":"pith:3RE22VVZ","schema_version":"1.0","canonical_sha256":"dc49ad56b9f767bc11a3d9dc5a0f581daafe7363a61844802bde50017bacbc6f","source":{"kind":"arxiv","id":"2412.10783","version":3},"attestation_state":"computed","paper":{"title":"Video Diffusion Transformers are In-Context Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqian Yu, Debang Li, Di Qiu, Mingyuan Fan, Zhengcong Fei","submitted_at":"2024-12-14T10:39:55Z","abstract_excerpt":"This paper investigates a solution for enabling in-context capabilities of video diffusion transformers, with minimal tuning required for activation. Specifically, we propose a simple pipeline to leverage in-context generation: ($\\textbf{i}$) concatenate videos along spacial or time dimension, ($\\textbf{ii}$) jointly caption multi-scene video clips from one source, and ($\\textbf{iii}$) apply task-specific fine-tuning using carefully curated small datasets. Through a series of diverse controllable tasks, we demonstrate qualitatively that existing advanced text-to-video models can effectively pe"},"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":"2412.10783","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T10:39:55Z","cross_cats_sorted":[],"title_canon_sha256":"36d9c3264e3edecc4a08b91a8949cf0dda8d3d8da6aac16e88fed4f2ba150512","abstract_canon_sha256":"f68cf234b87b7453b4b52f155b4318de988df431a5802307c6ab1edec2567e29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:40.311213Z","signature_b64":"9haH3aeFdU43irxzUEj/C+aNUiMQkn/BmrnDlUbyJ70rq25NSFzNwGh3Y8J2esfUs8LQk7U+WZbkTobt+CFnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc49ad56b9f767bc11a3d9dc5a0f581daafe7363a61844802bde50017bacbc6f","last_reissued_at":"2026-07-05T10:37:40.310648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:40.310648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Diffusion Transformers are In-Context Learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqian Yu, Debang Li, Di Qiu, Mingyuan Fan, Zhengcong Fei","submitted_at":"2024-12-14T10:39:55Z","abstract_excerpt":"This paper investigates a solution for enabling in-context capabilities of video diffusion transformers, with minimal tuning required for activation. Specifically, we propose a simple pipeline to leverage in-context generation: ($\\textbf{i}$) concatenate videos along spacial or time dimension, ($\\textbf{ii}$) jointly caption multi-scene video clips from one source, and ($\\textbf{iii}$) apply task-specific fine-tuning using carefully curated small datasets. Through a series of diverse controllable tasks, we demonstrate qualitatively that existing advanced text-to-video models can effectively pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10783","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/2412.10783/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":"2412.10783","created_at":"2026-07-05T10:37:40.310712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10783v3","created_at":"2026-07-05T10:37:40.310712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10783","created_at":"2026-07-05T10:37:40.310712+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RE22VVZ65T3","created_at":"2026-07-05T10:37:40.310712+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RE22VVZ65T3YEND","created_at":"2026-07-05T10:37:40.310712+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RE22VVZ","created_at":"2026-07-05T10:37:40.310712+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3RE22VVZ65T3YEND3HOFUD2YDW","json":"https://pith.science/pith/3RE22VVZ65T3YEND3HOFUD2YDW.json","graph_json":"https://pith.science/api/pith-number/3RE22VVZ65T3YEND3HOFUD2YDW/graph.json","events_json":"https://pith.science/api/pith-number/3RE22VVZ65T3YEND3HOFUD2YDW/events.json","paper":"https://pith.science/paper/3RE22VVZ"},"agent_actions":{"view_html":"https://pith.science/pith/3RE22VVZ65T3YEND3HOFUD2YDW","download_json":"https://pith.science/pith/3RE22VVZ65T3YEND3HOFUD2YDW.json","view_paper":"https://pith.science/paper/3RE22VVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10783&json=true","fetch_graph":"https://pith.science/api/pith-number/3RE22VVZ65T3YEND3HOFUD2YDW/graph.json","fetch_events":"https://pith.science/api/pith-number/3RE22VVZ65T3YEND3HOFUD2YDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RE22VVZ65T3YEND3HOFUD2YDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RE22VVZ65T3YEND3HOFUD2YDW/action/storage_attestation","attest_author":"https://pith.science/pith/3RE22VVZ65T3YEND3HOFUD2YDW/action/author_attestation","sign_citation":"https://pith.science/pith/3RE22VVZ65T3YEND3HOFUD2YDW/action/citation_signature","submit_replication":"https://pith.science/pith/3RE22VVZ65T3YEND3HOFUD2YDW/action/replication_record"}},"created_at":"2026-07-05T10:37:40.310712+00:00","updated_at":"2026-07-05T10:37:40.310712+00:00"}