{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3RE22VVZ65T3YEND3HOFUD2YDW","short_pith_number":"pith:3RE22VVZ","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"},"canonical_sha256":"dc49ad56b9f767bc11a3d9dc5a0f581daafe7363a61844802bde50017bacbc6f","source":{"kind":"arxiv","id":"2412.10783","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10783","created_at":"2026-07-05T10:37:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10783v3","created_at":"2026-07-05T10:37:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10783","created_at":"2026-07-05T10:37:40Z"},{"alias_kind":"pith_short_12","alias_value":"3RE22VVZ65T3","created_at":"2026-07-05T10:37:40Z"},{"alias_kind":"pith_short_16","alias_value":"3RE22VVZ65T3YEND","created_at":"2026-07-05T10:37:40Z"},{"alias_kind":"pith_short_8","alias_value":"3RE22VVZ","created_at":"2026-07-05T10:37:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3RE22VVZ65T3YEND3HOFUD2YDW","target":"record","payload":{"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"},"canonical_sha256":"dc49ad56b9f767bc11a3d9dc5a0f581daafe7363a61844802bde50017bacbc6f","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"},"source_kind":"arxiv","source_id":"2412.10783","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:37:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7M1KE0KxDGSRDsbsJxYgTsSaQ8f/aRleIdECcdcZjzRKBfDe957RjtPmi8hfx7jikYyT0GpH431uqNs/+pYDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:33:56.152721Z"},"content_sha256":"052b6b2a67fb2baf7ed4ceaa910b4f575790ae8163c0fb0be6490bf62ec263b7","schema_version":"1.0","event_id":"sha256:052b6b2a67fb2baf7ed4ceaa910b4f575790ae8163c0fb0be6490bf62ec263b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3RE22VVZ65T3YEND3HOFUD2YDW","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:37:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nm6oX9x0/eQzvgjvto9o5uqPiSvq3IW72dXpFvYfYYrn3Ciz2Y1RUFdH+sWKE0SFKMqImovbAsKDAkmOyrOuBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:33:56.153249Z"},"content_sha256":"c10ac5aa18e0b3afec9c2d8a6b0ac644a37bf25a62302f4d4b9132791475bd3b","schema_version":"1.0","event_id":"sha256:c10ac5aa18e0b3afec9c2d8a6b0ac644a37bf25a62302f4d4b9132791475bd3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3RE22VVZ65T3YEND3HOFUD2YDW/bundle.json","state_url":"https://pith.science/pith/3RE22VVZ65T3YEND3HOFUD2YDW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3RE22VVZ65T3YEND3HOFUD2YDW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T09:33:56Z","links":{"resolver":"https://pith.science/pith/3RE22VVZ65T3YEND3HOFUD2YDW","bundle":"https://pith.science/pith/3RE22VVZ65T3YEND3HOFUD2YDW/bundle.json","state":"https://pith.science/pith/3RE22VVZ65T3YEND3HOFUD2YDW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3RE22VVZ65T3YEND3HOFUD2YDW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3RE22VVZ65T3YEND3HOFUD2YDW","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":"f68cf234b87b7453b4b52f155b4318de988df431a5802307c6ab1edec2567e29","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T10:39:55Z","title_canon_sha256":"36d9c3264e3edecc4a08b91a8949cf0dda8d3d8da6aac16e88fed4f2ba150512"},"schema_version":"1.0","source":{"id":"2412.10783","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10783","created_at":"2026-07-05T10:37:40Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10783v3","created_at":"2026-07-05T10:37:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10783","created_at":"2026-07-05T10:37:40Z"},{"alias_kind":"pith_short_12","alias_value":"3RE22VVZ65T3","created_at":"2026-07-05T10:37:40Z"},{"alias_kind":"pith_short_16","alias_value":"3RE22VVZ65T3YEND","created_at":"2026-07-05T10:37:40Z"},{"alias_kind":"pith_short_8","alias_value":"3RE22VVZ","created_at":"2026-07-05T10:37:40Z"}],"graph_snapshots":[{"event_id":"sha256:c10ac5aa18e0b3afec9c2d8a6b0ac644a37bf25a62302f4d4b9132791475bd3b","target":"graph","created_at":"2026-07-05T10:37:40Z","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/2412.10783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Changqian Yu, Debang Li, Di Qiu, Mingyuan Fan, Zhengcong Fei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T10:39:55Z","title":"Video Diffusion Transformers are In-Context Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10783","kind":"arxiv","version":3},"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":"sha256:052b6b2a67fb2baf7ed4ceaa910b4f575790ae8163c0fb0be6490bf62ec263b7","target":"record","created_at":"2026-07-05T10:37:40Z","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":"f68cf234b87b7453b4b52f155b4318de988df431a5802307c6ab1edec2567e29","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-14T10:39:55Z","title_canon_sha256":"36d9c3264e3edecc4a08b91a8949cf0dda8d3d8da6aac16e88fed4f2ba150512"},"schema_version":"1.0","source":{"id":"2412.10783","kind":"arxiv","version":3}},"canonical_sha256":"dc49ad56b9f767bc11a3d9dc5a0f581daafe7363a61844802bde50017bacbc6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc49ad56b9f767bc11a3d9dc5a0f581daafe7363a61844802bde50017bacbc6f","first_computed_at":"2026-07-05T10:37:40.310648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:40.310648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9haH3aeFdU43irxzUEj/C+aNUiMQkn/BmrnDlUbyJ70rq25NSFzNwGh3Y8J2esfUs8LQk7U+WZbkTobt+CFnDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:40.311213Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10783","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:052b6b2a67fb2baf7ed4ceaa910b4f575790ae8163c0fb0be6490bf62ec263b7","sha256:c10ac5aa18e0b3afec9c2d8a6b0ac644a37bf25a62302f4d4b9132791475bd3b"],"state_sha256":"4820ed9a5713cc5a2cf284d5d80876427bc7a5d8c7d102527d6d0ddf5e935e50"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JUrQ9YJ3xz6YMtwqR2LJ7HJSnwf77Us5wJSTxiTSoYVqjJgwuYwA2BXC9kysBTWMlroKYjRidzBHNbAoi2UAAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:33:56.157720Z","bundle_sha256":"8d2f8b211b46a34d7d86c1da13a72d1480f2577bad6fd57221f3ccb266bca058"}}