{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RMT4HSRNJNUJ2HPIDCIAY7G3LH","short_pith_number":"pith:RMT4HSRN","canonical_record":{"source":{"id":"2209.14792","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-29T13:59:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"08eba9c4a0fc0b51bf8cecc8724418772c8143eb298c2f0dbc5fb27811b88099","abstract_canon_sha256":"aba523ef24a47557c4cc45d2005e48691e4fb7259af54dcf216ca2581522599f"},"schema_version":"1.0"},"canonical_sha256":"8b27c3ca2d4b689d1de818900c7cdb59cd80b5b83a6ad45b0ed02c8147182790","source":{"kind":"arxiv","id":"2209.14792","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14792","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14792v1","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14792","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"pith_short_12","alias_value":"RMT4HSRNJNUJ","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"pith_short_16","alias_value":"RMT4HSRNJNUJ2HPI","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"pith_short_8","alias_value":"RMT4HSRN","created_at":"2026-07-05T05:02:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RMT4HSRNJNUJ2HPIDCIAY7G3LH","target":"record","payload":{"canonical_record":{"source":{"id":"2209.14792","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-29T13:59:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"08eba9c4a0fc0b51bf8cecc8724418772c8143eb298c2f0dbc5fb27811b88099","abstract_canon_sha256":"aba523ef24a47557c4cc45d2005e48691e4fb7259af54dcf216ca2581522599f"},"schema_version":"1.0"},"canonical_sha256":"8b27c3ca2d4b689d1de818900c7cdb59cd80b5b83a6ad45b0ed02c8147182790","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:05.789566Z","signature_b64":"lCNtnvALCkzp6RbGQ1SdokXItSLVYpZxq8zcPMuZ3XVGBi8ffxUtkyYYiZDa3/PYeB05YSLMpnoqJj6ReRVEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b27c3ca2d4b689d1de818900c7cdb59cd80b5b83a6ad45b0ed02c8147182790","last_reissued_at":"2026-07-05T05:02:05.789195Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:05.789195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.14792","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:02:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yfEVEyWqbQZJHo1i5y/tUcZya8qvklADpkJo7uOU0v4riXicrAp50VhRCLR3qTCOO9O3ChHuxtbeinNmAx5UCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T02:45:58.318708Z"},"content_sha256":"799e140010203491306f292b54be82f632fe7a7e346cd2006d0cb81509d5e739","schema_version":"1.0","event_id":"sha256:799e140010203491306f292b54be82f632fe7a7e346cd2006d0cb81509d5e739"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RMT4HSRNJNUJ2HPIDCIAY7G3LH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A method turns text into videos by extending image generators with motion learned separately from unlabeled footage.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Adam Polyak, Devi Parikh, Harry Yang, Jie An, Oran Gafni, Oron Ashual, Qiyuan Hu, Sonal Gupta, Songyang Zhang, Thomas Hayes, Uriel Singer, Xi Yin, Yaniv Taigman","submitted_at":"2022-09-29T13:59:46Z","abstract_excerpt":"We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: learn what the world looks like and how it is described from paired text-image data, and learn how the world moves from unsupervised video footage. Make-A-Video has three advantages: (1) it accelerates training of the T2V model (it does not need to learn visual and multimodal representations from scratch), (2) it does not require paired text-video data, and (3) the generated videos inherit the vastness (diversity in ae"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Make-A-Video sets the new state-of-the-art in text-to-video generation, as determined by both qualitative and quantitative measures.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the proposed spatial-temporal decomposition and pipeline can transfer motion dynamics learned from unsupervised video to text-conditioned generation without introducing visible artifacts or losing text faithfulness.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Make-A-Video achieves state-of-the-art text-to-video generation by decomposing temporal U-Net and attention structures to add space-time modeling to text-to-image models, trained without any paired text-video data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A method turns text into videos by extending image generators with motion learned separately from unlabeled footage.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6246920416a3dc97bd69ce776b67afac4717b24d3e8991f1286e9eea16686c2e"},"source":{"id":"2209.14792","kind":"arxiv","version":1},"verdict":{"id":"b692e49f-8022-4dc6-8d28-ef916e606e9c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T01:08:48.153334Z","strongest_claim":"Make-A-Video sets the new state-of-the-art in text-to-video generation, as determined by both qualitative and quantitative measures.","one_line_summary":"Make-A-Video achieves state-of-the-art text-to-video generation by decomposing temporal U-Net and attention structures to add space-time modeling to text-to-image models, trained without any paired text-video data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the proposed spatial-temporal decomposition and pipeline can transfer motion dynamics learned from unsupervised video to text-conditioned generation without introducing visible artifacts or losing text faithfulness.","pith_extraction_headline":"A method turns text into videos by extending image generators with motion learned separately from unlabeled footage."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.14792/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":15,"sample":[{"doi":"","year":2005,"title":"Language Models are Few-Shot Learners","work_id":"214732c0-2edd-44a0-af9e-28184a2b8279","ref_index":2,"cited_arxiv_id":"2005.14165","is_internal_anchor":true},{"doi":"","year":null,"title":"arXiv preprint arXiv:2204.14217 , eprint =","work_id":"1768d36e-3377-4973-b3f4-698595fdb671","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Make-a-Scene","work_id":"2c99d6c4-d1c6-4714-95e0-006639b9ac5c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1109/cvprw50498.2020.00193","year":2020,"title":"Score-cam: Score-weighted visual explanations for convolutional neural net- works","work_id":"cafb0da8-3304-4402-975f-3fe00918e3fa","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2006,"title":"Denoising Diffusion Probabilistic Models","work_id":"dc023f4e-7c79-471c-b713-deeb559ba010","ref_index":6,"cited_arxiv_id":"2006.11239","is_internal_anchor":true}],"resolved_work":15,"snapshot_sha256":"afc3ac3c5164d2f43c2309612ee8c8c49567e878695321679744c868f5b96609","internal_anchors":12},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4d1ceaf666a386c984c02a6817e4891b399ef4a29719fb472265af1d22699866"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"b692e49f-8022-4dc6-8d28-ef916e606e9c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:02:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D+tfEKAP1sPu0dlcDlzxmQABQo4mxlOG/1zorGVyK2o4U9yppR8E+iAVl7bSszmGgItopCugXQKq5M96S2T0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T02:45:58.319230Z"},"content_sha256":"8d378c0c67adea9a12498ad66a2761ccb271ed55824cdd2ab29d2a06b50dae01","schema_version":"1.0","event_id":"sha256:8d378c0c67adea9a12498ad66a2761ccb271ed55824cdd2ab29d2a06b50dae01"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RMT4HSRNJNUJ2HPIDCIAY7G3LH/bundle.json","state_url":"https://pith.science/pith/RMT4HSRNJNUJ2HPIDCIAY7G3LH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RMT4HSRNJNUJ2HPIDCIAY7G3LH/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":"2026-07-19T02:45:58Z","links":{"resolver":"https://pith.science/pith/RMT4HSRNJNUJ2HPIDCIAY7G3LH","bundle":"https://pith.science/pith/RMT4HSRNJNUJ2HPIDCIAY7G3LH/bundle.json","state":"https://pith.science/pith/RMT4HSRNJNUJ2HPIDCIAY7G3LH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RMT4HSRNJNUJ2HPIDCIAY7G3LH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RMT4HSRNJNUJ2HPIDCIAY7G3LH","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":"aba523ef24a47557c4cc45d2005e48691e4fb7259af54dcf216ca2581522599f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-29T13:59:46Z","title_canon_sha256":"08eba9c4a0fc0b51bf8cecc8724418772c8143eb298c2f0dbc5fb27811b88099"},"schema_version":"1.0","source":{"id":"2209.14792","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14792","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14792v1","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14792","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"pith_short_12","alias_value":"RMT4HSRNJNUJ","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"pith_short_16","alias_value":"RMT4HSRNJNUJ2HPI","created_at":"2026-07-05T05:02:05Z"},{"alias_kind":"pith_short_8","alias_value":"RMT4HSRN","created_at":"2026-07-05T05:02:05Z"}],"graph_snapshots":[{"event_id":"sha256:8d378c0c67adea9a12498ad66a2761ccb271ed55824cdd2ab29d2a06b50dae01","target":"graph","created_at":"2026-07-05T05:02:05Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Make-A-Video sets the new state-of-the-art in text-to-video generation, as determined by both qualitative and quantitative measures."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the proposed spatial-temporal decomposition and pipeline can transfer motion dynamics learned from unsupervised video to text-conditioned generation without introducing visible artifacts or losing text faithfulness."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Make-A-Video achieves state-of-the-art text-to-video generation by decomposing temporal U-Net and attention structures to add space-time modeling to text-to-image models, trained without any paired text-video data."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A method turns text into videos by extending image generators with motion learned separately from unlabeled footage."}],"snapshot_sha256":"6246920416a3dc97bd69ce776b67afac4717b24d3e8991f1286e9eea16686c2e"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4d1ceaf666a386c984c02a6817e4891b399ef4a29719fb472265af1d22699866"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2209.14792/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: learn what the world looks like and how it is described from paired text-image data, and learn how the world moves from unsupervised video footage. Make-A-Video has three advantages: (1) it accelerates training of the T2V model (it does not need to learn visual and multimodal representations from scratch), (2) it does not require paired text-video data, and (3) the generated videos inherit the vastness (diversity in ae","authors_text":"Adam Polyak, Devi Parikh, Harry Yang, Jie An, Oran Gafni, Oron Ashual, Qiyuan Hu, Sonal Gupta, Songyang Zhang, Thomas Hayes, Uriel Singer, Xi Yin, Yaniv Taigman","cross_cats":["cs.AI","cs.LG"],"headline":"A method turns text into videos by extending image generators with motion learned separately from unlabeled footage.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-29T13:59:46Z","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data"},"references":{"count":15,"internal_anchors":12,"resolved_work":15,"sample":[{"cited_arxiv_id":"2005.14165","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Language Models are Few-Shot Learners","work_id":"214732c0-2edd-44a0-af9e-28184a2b8279","year":2005},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"arXiv preprint arXiv:2204.14217 , eprint =","work_id":"1768d36e-3377-4973-b3f4-698595fdb671","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Make-a-Scene","work_id":"2c99d6c4-d1c6-4714-95e0-006639b9ac5c","year":null},{"cited_arxiv_id":"","doi":"10.1109/cvprw50498.2020.00193","is_internal_anchor":false,"ref_index":5,"title":"Score-cam: Score-weighted visual explanations for convolutional neural net- works","work_id":"cafb0da8-3304-4402-975f-3fe00918e3fa","year":2020},{"cited_arxiv_id":"2006.11239","doi":"","is_internal_anchor":true,"ref_index":6,"title":"Denoising Diffusion Probabilistic Models","work_id":"dc023f4e-7c79-471c-b713-deeb559ba010","year":2006}],"snapshot_sha256":"afc3ac3c5164d2f43c2309612ee8c8c49567e878695321679744c868f5b96609"},"source":{"id":"2209.14792","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-11T01:08:48.153334Z","id":"b692e49f-8022-4dc6-8d28-ef916e606e9c","model_set":{"reader":"grok-4.3"},"one_line_summary":"Make-A-Video achieves state-of-the-art text-to-video generation by decomposing temporal U-Net and attention structures to add space-time modeling to text-to-image models, trained without any paired text-video data.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A method turns text into videos by extending image generators with motion learned separately from unlabeled footage.","strongest_claim":"Make-A-Video sets the new state-of-the-art in text-to-video generation, as determined by both qualitative and quantitative measures.","weakest_assumption":"That the proposed spatial-temporal decomposition and pipeline can transfer motion dynamics learned from unsupervised video to text-conditioned generation without introducing visible artifacts or losing text faithfulness."}},"verdict_id":"b692e49f-8022-4dc6-8d28-ef916e606e9c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:799e140010203491306f292b54be82f632fe7a7e346cd2006d0cb81509d5e739","target":"record","created_at":"2026-07-05T05:02:05Z","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":"aba523ef24a47557c4cc45d2005e48691e4fb7259af54dcf216ca2581522599f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-29T13:59:46Z","title_canon_sha256":"08eba9c4a0fc0b51bf8cecc8724418772c8143eb298c2f0dbc5fb27811b88099"},"schema_version":"1.0","source":{"id":"2209.14792","kind":"arxiv","version":1}},"canonical_sha256":"8b27c3ca2d4b689d1de818900c7cdb59cd80b5b83a6ad45b0ed02c8147182790","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b27c3ca2d4b689d1de818900c7cdb59cd80b5b83a6ad45b0ed02c8147182790","first_computed_at":"2026-07-05T05:02:05.789195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:02:05.789195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lCNtnvALCkzp6RbGQ1SdokXItSLVYpZxq8zcPMuZ3XVGBi8ffxUtkyYYiZDa3/PYeB05YSLMpnoqJj6ReRVEBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:02:05.789566Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.14792","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:799e140010203491306f292b54be82f632fe7a7e346cd2006d0cb81509d5e739","sha256:8d378c0c67adea9a12498ad66a2761ccb271ed55824cdd2ab29d2a06b50dae01"],"state_sha256":"7ccaf8386aec9ed19575a4327a0d23352011e1a66201dec7b4a1ae01a25d5171"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ah1nf6G5UcxfYgX+Go5pi7gMm8u7P5HIsPV9ZnGRHaFTw85bMbn9MytaBSSlfDZfeTRGnWkOHGzZd+iasBTfCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T02:45:58.321755Z","bundle_sha256":"6ac6a784c9ced80ba33863703b47b9f91045c3572a383ecf0c36d6b03acd38fd"}}