{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SGZ4SGJVXWZXRTENYLEDTU2CHY","short_pith_number":"pith:SGZ4SGJV","canonical_record":{"source":{"id":"2210.02399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-05T17:18:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c54beac000dad91c668bfb816e68d68aa9de9253c2b195eef3f845ca76408f71","abstract_canon_sha256":"28d83a4fde64ee7902ee14407e1415779ff182497a5c65ca4b48e0014bdead28"},"schema_version":"1.0"},"canonical_sha256":"91b3c91935bdb378cc8dc2c839d3423e38c3175acdb205afdbd741e14fea355f","source":{"kind":"arxiv","id":"2210.02399","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02399","created_at":"2026-05-17T23:38:45Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02399v1","created_at":"2026-05-17T23:38:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02399","created_at":"2026-05-17T23:38:45Z"},{"alias_kind":"pith_short_12","alias_value":"SGZ4SGJVXWZX","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"SGZ4SGJVXWZXRTEN","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"SGZ4SGJV","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SGZ4SGJVXWZXRTENYLEDTU2CHY","target":"record","payload":{"canonical_record":{"source":{"id":"2210.02399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-05T17:18:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c54beac000dad91c668bfb816e68d68aa9de9253c2b195eef3f845ca76408f71","abstract_canon_sha256":"28d83a4fde64ee7902ee14407e1415779ff182497a5c65ca4b48e0014bdead28"},"schema_version":"1.0"},"canonical_sha256":"91b3c91935bdb378cc8dc2c839d3423e38c3175acdb205afdbd741e14fea355f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:45.946147Z","signature_b64":"701cHBV2g9vq59JjoxPbclcDPZf9y7D2JyYxgduWKzMJimMADzvgm31RVybmuQKBjuPuxS7+BZtKeCdWpBIMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91b3c91935bdb378cc8dc2c839d3423e38c3175acdb205afdbd741e14fea355f","last_reissued_at":"2026-05-17T23:38:45.945602Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:45.945602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.02399","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":"2026-05-17T23:38:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C6hvx8jCh2YSBr80Kzodo5bDoZikjA6b3/y5H3jaqZiidUz+YVV/PDv7uNm2I9QdGJHwPze9/UPbSWZX/JyeDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T22:35:10.144462Z"},"content_sha256":"09ab3fe8e7e4f2a23508ebcd8c0b0a1903d19426eb8a2cd0968573b5d91f885d","schema_version":"1.0","event_id":"sha256:09ab3fe8e7e4f2a23508ebcd8c0b0a1903d19426eb8a2cd0968573b5d91f885d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SGZ4SGJVXWZXRTENYLEDTU2CHY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Phenaki generates arbitrarily long videos from sequences of text prompts describing evolving scenes.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dumitru Erhan, Han Zhang, Hernan Moraldo, Julius Kunze, Mohammad Babaeizadeh, Mohammad Taghi Saffar, Pieter-Jan Kindermans, Ruben Villegas, Santiago Castro","submitted_at":"2022-10-05T17:18:28Z","abstract_excerpt":"We present Phenaki, a model capable of realistic video synthesis, given a sequence of textual prompts. Generating videos from text is particularly challenging due to the computational cost, limited quantities of high quality text-video data and variable length of videos. To address these issues, we introduce a new model for learning video representation which compresses the video to a small representation of discrete tokens. This tokenizer uses causal attention in time, which allows it to work with variable-length videos. To generate video tokens from text we are using a bidirectional masked t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Phenaki can generate arbitrary long videos conditioned on a sequence of prompts (i.e. time variable text or a story) in open domain. To the best of our knowledge, this is the first time a paper studies generating videos from time variable prompts.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That joint training on a large corpus of image-text pairs as well as a smaller number of video-text examples can result in generalization beyond what is available in the video datasets.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Phenaki generates arbitrary-length videos from sequences of text prompts by tokenizing videos with causal temporal attention and generating tokens with a text-conditioned masked transformer, trained jointly on images and videos.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Phenaki generates arbitrarily long videos from sequences of text prompts describing evolving scenes.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f745509c0bad2ab37e58c3943ae7856003a85695ccdb6ca9dd4f69f0e7c644cd"},"source":{"id":"2210.02399","kind":"arxiv","version":1},"verdict":{"id":"0ff5b6dc-2ee4-45f2-8b5a-f6cac5d36245","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T01:37:51.649559Z","strongest_claim":"Phenaki can generate arbitrary long videos conditioned on a sequence of prompts (i.e. time variable text or a story) in open domain. To the best of our knowledge, this is the first time a paper studies generating videos from time variable prompts.","one_line_summary":"Phenaki generates arbitrary-length videos from sequences of text prompts by tokenizing videos with causal temporal attention and generating tokens with a text-conditioned masked transformer, trained jointly on images and videos.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That joint training on a large corpus of image-text pairs as well as a smaller number of video-text examples can result in generalization beyond what is available in the video datasets.","pith_extraction_headline":"Phenaki generates arbitrarily long videos from sequences of text prompts describing evolving scenes."},"references":{"count":61,"sample":[{"doi":"","year":2021,"title":"Vivit: A video vision transformer","work_id":"8c555c6f-f480-49d7-89f7-435aedd756bd","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Stochastic variational video prediction","work_id":"7ebdee21-b63c-4ceb-a897-a0e2326c0f2a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Fitvid: Overfitting in pixel-level video prediction","work_id":"98b75ffa-1d61-4641-a59f-5967267b7d2c","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Frozen in time: A joint video and image encoder for end-to-end retrieval","work_id":"1ae0008f-2042-4c35-a953-fb26d78a25c2","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Con- ditional gan with discriminative filter generation for text-to-video synthesis","work_id":"14854921-8b97-4939-9d4b-2c8723e1596c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":61,"snapshot_sha256":"f24d49bcd3d44a312b074908ad4dc8bbd828765188fcb3fc1759a0257e414eab","internal_anchors":12},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c42790fbbfe7d935441820feabe9affea9f1cdb898f97273afde1a8c768d8968"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"0ff5b6dc-2ee4-45f2-8b5a-f6cac5d36245"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NQR1CyTp9M0EvplDmFEGtEXAhfh5rwvWb+NOTZ7PEfxDPUmHBbzOkcc8THxMDTvkOT+1rFxRGwQF5Euh1LbbCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T22:35:10.145311Z"},"content_sha256":"cca0ea323000aee6f49c0435b09caccf379ceba088afe89b15d31a82504fc425","schema_version":"1.0","event_id":"sha256:cca0ea323000aee6f49c0435b09caccf379ceba088afe89b15d31a82504fc425"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SGZ4SGJVXWZXRTENYLEDTU2CHY/bundle.json","state_url":"https://pith.science/pith/SGZ4SGJVXWZXRTENYLEDTU2CHY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SGZ4SGJVXWZXRTENYLEDTU2CHY/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":"2026-05-20T22:35:10Z","links":{"resolver":"https://pith.science/pith/SGZ4SGJVXWZXRTENYLEDTU2CHY","bundle":"https://pith.science/pith/SGZ4SGJVXWZXRTENYLEDTU2CHY/bundle.json","state":"https://pith.science/pith/SGZ4SGJVXWZXRTENYLEDTU2CHY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SGZ4SGJVXWZXRTENYLEDTU2CHY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SGZ4SGJVXWZXRTENYLEDTU2CHY","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":"28d83a4fde64ee7902ee14407e1415779ff182497a5c65ca4b48e0014bdead28","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-05T17:18:28Z","title_canon_sha256":"c54beac000dad91c668bfb816e68d68aa9de9253c2b195eef3f845ca76408f71"},"schema_version":"1.0","source":{"id":"2210.02399","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02399","created_at":"2026-05-17T23:38:45Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02399v1","created_at":"2026-05-17T23:38:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02399","created_at":"2026-05-17T23:38:45Z"},{"alias_kind":"pith_short_12","alias_value":"SGZ4SGJVXWZX","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"SGZ4SGJVXWZXRTEN","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"SGZ4SGJV","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:cca0ea323000aee6f49c0435b09caccf379ceba088afe89b15d31a82504fc425","target":"graph","created_at":"2026-05-17T23:38:45Z","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":"Phenaki can generate arbitrary long videos conditioned on a sequence of prompts (i.e. time variable text or a story) in open domain. To the best of our knowledge, this is the first time a paper studies generating videos from time variable prompts."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That joint training on a large corpus of image-text pairs as well as a smaller number of video-text examples can result in generalization beyond what is available in the video datasets."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Phenaki generates arbitrary-length videos from sequences of text prompts by tokenizing videos with causal temporal attention and generating tokens with a text-conditioned masked transformer, trained jointly on images and videos."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Phenaki generates arbitrarily long videos from sequences of text prompts describing evolving scenes."}],"snapshot_sha256":"f745509c0bad2ab37e58c3943ae7856003a85695ccdb6ca9dd4f69f0e7c644cd"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c42790fbbfe7d935441820feabe9affea9f1cdb898f97273afde1a8c768d8968"},"paper":{"abstract_excerpt":"We present Phenaki, a model capable of realistic video synthesis, given a sequence of textual prompts. Generating videos from text is particularly challenging due to the computational cost, limited quantities of high quality text-video data and variable length of videos. To address these issues, we introduce a new model for learning video representation which compresses the video to a small representation of discrete tokens. This tokenizer uses causal attention in time, which allows it to work with variable-length videos. To generate video tokens from text we are using a bidirectional masked t","authors_text":"Dumitru Erhan, Han Zhang, Hernan Moraldo, Julius Kunze, Mohammad Babaeizadeh, Mohammad Taghi Saffar, Pieter-Jan Kindermans, Ruben Villegas, Santiago Castro","cross_cats":["cs.AI"],"headline":"Phenaki generates arbitrarily long videos from sequences of text prompts describing evolving scenes.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-05T17:18:28Z","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description"},"references":{"count":61,"internal_anchors":12,"resolved_work":61,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Vivit: A video vision transformer","work_id":"8c555c6f-f480-49d7-89f7-435aedd756bd","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Stochastic variational video prediction","work_id":"7ebdee21-b63c-4ceb-a897-a0e2326c0f2a","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Fitvid: Overfitting in pixel-level video prediction","work_id":"98b75ffa-1d61-4641-a59f-5967267b7d2c","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Frozen in time: A joint video and image encoder for end-to-end retrieval","work_id":"1ae0008f-2042-4c35-a953-fb26d78a25c2","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Con- ditional gan with discriminative filter generation for text-to-video synthesis","work_id":"14854921-8b97-4939-9d4b-2c8723e1596c","year":2019}],"snapshot_sha256":"f24d49bcd3d44a312b074908ad4dc8bbd828765188fcb3fc1759a0257e414eab"},"source":{"id":"2210.02399","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-17T01:37:51.649559Z","id":"0ff5b6dc-2ee4-45f2-8b5a-f6cac5d36245","model_set":{"reader":"grok-4.3"},"one_line_summary":"Phenaki generates arbitrary-length videos from sequences of text prompts by tokenizing videos with causal temporal attention and generating tokens with a text-conditioned masked transformer, trained jointly on images and videos.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Phenaki generates arbitrarily long videos from sequences of text prompts describing evolving scenes.","strongest_claim":"Phenaki can generate arbitrary long videos conditioned on a sequence of prompts (i.e. time variable text or a story) in open domain. To the best of our knowledge, this is the first time a paper studies generating videos from time variable prompts.","weakest_assumption":"That joint training on a large corpus of image-text pairs as well as a smaller number of video-text examples can result in generalization beyond what is available in the video datasets."}},"verdict_id":"0ff5b6dc-2ee4-45f2-8b5a-f6cac5d36245"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:09ab3fe8e7e4f2a23508ebcd8c0b0a1903d19426eb8a2cd0968573b5d91f885d","target":"record","created_at":"2026-05-17T23:38:45Z","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":"28d83a4fde64ee7902ee14407e1415779ff182497a5c65ca4b48e0014bdead28","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-05T17:18:28Z","title_canon_sha256":"c54beac000dad91c668bfb816e68d68aa9de9253c2b195eef3f845ca76408f71"},"schema_version":"1.0","source":{"id":"2210.02399","kind":"arxiv","version":1}},"canonical_sha256":"91b3c91935bdb378cc8dc2c839d3423e38c3175acdb205afdbd741e14fea355f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91b3c91935bdb378cc8dc2c839d3423e38c3175acdb205afdbd741e14fea355f","first_computed_at":"2026-05-17T23:38:45.945602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:45.945602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"701cHBV2g9vq59JjoxPbclcDPZf9y7D2JyYxgduWKzMJimMADzvgm31RVybmuQKBjuPuxS7+BZtKeCdWpBIMAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:45.946147Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.02399","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09ab3fe8e7e4f2a23508ebcd8c0b0a1903d19426eb8a2cd0968573b5d91f885d","sha256:cca0ea323000aee6f49c0435b09caccf379ceba088afe89b15d31a82504fc425"],"state_sha256":"dc4551f64c2505060b92001ac99c16c4596f149f014de215d9fa7ee5866240ec"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tis++/dXWxjawCmaSP/37AxQbnJmGC9mzNWqW+VTD2kLuDFbGEvnK9/ASFo/iAcrAgQKNiTTqYAwiYOh/wYSAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T22:35:10.149062Z","bundle_sha256":"1b2099ea96fa0640adcd85f287a4844730ab592c41798be9e539573532033cf4"}}