{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:OU26JZVXN7PFRPGWZIILPOBJGB","short_pith_number":"pith:OU26JZVX","canonical_record":{"source":{"id":"2104.14806","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-30T07:40:35Z","cross_cats_sorted":[],"title_canon_sha256":"b311166ff76651063503877899e661c1ebfbbffe9021a69a9183b1edbcec8023","abstract_canon_sha256":"01bcdca673ccfd100ddc1c22286c0de76c74f8341f266347bb340f720e036738"},"schema_version":"1.0"},"canonical_sha256":"7535e4e6b76fde58bcd6ca10b7b829305595e3f26eab4bd522a9a21136384f9b","source":{"kind":"arxiv","id":"2104.14806","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.14806","created_at":"2026-07-05T02:36:26Z"},{"alias_kind":"arxiv_version","alias_value":"2104.14806v1","created_at":"2026-07-05T02:36:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.14806","created_at":"2026-07-05T02:36:26Z"},{"alias_kind":"pith_short_12","alias_value":"OU26JZVXN7PF","created_at":"2026-07-05T02:36:26Z"},{"alias_kind":"pith_short_16","alias_value":"OU26JZVXN7PFRPGW","created_at":"2026-07-05T02:36:26Z"},{"alias_kind":"pith_short_8","alias_value":"OU26JZVX","created_at":"2026-07-05T02:36:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:OU26JZVXN7PFRPGWZIILPOBJGB","target":"record","payload":{"canonical_record":{"source":{"id":"2104.14806","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-30T07:40:35Z","cross_cats_sorted":[],"title_canon_sha256":"b311166ff76651063503877899e661c1ebfbbffe9021a69a9183b1edbcec8023","abstract_canon_sha256":"01bcdca673ccfd100ddc1c22286c0de76c74f8341f266347bb340f720e036738"},"schema_version":"1.0"},"canonical_sha256":"7535e4e6b76fde58bcd6ca10b7b829305595e3f26eab4bd522a9a21136384f9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:26.770578Z","signature_b64":"z8NLLASbP4ZRCMBYrStlko/gARdRG8EBMsfNQBW7zs95TB/MRqR5aNDnBEz/lttJTScOQycuGDtdOvfVmGf0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7535e4e6b76fde58bcd6ca10b7b829305595e3f26eab4bd522a9a21136384f9b","last_reissued_at":"2026-07-05T02:36:26.770113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:26.770113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.14806","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":"2026-07-05T02:36:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+rRfByXvNP3RXL+qW0Z4RtIKbvbmOsZuEkyGbYI5zcLU6fzj121GNpwV3WsrRDSOdKMK1aOXhURzFTp1sAH9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:20:04.286353Z"},"content_sha256":"47dc8e9a035be4c6cb01b938fad1aa359c5329b5eff13550b828b04577c871f8","schema_version":"1.0","event_id":"sha256:47dc8e9a035be4c6cb01b938fad1aa359c5329b5eff13550b828b04577c871f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:OU26JZVXN7PFRPGWZIILPOBJGB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binyang Li, Chenfei Wu, Fan Yang, Guillermo Sapiro, Lei Ji, Lun Huang, Nan Duan, Qianxi Zhang","submitted_at":"2021-04-30T07:40:35Z","abstract_excerpt":"Generating videos from text is a challenging task due to its high computational requirements for training and infinite possible answers for evaluation. Existing works typically experiment on simple or small datasets, where the generalization ability is quite limited. In this work, we propose GODIVA, an open-domain text-to-video pretrained model that can generate videos from text in an auto-regressive manner using a three-dimensional sparse attention mechanism. We pretrain our model on Howto100M, a large-scale text-video dataset that contains more than 136 million text-video pairs. Experiments "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.14806","kind":"arxiv","version":1},"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/2104.14806/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":"2026-07-05T02:36:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V3vRQC4e90J61CBSuNQO2OHlqHmXS1J78BtxrGiha74OLk/hzMVn1jE7XKdzX4mbAcDjqgb+ZEiEMlv3Xl3JDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:20:04.287011Z"},"content_sha256":"7e62964a770c571b1c732ae1dcf2097ff531049d098b9126c4d82c5a512c743c","schema_version":"1.0","event_id":"sha256:7e62964a770c571b1c732ae1dcf2097ff531049d098b9126c4d82c5a512c743c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OU26JZVXN7PFRPGWZIILPOBJGB/bundle.json","state_url":"https://pith.science/pith/OU26JZVXN7PFRPGWZIILPOBJGB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OU26JZVXN7PFRPGWZIILPOBJGB/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":"2026-08-05T11:20:04Z","links":{"resolver":"https://pith.science/pith/OU26JZVXN7PFRPGWZIILPOBJGB","bundle":"https://pith.science/pith/OU26JZVXN7PFRPGWZIILPOBJGB/bundle.json","state":"https://pith.science/pith/OU26JZVXN7PFRPGWZIILPOBJGB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OU26JZVXN7PFRPGWZIILPOBJGB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OU26JZVXN7PFRPGWZIILPOBJGB","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":"01bcdca673ccfd100ddc1c22286c0de76c74f8341f266347bb340f720e036738","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-30T07:40:35Z","title_canon_sha256":"b311166ff76651063503877899e661c1ebfbbffe9021a69a9183b1edbcec8023"},"schema_version":"1.0","source":{"id":"2104.14806","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.14806","created_at":"2026-07-05T02:36:26Z"},{"alias_kind":"arxiv_version","alias_value":"2104.14806v1","created_at":"2026-07-05T02:36:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.14806","created_at":"2026-07-05T02:36:26Z"},{"alias_kind":"pith_short_12","alias_value":"OU26JZVXN7PF","created_at":"2026-07-05T02:36:26Z"},{"alias_kind":"pith_short_16","alias_value":"OU26JZVXN7PFRPGW","created_at":"2026-07-05T02:36:26Z"},{"alias_kind":"pith_short_8","alias_value":"OU26JZVX","created_at":"2026-07-05T02:36:26Z"}],"graph_snapshots":[{"event_id":"sha256:7e62964a770c571b1c732ae1dcf2097ff531049d098b9126c4d82c5a512c743c","target":"graph","created_at":"2026-07-05T02:36:26Z","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/2104.14806/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating videos from text is a challenging task due to its high computational requirements for training and infinite possible answers for evaluation. Existing works typically experiment on simple or small datasets, where the generalization ability is quite limited. In this work, we propose GODIVA, an open-domain text-to-video pretrained model that can generate videos from text in an auto-regressive manner using a three-dimensional sparse attention mechanism. We pretrain our model on Howto100M, a large-scale text-video dataset that contains more than 136 million text-video pairs. Experiments ","authors_text":"Binyang Li, Chenfei Wu, Fan Yang, Guillermo Sapiro, Lei Ji, Lun Huang, Nan Duan, Qianxi Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-30T07:40:35Z","title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.14806","kind":"arxiv","version":1},"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":"sha256:47dc8e9a035be4c6cb01b938fad1aa359c5329b5eff13550b828b04577c871f8","target":"record","created_at":"2026-07-05T02:36:26Z","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":"01bcdca673ccfd100ddc1c22286c0de76c74f8341f266347bb340f720e036738","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-30T07:40:35Z","title_canon_sha256":"b311166ff76651063503877899e661c1ebfbbffe9021a69a9183b1edbcec8023"},"schema_version":"1.0","source":{"id":"2104.14806","kind":"arxiv","version":1}},"canonical_sha256":"7535e4e6b76fde58bcd6ca10b7b829305595e3f26eab4bd522a9a21136384f9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7535e4e6b76fde58bcd6ca10b7b829305595e3f26eab4bd522a9a21136384f9b","first_computed_at":"2026-07-05T02:36:26.770113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:36:26.770113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z8NLLASbP4ZRCMBYrStlko/gARdRG8EBMsfNQBW7zs95TB/MRqR5aNDnBEz/lttJTScOQycuGDtdOvfVmGf0Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:36:26.770578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.14806","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47dc8e9a035be4c6cb01b938fad1aa359c5329b5eff13550b828b04577c871f8","sha256:7e62964a770c571b1c732ae1dcf2097ff531049d098b9126c4d82c5a512c743c"],"state_sha256":"7c68c11b85c7ba9f1f9f8e6cda0bd9d8043927040f97b591b611b23ca255303f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yled7LoYPNm3emiT1CmKU3pR4pJ9prSEMxGrPLBhb0ncVFGR6UyDf+UD3QUgx/4vlzBmD+EAc687GavAijmdBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:20:04.291408Z","bundle_sha256":"8e9cda05650bfe223fdf73e5856226a2270838c22fd64d5f15cab7f54f1c4a31"}}