{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:F5OQYRSNQFLNWM4OHEC6LPTHAE","short_pith_number":"pith:F5OQYRSN","canonical_record":{"source":{"id":"2311.04145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-07T17:16:06Z","cross_cats_sorted":[],"title_canon_sha256":"463aebdc2591e5cedd897bdf457d6ff329f77156d5c00c398df35bdbecbd84e5","abstract_canon_sha256":"f2d0adc1d96d3c17ed39de6f450a0dad9f2503244156a80a09ce1e0fdccf0aa2"},"schema_version":"1.0"},"canonical_sha256":"2f5d0c464d8156db338e3905e5be67012dc41effa8fea867da5bada3b8ed6243","source":{"kind":"arxiv","id":"2311.04145","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.04145","created_at":"2026-05-17T23:46:49Z"},{"alias_kind":"arxiv_version","alias_value":"2311.04145v1","created_at":"2026-05-17T23:46:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04145","created_at":"2026-05-17T23:46:49Z"},{"alias_kind":"pith_short_12","alias_value":"F5OQYRSNQFLN","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"F5OQYRSNQFLNWM4O","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"F5OQYRSN","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:F5OQYRSNQFLNWM4OHEC6LPTHAE","target":"record","payload":{"canonical_record":{"source":{"id":"2311.04145","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-07T17:16:06Z","cross_cats_sorted":[],"title_canon_sha256":"463aebdc2591e5cedd897bdf457d6ff329f77156d5c00c398df35bdbecbd84e5","abstract_canon_sha256":"f2d0adc1d96d3c17ed39de6f450a0dad9f2503244156a80a09ce1e0fdccf0aa2"},"schema_version":"1.0"},"canonical_sha256":"2f5d0c464d8156db338e3905e5be67012dc41effa8fea867da5bada3b8ed6243","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:49.010191Z","signature_b64":"tHTocHGNjuVSXUkyg8GaUm/zhHdBE4qlRLCjumqtLm17J/vMEqVTovpIdBK1pG28M1I/zLa9dPEWB4cKZyTZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f5d0c464d8156db338e3905e5be67012dc41effa8fea867da5bada3b8ed6243","last_reissued_at":"2026-05-17T23:46:49.009689Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:49.009689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.04145","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":"2026-05-17T23:46:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z1NSRg4CLvQk/UpIix/PhrnmNKvjzWm/XQR5uhl1/8TghBCi1fOnej9F7ykJOezt58NQUFHk8TnuKl3vaWnGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T19:22:14.175025Z"},"content_sha256":"bf38b827ce95f97a9fabb811d09cb06d9883f4538d24c80fa5b50d49cb22ebf2","schema_version":"1.0","event_id":"sha256:bf38b827ce95f97a9fabb811d09cb06d9883f4538d24c80fa5b50d49cb22ebf2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:F5OQYRSNQFLNWM4OHEC6LPTHAE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Deli Zhao, Hangjie Yuan, Jiayu Wang, Jingren Zhou, Kang Zhao, Shiwei Zhang, Xiang Wang, Yingya Zhang, Zhiwu Qin","submitted_at":"2023-11-07T17:16:06Z","abstract_excerpt":"Video synthesis has recently made remarkable strides benefiting from the rapid development of diffusion models. However, it still encounters challenges in terms of semantic accuracy, clarity and spatio-temporal continuity. They primarily arise from the scarcity of well-aligned text-video data and the complex inherent structure of videos, making it difficult for the model to simultaneously ensure semantic and qualitative excellence. In this report, we propose a cascaded I2VGen-XL approach that enhances model performance by decoupling these two factors and ensures the alignment of the input data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04145","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":""},"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":"2026-05-17T23:46:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nBBSlo/RtVwjaGvd4avrbpwbKNYzrX9tUkBXH9AKlQp3hJdwFRlHyUTfnIYWRCcmL8Vbn+wpwL5GYsd4EesjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T19:22:14.175691Z"},"content_sha256":"48a4caf09b91a2c7aee3ef0c017e2122d7a555f61733b774fbf46625e8c00a85","schema_version":"1.0","event_id":"sha256:48a4caf09b91a2c7aee3ef0c017e2122d7a555f61733b774fbf46625e8c00a85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE/bundle.json","state_url":"https://pith.science/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE/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":"2026-05-19T19:22:14Z","links":{"resolver":"https://pith.science/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE","bundle":"https://pith.science/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE/bundle.json","state":"https://pith.science/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5OQYRSNQFLNWM4OHEC6LPTHAE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:F5OQYRSNQFLNWM4OHEC6LPTHAE","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":"f2d0adc1d96d3c17ed39de6f450a0dad9f2503244156a80a09ce1e0fdccf0aa2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-07T17:16:06Z","title_canon_sha256":"463aebdc2591e5cedd897bdf457d6ff329f77156d5c00c398df35bdbecbd84e5"},"schema_version":"1.0","source":{"id":"2311.04145","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.04145","created_at":"2026-05-17T23:46:49Z"},{"alias_kind":"arxiv_version","alias_value":"2311.04145v1","created_at":"2026-05-17T23:46:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04145","created_at":"2026-05-17T23:46:49Z"},{"alias_kind":"pith_short_12","alias_value":"F5OQYRSNQFLN","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"F5OQYRSNQFLNWM4O","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"F5OQYRSN","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:48a4caf09b91a2c7aee3ef0c017e2122d7a555f61733b774fbf46625e8c00a85","target":"graph","created_at":"2026-05-17T23:46:49Z","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"},"paper":{"abstract_excerpt":"Video synthesis has recently made remarkable strides benefiting from the rapid development of diffusion models. However, it still encounters challenges in terms of semantic accuracy, clarity and spatio-temporal continuity. They primarily arise from the scarcity of well-aligned text-video data and the complex inherent structure of videos, making it difficult for the model to simultaneously ensure semantic and qualitative excellence. In this report, we propose a cascaded I2VGen-XL approach that enhances model performance by decoupling these two factors and ensures the alignment of the input data","authors_text":"Deli Zhao, Hangjie Yuan, Jiayu Wang, Jingren Zhou, Kang Zhao, Shiwei Zhang, Xiang Wang, Yingya Zhang, Zhiwu Qin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-07T17:16:06Z","title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04145","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:bf38b827ce95f97a9fabb811d09cb06d9883f4538d24c80fa5b50d49cb22ebf2","target":"record","created_at":"2026-05-17T23:46:49Z","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":"f2d0adc1d96d3c17ed39de6f450a0dad9f2503244156a80a09ce1e0fdccf0aa2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-07T17:16:06Z","title_canon_sha256":"463aebdc2591e5cedd897bdf457d6ff329f77156d5c00c398df35bdbecbd84e5"},"schema_version":"1.0","source":{"id":"2311.04145","kind":"arxiv","version":1}},"canonical_sha256":"2f5d0c464d8156db338e3905e5be67012dc41effa8fea867da5bada3b8ed6243","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f5d0c464d8156db338e3905e5be67012dc41effa8fea867da5bada3b8ed6243","first_computed_at":"2026-05-17T23:46:49.009689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:49.009689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tHTocHGNjuVSXUkyg8GaUm/zhHdBE4qlRLCjumqtLm17J/vMEqVTovpIdBK1pG28M1I/zLa9dPEWB4cKZyTZDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:49.010191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.04145","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf38b827ce95f97a9fabb811d09cb06d9883f4538d24c80fa5b50d49cb22ebf2","sha256:48a4caf09b91a2c7aee3ef0c017e2122d7a555f61733b774fbf46625e8c00a85"],"state_sha256":"866ac9433ccfefdcb511ae8df4de806134af4b9db03cd3b0e1732a846d612cce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bAM2NDaGmbQya+eEVVWJZDXQjFpyZPZD036CWrGU1kXqZcGM2hJKTbTtrcQJ8wT8my9M1E2kHYb+cpm52153AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T19:22:14.179309Z","bundle_sha256":"d6480d6aade25d420a4144065ec483950e309f75619223ff121f26e4a9fae740"}}