{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4ATSCFTP7QV7OHWM6MPHJPFP3S","short_pith_number":"pith:4ATSCFTP","schema_version":"1.0","canonical_sha256":"e02721166ffc2bf71eccf31e74bcafdc9eab249292895ca3a79d5452c16eb8d9","source":{"kind":"arxiv","id":"2312.16693","version":4},"attestation_state":"computed","paper":{"title":"I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyang Ma, Di Zhang, Haibin Huang, Liang Hou, Mingwu Zheng, Pengfei Wan, Weiming Hu, Xun Guo, Yuan Gao, Yufan Deng, Yufan Liu, Zhengjun Zha","submitted_at":"2023-12-27T19:11:50Z","abstract_excerpt":"Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image and semantically aligns with the input prompt. Existing methods typically augment pretrained text-to-video (T2V) models by either concatenating the image with noised video frames channel-wise before being fed into the model or injecting the image embedding produced by pretrained image encoders in cross-attention modules. However, the former approach often necessitates altering the fundamental weights of pretrained T2V models, thus restricting the model's compatibility wi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.16693","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-27T19:11:50Z","cross_cats_sorted":[],"title_canon_sha256":"65048b7769426efaf6d765737e31769f1df5c6c72269c27876d6ed94b8bfdc75","abstract_canon_sha256":"bcecdc9c9963bedfff39e4675767ca1bce7049206a893904c0723e3799935103"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:16.303859Z","signature_b64":"eOG2uZd5/Jr5k7V2tekBgCxXJlX6mYPELpZpZ9kEJp4omAhVNz39cRtx7I3N4sJYG1FY83hCuTYVRrbK+Bi1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e02721166ffc2bf71eccf31e74bcafdc9eab249292895ca3a79d5452c16eb8d9","last_reissued_at":"2026-07-05T08:37:16.303379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:16.303379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chongyang Ma, Di Zhang, Haibin Huang, Liang Hou, Mingwu Zheng, Pengfei Wan, Weiming Hu, Xun Guo, Yuan Gao, Yufan Deng, Yufan Liu, Zhengjun Zha","submitted_at":"2023-12-27T19:11:50Z","abstract_excerpt":"Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image and semantically aligns with the input prompt. Existing methods typically augment pretrained text-to-video (T2V) models by either concatenating the image with noised video frames channel-wise before being fed into the model or injecting the image embedding produced by pretrained image encoders in cross-attention modules. However, the former approach often necessitates altering the fundamental weights of pretrained T2V models, thus restricting the model's compatibility wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16693","kind":"arxiv","version":4},"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/2312.16693/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.16693","created_at":"2026-07-05T08:37:16.303438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16693v4","created_at":"2026-07-05T08:37:16.303438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16693","created_at":"2026-07-05T08:37:16.303438+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ATSCFTP7QV7","created_at":"2026-07-05T08:37:16.303438+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ATSCFTP7QV7OHWM","created_at":"2026-07-05T08:37:16.303438+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ATSCFTP","created_at":"2026-07-05T08:37:16.303438+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ATSCFTP7QV7OHWM6MPHJPFP3S","json":"https://pith.science/pith/4ATSCFTP7QV7OHWM6MPHJPFP3S.json","graph_json":"https://pith.science/api/pith-number/4ATSCFTP7QV7OHWM6MPHJPFP3S/graph.json","events_json":"https://pith.science/api/pith-number/4ATSCFTP7QV7OHWM6MPHJPFP3S/events.json","paper":"https://pith.science/paper/4ATSCFTP"},"agent_actions":{"view_html":"https://pith.science/pith/4ATSCFTP7QV7OHWM6MPHJPFP3S","download_json":"https://pith.science/pith/4ATSCFTP7QV7OHWM6MPHJPFP3S.json","view_paper":"https://pith.science/paper/4ATSCFTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16693&json=true","fetch_graph":"https://pith.science/api/pith-number/4ATSCFTP7QV7OHWM6MPHJPFP3S/graph.json","fetch_events":"https://pith.science/api/pith-number/4ATSCFTP7QV7OHWM6MPHJPFP3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ATSCFTP7QV7OHWM6MPHJPFP3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ATSCFTP7QV7OHWM6MPHJPFP3S/action/storage_attestation","attest_author":"https://pith.science/pith/4ATSCFTP7QV7OHWM6MPHJPFP3S/action/author_attestation","sign_citation":"https://pith.science/pith/4ATSCFTP7QV7OHWM6MPHJPFP3S/action/citation_signature","submit_replication":"https://pith.science/pith/4ATSCFTP7QV7OHWM6MPHJPFP3S/action/replication_record"}},"created_at":"2026-07-05T08:37:16.303438+00:00","updated_at":"2026-07-05T08:37:16.303438+00:00"}