{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LCKOSK3PRRQ6T5SXGH4HGLXI4J","short_pith_number":"pith:LCKOSK3P","schema_version":"1.0","canonical_sha256":"5894e92b6f8c61e9f65731f8732ee8e2515dd0b335018c9b4719962abcd7cf20","source":{"kind":"arxiv","id":"2505.21205","version":2},"attestation_state":"computed","paper":{"title":"EF-VI: Enhancing End-Frame Injection for Video Inbetweening","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Chen, Liuhan Chen, Li Yuan, Shenghai Yuan, Xianyi He, Xiaodong Cun, Xiaoyu Li, Ying Shan","submitted_at":"2025-05-27T13:53:50Z","abstract_excerpt":"Video inbetweening aims to synthesize intermediate video sequences conditioned on the given start and end frames. Current state-of-the-art methods primarily extend large-scale pre-trained Image-to-Video Diffusion Models (I2V-DMs) by incorporating the end-frame condition via direct fine-tuning or temporally bidirectional sampling. However, the former results in a weak end-frame constraint, while the latter inevitably disrupts the input representation of video frames, leading to suboptimal performance. To improve the end-frame constraint while avoiding disruption of the input representation, we "},"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":"2505.21205","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T13:53:50Z","cross_cats_sorted":[],"title_canon_sha256":"6cf6e03e8d4a6dc1bb0b1487342d1e2a622cf228836b68c4df5873a01a1bfe78","abstract_canon_sha256":"f3215994582c589858ed2083d169e32e6b5f20c4c8bdb7afa19077529da60a6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:27.509433Z","signature_b64":"VTL1Dw3ClZRJgHvQpLlltKI0lPTDCidzUa6WO1Evqk2cXUj4UVnIvVxvZUCxOdm9hcn6DLOdwnBXqRU5zAv3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5894e92b6f8c61e9f65731f8732ee8e2515dd0b335018c9b4719962abcd7cf20","last_reissued_at":"2026-07-05T11:51:27.508892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:27.508892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EF-VI: Enhancing End-Frame Injection for Video Inbetweening","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Chen, Liuhan Chen, Li Yuan, Shenghai Yuan, Xianyi He, Xiaodong Cun, Xiaoyu Li, Ying Shan","submitted_at":"2025-05-27T13:53:50Z","abstract_excerpt":"Video inbetweening aims to synthesize intermediate video sequences conditioned on the given start and end frames. Current state-of-the-art methods primarily extend large-scale pre-trained Image-to-Video Diffusion Models (I2V-DMs) by incorporating the end-frame condition via direct fine-tuning or temporally bidirectional sampling. However, the former results in a weak end-frame constraint, while the latter inevitably disrupts the input representation of video frames, leading to suboptimal performance. To improve the end-frame constraint while avoiding disruption of the input representation, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21205","kind":"arxiv","version":2},"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/2505.21205/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":"2505.21205","created_at":"2026-07-05T11:51:27.508955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21205v2","created_at":"2026-07-05T11:51:27.508955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21205","created_at":"2026-07-05T11:51:27.508955+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCKOSK3PRRQ6","created_at":"2026-07-05T11:51:27.508955+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCKOSK3PRRQ6T5SX","created_at":"2026-07-05T11:51:27.508955+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCKOSK3P","created_at":"2026-07-05T11:51:27.508955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03819","citing_title":"ActivityForensics: A Comprehensive Benchmark for Localizing Manipulated Activity in Videos","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCKOSK3PRRQ6T5SXGH4HGLXI4J","json":"https://pith.science/pith/LCKOSK3PRRQ6T5SXGH4HGLXI4J.json","graph_json":"https://pith.science/api/pith-number/LCKOSK3PRRQ6T5SXGH4HGLXI4J/graph.json","events_json":"https://pith.science/api/pith-number/LCKOSK3PRRQ6T5SXGH4HGLXI4J/events.json","paper":"https://pith.science/paper/LCKOSK3P"},"agent_actions":{"view_html":"https://pith.science/pith/LCKOSK3PRRQ6T5SXGH4HGLXI4J","download_json":"https://pith.science/pith/LCKOSK3PRRQ6T5SXGH4HGLXI4J.json","view_paper":"https://pith.science/paper/LCKOSK3P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21205&json=true","fetch_graph":"https://pith.science/api/pith-number/LCKOSK3PRRQ6T5SXGH4HGLXI4J/graph.json","fetch_events":"https://pith.science/api/pith-number/LCKOSK3PRRQ6T5SXGH4HGLXI4J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCKOSK3PRRQ6T5SXGH4HGLXI4J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCKOSK3PRRQ6T5SXGH4HGLXI4J/action/storage_attestation","attest_author":"https://pith.science/pith/LCKOSK3PRRQ6T5SXGH4HGLXI4J/action/author_attestation","sign_citation":"https://pith.science/pith/LCKOSK3PRRQ6T5SXGH4HGLXI4J/action/citation_signature","submit_replication":"https://pith.science/pith/LCKOSK3PRRQ6T5SXGH4HGLXI4J/action/replication_record"}},"created_at":"2026-07-05T11:51:27.508955+00:00","updated_at":"2026-07-05T11:51:27.508955+00:00"}