{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3EY4ZDFD2X677CF4JN5EDU6SS2","short_pith_number":"pith:3EY4ZDFD","schema_version":"1.0","canonical_sha256":"d931cc8ca3d5fdff88bc4b7a41d3d296b42214a2186167d88a56941c40d62c80","source":{"kind":"arxiv","id":"2503.11412","version":1},"attestation_state":"computed","paper":{"title":"MTV-Inpaint: Multi-Task Long Video Inpainting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Liao, Liang Hou, Pengfei Wan, Shiyuan Yang, Xiaodong Chen, Xin Tao, Zheng Gu","submitted_at":"2025-03-14T13:54:10Z","abstract_excerpt":"Video inpainting involves modifying local regions within a video, ensuring spatial and temporal consistency. Most existing methods focus primarily on scene completion (i.e., filling missing regions) and lack the capability to insert new objects into a scene in a controllable manner. Fortunately, recent advancements in text-to-video (T2V) diffusion models pave the way for text-guided video inpainting. However, directly adapting T2V models for inpainting remains limited in unifying completion and insertion tasks, lacks input controllability, and struggles with long videos, thereby restricting th"},"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":"2503.11412","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T13:54:10Z","cross_cats_sorted":[],"title_canon_sha256":"c14620fb195a054d22393a6c902b98845bb89b7f77f4e7324073db81faa3c1d0","abstract_canon_sha256":"1ef225c0925725135b8017e7e8fc3a31c36a00e6cb48590394113a8fcd8f228d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:31.007267Z","signature_b64":"xK+b6BMvnHmgefehG5BHYMUBb8kNm2j5T9YnvjQrLphHkc8qA7IfGYAHnaeKq50zB3r0ctbcsRniO2xQOP5yAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d931cc8ca3d5fdff88bc4b7a41d3d296b42214a2186167d88a56941c40d62c80","last_reissued_at":"2026-07-05T10:31:31.006461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:31.006461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MTV-Inpaint: Multi-Task Long Video Inpainting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Liao, Liang Hou, Pengfei Wan, Shiyuan Yang, Xiaodong Chen, Xin Tao, Zheng Gu","submitted_at":"2025-03-14T13:54:10Z","abstract_excerpt":"Video inpainting involves modifying local regions within a video, ensuring spatial and temporal consistency. Most existing methods focus primarily on scene completion (i.e., filling missing regions) and lack the capability to insert new objects into a scene in a controllable manner. Fortunately, recent advancements in text-to-video (T2V) diffusion models pave the way for text-guided video inpainting. However, directly adapting T2V models for inpainting remains limited in unifying completion and insertion tasks, lacks input controllability, and struggles with long videos, thereby restricting th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11412","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/2503.11412/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":"2503.11412","created_at":"2026-07-05T10:31:31.006579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11412v1","created_at":"2026-07-05T10:31:31.006579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11412","created_at":"2026-07-05T10:31:31.006579+00:00"},{"alias_kind":"pith_short_12","alias_value":"3EY4ZDFD2X67","created_at":"2026-07-05T10:31:31.006579+00:00"},{"alias_kind":"pith_short_16","alias_value":"3EY4ZDFD2X677CF4","created_at":"2026-07-05T10:31:31.006579+00:00"},{"alias_kind":"pith_short_8","alias_value":"3EY4ZDFD","created_at":"2026-07-05T10:31:31.006579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24225","citing_title":"Geometry-Instructed Video Editing","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23192","citing_title":"Occlusion-Aware Physics-Semantic Keyframe Selection for Robust Video Editing","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09283","citing_title":"From Ideal to Real: Stable Video Object Removal under Imperfect Conditions","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21901","citing_title":"CLEAR: Context-Aware Learning with End-to-End Mask-Free Inference for Adaptive Video Subtitle Removal","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14556","citing_title":"Controllable Video Object Insertion via Multiview Priors","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3EY4ZDFD2X677CF4JN5EDU6SS2","json":"https://pith.science/pith/3EY4ZDFD2X677CF4JN5EDU6SS2.json","graph_json":"https://pith.science/api/pith-number/3EY4ZDFD2X677CF4JN5EDU6SS2/graph.json","events_json":"https://pith.science/api/pith-number/3EY4ZDFD2X677CF4JN5EDU6SS2/events.json","paper":"https://pith.science/paper/3EY4ZDFD"},"agent_actions":{"view_html":"https://pith.science/pith/3EY4ZDFD2X677CF4JN5EDU6SS2","download_json":"https://pith.science/pith/3EY4ZDFD2X677CF4JN5EDU6SS2.json","view_paper":"https://pith.science/paper/3EY4ZDFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11412&json=true","fetch_graph":"https://pith.science/api/pith-number/3EY4ZDFD2X677CF4JN5EDU6SS2/graph.json","fetch_events":"https://pith.science/api/pith-number/3EY4ZDFD2X677CF4JN5EDU6SS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3EY4ZDFD2X677CF4JN5EDU6SS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3EY4ZDFD2X677CF4JN5EDU6SS2/action/storage_attestation","attest_author":"https://pith.science/pith/3EY4ZDFD2X677CF4JN5EDU6SS2/action/author_attestation","sign_citation":"https://pith.science/pith/3EY4ZDFD2X677CF4JN5EDU6SS2/action/citation_signature","submit_replication":"https://pith.science/pith/3EY4ZDFD2X677CF4JN5EDU6SS2/action/replication_record"}},"created_at":"2026-07-05T10:31:31.006579+00:00","updated_at":"2026-07-05T10:31:31.006579+00:00"}