{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D2K2NMBKWV7R6Z3BVYM3FY7HDI","short_pith_number":"pith:D2K2NMBK","schema_version":"1.0","canonical_sha256":"1e95a6b02ab57f1f6761ae19b2e3e71a38306dd0293d0c5cb21da87c93c55c11","source":{"kind":"arxiv","id":"2501.10018","version":1},"attestation_state":"computed","paper":{"title":"DiffuEraser: A Diffusion Model for Video Inpainting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haolan Xue, Liefeng Bo, Peiran Ren, Xiaowen Li","submitted_at":"2025-01-17T08:03:02Z","abstract_excerpt":"Recent video inpainting algorithms integrate flow-based pixel propagation with transformer-based generation to leverage optical flow for restoring textures and objects using information from neighboring frames, while completing masked regions through visual Transformers. However, these approaches often encounter blurring and temporal inconsistencies when dealing with large masks, highlighting the need for models with enhanced generative capabilities. Recently, diffusion models have emerged as a prominent technique in image and video generation due to their impressive performance. In this paper"},"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":"2501.10018","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-17T08:03:02Z","cross_cats_sorted":[],"title_canon_sha256":"a7980bdc02b48762032a6a756d3c6c80147c9e448fb50ee17c6466aea48f248d","abstract_canon_sha256":"11455f173ddec3836a36d0cc6589dcc85e3131e8300d18d3f344787502a4c11f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:15.308607Z","signature_b64":"ZPW+Nlt1Y8krPvgH4r6CgB4Dt8XSe+JkxRfRMsuigZ2Wu7l8M7hGE6SUUwgFNTaqZ/HMPvf+CC5v8citwRAxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e95a6b02ab57f1f6761ae19b2e3e71a38306dd0293d0c5cb21da87c93c55c11","last_reissued_at":"2026-07-05T10:02:15.308074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:15.308074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffuEraser: A Diffusion Model for Video Inpainting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haolan Xue, Liefeng Bo, Peiran Ren, Xiaowen Li","submitted_at":"2025-01-17T08:03:02Z","abstract_excerpt":"Recent video inpainting algorithms integrate flow-based pixel propagation with transformer-based generation to leverage optical flow for restoring textures and objects using information from neighboring frames, while completing masked regions through visual Transformers. However, these approaches often encounter blurring and temporal inconsistencies when dealing with large masks, highlighting the need for models with enhanced generative capabilities. Recently, diffusion models have emerged as a prominent technique in image and video generation due to their impressive performance. In this paper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10018","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/2501.10018/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":"2501.10018","created_at":"2026-07-05T10:02:15.308139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10018v1","created_at":"2026-07-05T10:02:15.308139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10018","created_at":"2026-07-05T10:02:15.308139+00:00"},{"alias_kind":"pith_short_12","alias_value":"D2K2NMBKWV7R","created_at":"2026-07-05T10:02:15.308139+00:00"},{"alias_kind":"pith_short_16","alias_value":"D2K2NMBKWV7R6Z3B","created_at":"2026-07-05T10:02:15.308139+00:00"},{"alias_kind":"pith_short_8","alias_value":"D2K2NMBK","created_at":"2026-07-05T10:02:15.308139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01362","citing_title":"AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30045","citing_title":"GenEraser: Generalizable Video Object Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22344","citing_title":"Bernini: Latent Semantic Planning for Video Diffusion","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15843","citing_title":"WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20360","citing_title":"EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07469","citing_title":"VideoCoF: Unified Video Editing with Temporal Reasoner","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09283","citing_title":"From Ideal to Real: Stable Video Object Removal under Imperfect Conditions","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14534","citing_title":"PROVE: A Perceptual RemOVal cohErence Benchmark for Visual Media","ref_index":18,"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":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27322","citing_title":"YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09897","citing_title":"Tube-Structured Incremental Semantic HARQ for Generative Video Receivers","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06535","citing_title":"Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via Decoupled Guidance","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08546","citing_title":"When Numbers Speak: Aligning Textual Numerals and Visual Instances in Text-to-Video Diffusion Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05898","citing_title":"Physics-Aware Video Instance Removal Benchmark","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04331","citing_title":"GA-GS: Generation-Assisted Gaussian Splatting for Static Scene Reconstruction","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D2K2NMBKWV7R6Z3BVYM3FY7HDI","json":"https://pith.science/pith/D2K2NMBKWV7R6Z3BVYM3FY7HDI.json","graph_json":"https://pith.science/api/pith-number/D2K2NMBKWV7R6Z3BVYM3FY7HDI/graph.json","events_json":"https://pith.science/api/pith-number/D2K2NMBKWV7R6Z3BVYM3FY7HDI/events.json","paper":"https://pith.science/paper/D2K2NMBK"},"agent_actions":{"view_html":"https://pith.science/pith/D2K2NMBKWV7R6Z3BVYM3FY7HDI","download_json":"https://pith.science/pith/D2K2NMBKWV7R6Z3BVYM3FY7HDI.json","view_paper":"https://pith.science/paper/D2K2NMBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10018&json=true","fetch_graph":"https://pith.science/api/pith-number/D2K2NMBKWV7R6Z3BVYM3FY7HDI/graph.json","fetch_events":"https://pith.science/api/pith-number/D2K2NMBKWV7R6Z3BVYM3FY7HDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D2K2NMBKWV7R6Z3BVYM3FY7HDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D2K2NMBKWV7R6Z3BVYM3FY7HDI/action/storage_attestation","attest_author":"https://pith.science/pith/D2K2NMBKWV7R6Z3BVYM3FY7HDI/action/author_attestation","sign_citation":"https://pith.science/pith/D2K2NMBKWV7R6Z3BVYM3FY7HDI/action/citation_signature","submit_replication":"https://pith.science/pith/D2K2NMBKWV7R6Z3BVYM3FY7HDI/action/replication_record"}},"created_at":"2026-07-05T10:02:15.308139+00:00","updated_at":"2026-07-05T10:02:15.308139+00:00"}