{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VIMTSFQ6GP34CJQ7KHRBT44GRH","short_pith_number":"pith:VIMTSFQ6","schema_version":"1.0","canonical_sha256":"aa1939161e33f7c1261f51e219f38689e075d646962bc9ad4730eacfb8b86451","source":{"kind":"arxiv","id":"2501.08225","version":1},"attestation_state":"computed","paper":{"title":"FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Xu, Hui Li, Wangmeng Zuo, Xinpeng Zhou, Yabo Zhang, Yihan Zeng","submitted_at":"2025-01-14T16:09:16Z","abstract_excerpt":"Interactive image editing allows users to modify images through visual interaction operations such as drawing, clicking, and dragging. Existing methods construct such supervision signals from videos, as they capture how objects change with various physical interactions. However, these models are usually built upon text-to-image diffusion models, so necessitate (i) massive training samples and (ii) an additional reference encoder to learn real-world dynamics and visual consistency. In this paper, we reformulate this task as an image-to-video generation problem, so that inherit powerful video di"},"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":"2501.08225","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T16:09:16Z","cross_cats_sorted":[],"title_canon_sha256":"d60cf6dd1945a1ec10562d7a0db5a5fae7cd839c9477e71d469b5e09e40ac36f","abstract_canon_sha256":"33760554a68ef2fe79ce78dee2612765f6d556ef6c5f7730bd5cf3739aa885fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:57.871209Z","signature_b64":"4n+saC7RnoB8q/9zSynJgqUEow7KRaaNyqmNjySe2Cv8lSMmUxZw7WXeHH1ftp2ajf1qoY43Idy0VP+f1gnWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa1939161e33f7c1261f51e219f38689e075d646962bc9ad4730eacfb8b86451","last_reissued_at":"2026-07-05T10:00:57.870877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:57.870877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hang Xu, Hui Li, Wangmeng Zuo, Xinpeng Zhou, Yabo Zhang, Yihan Zeng","submitted_at":"2025-01-14T16:09:16Z","abstract_excerpt":"Interactive image editing allows users to modify images through visual interaction operations such as drawing, clicking, and dragging. Existing methods construct such supervision signals from videos, as they capture how objects change with various physical interactions. However, these models are usually built upon text-to-image diffusion models, so necessitate (i) massive training samples and (ii) an additional reference encoder to learn real-world dynamics and visual consistency. In this paper, we reformulate this task as an image-to-video generation problem, so that inherit powerful video di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08225","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/2501.08225/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":"2501.08225","created_at":"2026-07-05T10:00:57.870926+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08225v1","created_at":"2026-07-05T10:00:57.870926+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08225","created_at":"2026-07-05T10:00:57.870926+00:00"},{"alias_kind":"pith_short_12","alias_value":"VIMTSFQ6GP34","created_at":"2026-07-05T10:00:57.870926+00:00"},{"alias_kind":"pith_short_16","alias_value":"VIMTSFQ6GP34CJQ7","created_at":"2026-07-05T10:00:57.870926+00:00"},{"alias_kind":"pith_short_8","alias_value":"VIMTSFQ6","created_at":"2026-07-05T10:00:57.870926+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07986","citing_title":"Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VIMTSFQ6GP34CJQ7KHRBT44GRH","json":"https://pith.science/pith/VIMTSFQ6GP34CJQ7KHRBT44GRH.json","graph_json":"https://pith.science/api/pith-number/VIMTSFQ6GP34CJQ7KHRBT44GRH/graph.json","events_json":"https://pith.science/api/pith-number/VIMTSFQ6GP34CJQ7KHRBT44GRH/events.json","paper":"https://pith.science/paper/VIMTSFQ6"},"agent_actions":{"view_html":"https://pith.science/pith/VIMTSFQ6GP34CJQ7KHRBT44GRH","download_json":"https://pith.science/pith/VIMTSFQ6GP34CJQ7KHRBT44GRH.json","view_paper":"https://pith.science/paper/VIMTSFQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08225&json=true","fetch_graph":"https://pith.science/api/pith-number/VIMTSFQ6GP34CJQ7KHRBT44GRH/graph.json","fetch_events":"https://pith.science/api/pith-number/VIMTSFQ6GP34CJQ7KHRBT44GRH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VIMTSFQ6GP34CJQ7KHRBT44GRH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VIMTSFQ6GP34CJQ7KHRBT44GRH/action/storage_attestation","attest_author":"https://pith.science/pith/VIMTSFQ6GP34CJQ7KHRBT44GRH/action/author_attestation","sign_citation":"https://pith.science/pith/VIMTSFQ6GP34CJQ7KHRBT44GRH/action/citation_signature","submit_replication":"https://pith.science/pith/VIMTSFQ6GP34CJQ7KHRBT44GRH/action/replication_record"}},"created_at":"2026-07-05T10:00:57.870926+00:00","updated_at":"2026-07-05T10:00:57.870926+00:00"}