{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7GIT4I6P7QSYPMDQDBFDGMVBEH","short_pith_number":"pith:7GIT4I6P","schema_version":"1.0","canonical_sha256":"f9913e23cffc2587b070184a3332a121f278fcf37f58733a632776eeedb0678c","source":{"kind":"arxiv","id":"2403.06976","version":1},"attestation_state":"computed","paper":{"title":"BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qiang Xu, Xian Liu, Xintao Wang, Xuan Ju, Ying Shan, Yuxuan Bian","submitted_at":"2024-03-11T17:59:31Z","abstract_excerpt":"Image inpainting, the process of restoring corrupted images, has seen significant advancements with the advent of diffusion models (DMs). Despite these advancements, current DM adaptations for inpainting, which involve modifications to the sampling strategy or the development of inpainting-specific DMs, frequently suffer from semantic inconsistencies and reduced image quality. Addressing these challenges, our work introduces a novel paradigm: the division of masked image features and noisy latent into separate branches. This division dramatically diminishes the model's learning load, facilitat"},"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":"2403.06976","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T17:59:31Z","cross_cats_sorted":[],"title_canon_sha256":"56f86f26f589a7171f0be90b01f7b93df88e120ac414c34f1afbf378b88b9d62","abstract_canon_sha256":"a668ecefddf5f29446cb0eb68950d1f4992785a1a3aaf0efdcbe3bd13e3b4227"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:45.386391Z","signature_b64":"1aNdHmR81TLtNKhIulcfbAcCQfgLsv4ud156kElIAiJOWgHY0yW34H7yNGd2ntTfaoQOEx6nXhi0rIkbzELsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9913e23cffc2587b070184a3332a121f278fcf37f58733a632776eeedb0678c","last_reissued_at":"2026-07-05T07:54:45.385967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:45.385967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qiang Xu, Xian Liu, Xintao Wang, Xuan Ju, Ying Shan, Yuxuan Bian","submitted_at":"2024-03-11T17:59:31Z","abstract_excerpt":"Image inpainting, the process of restoring corrupted images, has seen significant advancements with the advent of diffusion models (DMs). Despite these advancements, current DM adaptations for inpainting, which involve modifications to the sampling strategy or the development of inpainting-specific DMs, frequently suffer from semantic inconsistencies and reduced image quality. Addressing these challenges, our work introduces a novel paradigm: the division of masked image features and noisy latent into separate branches. This division dramatically diminishes the model's learning load, facilitat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06976","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/2403.06976/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":"2403.06976","created_at":"2026-07-05T07:54:45.386038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.06976v1","created_at":"2026-07-05T07:54:45.386038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06976","created_at":"2026-07-05T07:54:45.386038+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GIT4I6P7QSY","created_at":"2026-07-05T07:54:45.386038+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GIT4I6P7QSYPMDQ","created_at":"2026-07-05T07:54:45.386038+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GIT4I6P","created_at":"2026-07-05T07:54:45.386038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26944","citing_title":"Object Pose and Shape Estimation for Grasping: Does it Work?","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7GIT4I6P7QSYPMDQDBFDGMVBEH","json":"https://pith.science/pith/7GIT4I6P7QSYPMDQDBFDGMVBEH.json","graph_json":"https://pith.science/api/pith-number/7GIT4I6P7QSYPMDQDBFDGMVBEH/graph.json","events_json":"https://pith.science/api/pith-number/7GIT4I6P7QSYPMDQDBFDGMVBEH/events.json","paper":"https://pith.science/paper/7GIT4I6P"},"agent_actions":{"view_html":"https://pith.science/pith/7GIT4I6P7QSYPMDQDBFDGMVBEH","download_json":"https://pith.science/pith/7GIT4I6P7QSYPMDQDBFDGMVBEH.json","view_paper":"https://pith.science/paper/7GIT4I6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.06976&json=true","fetch_graph":"https://pith.science/api/pith-number/7GIT4I6P7QSYPMDQDBFDGMVBEH/graph.json","fetch_events":"https://pith.science/api/pith-number/7GIT4I6P7QSYPMDQDBFDGMVBEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GIT4I6P7QSYPMDQDBFDGMVBEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GIT4I6P7QSYPMDQDBFDGMVBEH/action/storage_attestation","attest_author":"https://pith.science/pith/7GIT4I6P7QSYPMDQDBFDGMVBEH/action/author_attestation","sign_citation":"https://pith.science/pith/7GIT4I6P7QSYPMDQDBFDGMVBEH/action/citation_signature","submit_replication":"https://pith.science/pith/7GIT4I6P7QSYPMDQDBFDGMVBEH/action/replication_record"}},"created_at":"2026-07-05T07:54:45.386038+00:00","updated_at":"2026-07-05T07:54:45.386038+00:00"}