{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EQSNC6JYHUTASDBCZTGSYEOX2H","short_pith_number":"pith:EQSNC6JY","schema_version":"1.0","canonical_sha256":"2424d179383d26090c22cccd2c11d7d1cc9c2630692331110dbaeb1197afa006","source":{"kind":"arxiv","id":"2504.20438","version":2},"attestation_state":"computed","paper":{"title":"PixelHacker: Image Inpainting with Structural and Semantic Consistency","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kangsheng Duan, Wenyu Liu, Xiaohu Ruan, Xiaolei Shen, Xiaoxin Chen, Xinggang Wang, Zhifeng Ding, Ziyang Xu","submitted_at":"2025-04-29T05:28:36Z","abstract_excerpt":"Image inpainting is a fundamental research area between image editing and image generation. Recent state-of-the-art (SOTA) methods have explored novel attention mechanisms, lightweight architectures, and context-aware modeling, demonstrating impressive performance. However, they often struggle with complex structure (e.g., texture, shape, spatial relations) and semantics (e.g., color consistency, object restoration, and logical correctness), leading to artifacts and inappropriate generation. To address this challenge, we design a simple yet effective inpainting paradigm called latent categorie"},"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":"2504.20438","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T05:28:36Z","cross_cats_sorted":[],"title_canon_sha256":"16b824e185638057ced11db197be1987e843274015f1c1b67688254353dfcd16","abstract_canon_sha256":"6c6ba339a98673d68170230285b23a2b9b81eb7964e90cf7dece5b78be032151"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:18.881028Z","signature_b64":"wGo5XrjgJp4ASO7jFv4d/ZxGhTMRRiEbxJHNKrIbR6/k1Y08hE0GcksBKtqSzz3GbZ7RorJXfbNDS30PAIpJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2424d179383d26090c22cccd2c11d7d1cc9c2630692331110dbaeb1197afa006","last_reissued_at":"2026-07-05T10:56:18.880534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:18.880534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PixelHacker: Image Inpainting with Structural and Semantic Consistency","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kangsheng Duan, Wenyu Liu, Xiaohu Ruan, Xiaolei Shen, Xiaoxin Chen, Xinggang Wang, Zhifeng Ding, Ziyang Xu","submitted_at":"2025-04-29T05:28:36Z","abstract_excerpt":"Image inpainting is a fundamental research area between image editing and image generation. Recent state-of-the-art (SOTA) methods have explored novel attention mechanisms, lightweight architectures, and context-aware modeling, demonstrating impressive performance. However, they often struggle with complex structure (e.g., texture, shape, spatial relations) and semantics (e.g., color consistency, object restoration, and logical correctness), leading to artifacts and inappropriate generation. To address this challenge, we design a simple yet effective inpainting paradigm called latent categorie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20438","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/2504.20438/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":"2504.20438","created_at":"2026-07-05T10:56:18.880598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20438v2","created_at":"2026-07-05T10:56:18.880598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20438","created_at":"2026-07-05T10:56:18.880598+00:00"},{"alias_kind":"pith_short_12","alias_value":"EQSNC6JYHUTA","created_at":"2026-07-05T10:56:18.880598+00:00"},{"alias_kind":"pith_short_16","alias_value":"EQSNC6JYHUTASDBC","created_at":"2026-07-05T10:56:18.880598+00:00"},{"alias_kind":"pith_short_8","alias_value":"EQSNC6JY","created_at":"2026-07-05T10:56:18.880598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19195","citing_title":"Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14461","citing_title":"ClickRemoval: An Interactive Open-Source Tool for Object Removal in Diffusion Models","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EQSNC6JYHUTASDBCZTGSYEOX2H","json":"https://pith.science/pith/EQSNC6JYHUTASDBCZTGSYEOX2H.json","graph_json":"https://pith.science/api/pith-number/EQSNC6JYHUTASDBCZTGSYEOX2H/graph.json","events_json":"https://pith.science/api/pith-number/EQSNC6JYHUTASDBCZTGSYEOX2H/events.json","paper":"https://pith.science/paper/EQSNC6JY"},"agent_actions":{"view_html":"https://pith.science/pith/EQSNC6JYHUTASDBCZTGSYEOX2H","download_json":"https://pith.science/pith/EQSNC6JYHUTASDBCZTGSYEOX2H.json","view_paper":"https://pith.science/paper/EQSNC6JY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20438&json=true","fetch_graph":"https://pith.science/api/pith-number/EQSNC6JYHUTASDBCZTGSYEOX2H/graph.json","fetch_events":"https://pith.science/api/pith-number/EQSNC6JYHUTASDBCZTGSYEOX2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EQSNC6JYHUTASDBCZTGSYEOX2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EQSNC6JYHUTASDBCZTGSYEOX2H/action/storage_attestation","attest_author":"https://pith.science/pith/EQSNC6JYHUTASDBCZTGSYEOX2H/action/author_attestation","sign_citation":"https://pith.science/pith/EQSNC6JYHUTASDBCZTGSYEOX2H/action/citation_signature","submit_replication":"https://pith.science/pith/EQSNC6JYHUTASDBCZTGSYEOX2H/action/replication_record"}},"created_at":"2026-07-05T10:56:18.880598+00:00","updated_at":"2026-07-05T10:56:18.880598+00:00"}