{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WESMG3ARWUSPXEARRHBCOVNGNL","short_pith_number":"pith:WESMG3AR","schema_version":"1.0","canonical_sha256":"b124c36c11b524fb901189c22755a66ad439698d1be814159fc25e653c27391c","source":{"kind":"arxiv","id":"2606.23270","version":1},"attestation_state":"computed","paper":{"title":"BoxCtrl: 3D-Aware Visual Prompting for Geometric Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feifei Wang, Jing Liao, Shiyuan Yang, Xiaoyu Li","submitted_at":"2026-06-22T12:49:29Z","abstract_excerpt":"As instruction-based editing models and multimodal large language models advance, diverse image editing tasks have become feasible. However, achieving precise and consistent geometric image editing, such as translating, scaling, and rotating in 3D space, remains a major challenge. In this work, we introduce BoxCtrl, a 3D-aware visual prompting framework. Unlike text-only or coarse 2D-guided approaches, our method introduces informative RGB 3D bounding boxes projected onto 2D images as visual prompts. The three orthogonal faces of each box are painted with distinct RGB colors, simultaneously en"},"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":"2606.23270","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-22T12:49:29Z","cross_cats_sorted":[],"title_canon_sha256":"72bdeeac78b1e3a491fa41b4d28a6854704ea32d234b1c858f48cd1c2ea0e73c","abstract_canon_sha256":"4e90a0d5e2f69d56912d6645e11f8264fd642981b990b03e99e34a13910c2bf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:14:15.339290Z","signature_b64":"mVikstv22g5JCx9bkwlSzYLlwDw11+Dm4CshHkF/ueZ/MCK7gfmjRAOlWv269EtJQKmP27uurm18h0uHa1BKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b124c36c11b524fb901189c22755a66ad439698d1be814159fc25e653c27391c","last_reissued_at":"2026-06-23T03:14:15.338922Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:14:15.338922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BoxCtrl: 3D-Aware Visual Prompting for Geometric Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feifei Wang, Jing Liao, Shiyuan Yang, Xiaoyu Li","submitted_at":"2026-06-22T12:49:29Z","abstract_excerpt":"As instruction-based editing models and multimodal large language models advance, diverse image editing tasks have become feasible. However, achieving precise and consistent geometric image editing, such as translating, scaling, and rotating in 3D space, remains a major challenge. In this work, we introduce BoxCtrl, a 3D-aware visual prompting framework. Unlike text-only or coarse 2D-guided approaches, our method introduces informative RGB 3D bounding boxes projected onto 2D images as visual prompts. The three orthogonal faces of each box are painted with distinct RGB colors, simultaneously en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.23270","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/2606.23270/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":"2606.23270","created_at":"2026-06-23T03:14:15.338978+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.23270v1","created_at":"2026-06-23T03:14:15.338978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.23270","created_at":"2026-06-23T03:14:15.338978+00:00"},{"alias_kind":"pith_short_12","alias_value":"WESMG3ARWUSP","created_at":"2026-06-23T03:14:15.338978+00:00"},{"alias_kind":"pith_short_16","alias_value":"WESMG3ARWUSPXEAR","created_at":"2026-06-23T03:14:15.338978+00:00"},{"alias_kind":"pith_short_8","alias_value":"WESMG3AR","created_at":"2026-06-23T03:14:15.338978+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WESMG3ARWUSPXEARRHBCOVNGNL","json":"https://pith.science/pith/WESMG3ARWUSPXEARRHBCOVNGNL.json","graph_json":"https://pith.science/api/pith-number/WESMG3ARWUSPXEARRHBCOVNGNL/graph.json","events_json":"https://pith.science/api/pith-number/WESMG3ARWUSPXEARRHBCOVNGNL/events.json","paper":"https://pith.science/paper/WESMG3AR"},"agent_actions":{"view_html":"https://pith.science/pith/WESMG3ARWUSPXEARRHBCOVNGNL","download_json":"https://pith.science/pith/WESMG3ARWUSPXEARRHBCOVNGNL.json","view_paper":"https://pith.science/paper/WESMG3AR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.23270&json=true","fetch_graph":"https://pith.science/api/pith-number/WESMG3ARWUSPXEARRHBCOVNGNL/graph.json","fetch_events":"https://pith.science/api/pith-number/WESMG3ARWUSPXEARRHBCOVNGNL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WESMG3ARWUSPXEARRHBCOVNGNL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WESMG3ARWUSPXEARRHBCOVNGNL/action/storage_attestation","attest_author":"https://pith.science/pith/WESMG3ARWUSPXEARRHBCOVNGNL/action/author_attestation","sign_citation":"https://pith.science/pith/WESMG3ARWUSPXEARRHBCOVNGNL/action/citation_signature","submit_replication":"https://pith.science/pith/WESMG3ARWUSPXEARRHBCOVNGNL/action/replication_record"}},"created_at":"2026-06-23T03:14:15.338978+00:00","updated_at":"2026-06-23T03:14:15.338978+00:00"}