{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5D3DXDPWWNDFAV35VZH2PF7XRW","short_pith_number":"pith:5D3DXDPW","schema_version":"1.0","canonical_sha256":"e8f63b8df6b34650577dae4fa797f78dab01e4b3e958ec8116917c9d14644985","source":{"kind":"arxiv","id":"2403.18818","version":1},"attestation_state":"computed","paper":{"title":"ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Rav-Acha, Daniel Winter, Matan Cohen, Shlomi Fruchter, Yael Pritch, Yedid Hoshen","submitted_at":"2024-03-27T17:59:52Z","abstract_excerpt":"Diffusion models have revolutionized image editing but often generate images that violate physical laws, particularly the effects of objects on the scene, e.g., occlusions, shadows, and reflections. By analyzing the limitations of self-supervised approaches, we propose a practical solution centered on a \\q{counterfactual} dataset. Our method involves capturing a scene before and after removing a single object, while minimizing other changes. By fine-tuning a diffusion model on this dataset, we are able to not only remove objects but also their effects on the scene. However, we find that applyi"},"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":"2403.18818","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-27T17:59:52Z","cross_cats_sorted":[],"title_canon_sha256":"c568b05ba3c334cfeedf27f2e1614b330cd85be341300331819d0fd4cabfed68","abstract_canon_sha256":"368bb8f301feee60cdc86890d24d5603f4a724051169bc70fb0440cd88b9d434"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:27.546772Z","signature_b64":"HApP3Kebu1J3DY1WfXQlsuiggGWnUHoYlDlMUD24Obpe31UegwJHtiF+vfpv9N13NLga9xWdz7B6W1WQePdkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8f63b8df6b34650577dae4fa797f78dab01e4b3e958ec8116917c9d14644985","last_reissued_at":"2026-07-05T08:01:27.546243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:27.546243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ObjectDrop: Bootstrapping Counterfactuals for Photorealistic Object Removal and Insertion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Rav-Acha, Daniel Winter, Matan Cohen, Shlomi Fruchter, Yael Pritch, Yedid Hoshen","submitted_at":"2024-03-27T17:59:52Z","abstract_excerpt":"Diffusion models have revolutionized image editing but often generate images that violate physical laws, particularly the effects of objects on the scene, e.g., occlusions, shadows, and reflections. By analyzing the limitations of self-supervised approaches, we propose a practical solution centered on a \\q{counterfactual} dataset. Our method involves capturing a scene before and after removing a single object, while minimizing other changes. By fine-tuning a diffusion model on this dataset, we are able to not only remove objects but also their effects on the scene. However, we find that applyi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18818","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/2403.18818/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":"2403.18818","created_at":"2026-07-05T08:01:27.546300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.18818v1","created_at":"2026-07-05T08:01:27.546300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18818","created_at":"2026-07-05T08:01:27.546300+00:00"},{"alias_kind":"pith_short_12","alias_value":"5D3DXDPWWNDF","created_at":"2026-07-05T08:01:27.546300+00:00"},{"alias_kind":"pith_short_16","alias_value":"5D3DXDPWWNDFAV35","created_at":"2026-07-05T08:01:27.546300+00:00"},{"alias_kind":"pith_short_8","alias_value":"5D3DXDPW","created_at":"2026-07-05T08:01:27.546300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23058","citing_title":"Reference-Guided Diffusion Inpainting For Multimodal Counterfactual Generation","ref_index":84,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5D3DXDPWWNDFAV35VZH2PF7XRW","json":"https://pith.science/pith/5D3DXDPWWNDFAV35VZH2PF7XRW.json","graph_json":"https://pith.science/api/pith-number/5D3DXDPWWNDFAV35VZH2PF7XRW/graph.json","events_json":"https://pith.science/api/pith-number/5D3DXDPWWNDFAV35VZH2PF7XRW/events.json","paper":"https://pith.science/paper/5D3DXDPW"},"agent_actions":{"view_html":"https://pith.science/pith/5D3DXDPWWNDFAV35VZH2PF7XRW","download_json":"https://pith.science/pith/5D3DXDPWWNDFAV35VZH2PF7XRW.json","view_paper":"https://pith.science/paper/5D3DXDPW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.18818&json=true","fetch_graph":"https://pith.science/api/pith-number/5D3DXDPWWNDFAV35VZH2PF7XRW/graph.json","fetch_events":"https://pith.science/api/pith-number/5D3DXDPWWNDFAV35VZH2PF7XRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5D3DXDPWWNDFAV35VZH2PF7XRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5D3DXDPWWNDFAV35VZH2PF7XRW/action/storage_attestation","attest_author":"https://pith.science/pith/5D3DXDPWWNDFAV35VZH2PF7XRW/action/author_attestation","sign_citation":"https://pith.science/pith/5D3DXDPWWNDFAV35VZH2PF7XRW/action/citation_signature","submit_replication":"https://pith.science/pith/5D3DXDPWWNDFAV35VZH2PF7XRW/action/replication_record"}},"created_at":"2026-07-05T08:01:27.546300+00:00","updated_at":"2026-07-05T08:01:27.546300+00:00"}