{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SJNKBMIEKHIEVIPPWGWSA7U5GZ","short_pith_number":"pith:SJNKBMIE","schema_version":"1.0","canonical_sha256":"925aa0b10451d04aa1efb1ad207e9d36760c8c92d9820a781927c4922e9baa1c","source":{"kind":"arxiv","id":"2501.00740","version":3},"attestation_state":"computed","paper":{"title":"RORem: Training a Robust Object Remover with Human-in-the-Loop","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Ruibin Li, Song Guo, Tao Yang","submitted_at":"2025-01-01T06:07:02Z","abstract_excerpt":"Despite the significant advancements, existing object removal methods struggle with incomplete removal, incorrect content synthesis and blurry synthesized regions, resulting in low success rates. Such issues are mainly caused by the lack of high-quality paired training data, as well as the self-supervised training paradigm adopted in these methods, which forces the model to in-paint the masked regions, leading to ambiguity between synthesizing the masked objects and restoring the background. To address these issues, we propose a semi-supervised learning strategy with human-in-the-loop to creat"},"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":"2501.00740","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-01T06:07:02Z","cross_cats_sorted":[],"title_canon_sha256":"5efb74b9321a6b63a2d7d0cfde2651270f09cdec3272d0ce0877e8ac305ab882","abstract_canon_sha256":"f51677c0d196c000a9bdb3734b8ea9125ed5286f81aea177f9678bddf4401729"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:12.599460Z","signature_b64":"QqrOS9BgoRltlxSmUlekbu1rXP1PkThTRqXJuv7F0BHfzX+yUhkwwX7SgUtI1je/0D+9MEPu7AC0dPSDIobGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"925aa0b10451d04aa1efb1ad207e9d36760c8c92d9820a781927c4922e9baa1c","last_reissued_at":"2026-07-05T10:49:12.598868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:12.598868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RORem: Training a Robust Object Remover with Human-in-the-Loop","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lei Zhang, Ruibin Li, Song Guo, Tao Yang","submitted_at":"2025-01-01T06:07:02Z","abstract_excerpt":"Despite the significant advancements, existing object removal methods struggle with incomplete removal, incorrect content synthesis and blurry synthesized regions, resulting in low success rates. Such issues are mainly caused by the lack of high-quality paired training data, as well as the self-supervised training paradigm adopted in these methods, which forces the model to in-paint the masked regions, leading to ambiguity between synthesizing the masked objects and restoring the background. To address these issues, we propose a semi-supervised learning strategy with human-in-the-loop to creat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00740","kind":"arxiv","version":3},"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/2501.00740/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":"2501.00740","created_at":"2026-07-05T10:49:12.598933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00740v3","created_at":"2026-07-05T10:49:12.598933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00740","created_at":"2026-07-05T10:49:12.598933+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJNKBMIEKHIE","created_at":"2026-07-05T10:49:12.598933+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJNKBMIEKHIEVIPP","created_at":"2026-07-05T10:49:12.598933+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJNKBMIE","created_at":"2026-07-05T10:49:12.598933+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07397","citing_title":"OmniEraser: Remove Objects and Their Effects in Images with Paired Video-Frame Data","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SJNKBMIEKHIEVIPPWGWSA7U5GZ","json":"https://pith.science/pith/SJNKBMIEKHIEVIPPWGWSA7U5GZ.json","graph_json":"https://pith.science/api/pith-number/SJNKBMIEKHIEVIPPWGWSA7U5GZ/graph.json","events_json":"https://pith.science/api/pith-number/SJNKBMIEKHIEVIPPWGWSA7U5GZ/events.json","paper":"https://pith.science/paper/SJNKBMIE"},"agent_actions":{"view_html":"https://pith.science/pith/SJNKBMIEKHIEVIPPWGWSA7U5GZ","download_json":"https://pith.science/pith/SJNKBMIEKHIEVIPPWGWSA7U5GZ.json","view_paper":"https://pith.science/paper/SJNKBMIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00740&json=true","fetch_graph":"https://pith.science/api/pith-number/SJNKBMIEKHIEVIPPWGWSA7U5GZ/graph.json","fetch_events":"https://pith.science/api/pith-number/SJNKBMIEKHIEVIPPWGWSA7U5GZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJNKBMIEKHIEVIPPWGWSA7U5GZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJNKBMIEKHIEVIPPWGWSA7U5GZ/action/storage_attestation","attest_author":"https://pith.science/pith/SJNKBMIEKHIEVIPPWGWSA7U5GZ/action/author_attestation","sign_citation":"https://pith.science/pith/SJNKBMIEKHIEVIPPWGWSA7U5GZ/action/citation_signature","submit_replication":"https://pith.science/pith/SJNKBMIEKHIEVIPPWGWSA7U5GZ/action/replication_record"}},"created_at":"2026-07-05T10:49:12.598933+00:00","updated_at":"2026-07-05T10:49:12.598933+00:00"}