{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FFFU3RUO6NDSUJYU6Y6MILYZQE","short_pith_number":"pith:FFFU3RUO","schema_version":"1.0","canonical_sha256":"294b4dc68ef3472a2714f63cc42f19812f5ca5b74c41662cc5952e8d55c9651b","source":{"kind":"arxiv","id":"2312.06934","version":2},"attestation_state":"computed","paper":{"title":"Toward Real Text Manipulation Detection: New Dataset and New Solution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongliang Luo, Jishen Zeng, Rui Yang, Xiang Bai, Xianjin Liu, Yuliang Liu, Yu Zhou","submitted_at":"2023-12-12T02:10:16Z","abstract_excerpt":"With the surge in realistic text tampering, detecting fraudulent text in images has gained prominence for maintaining information security. However, the high costs associated with professional text manipulation and annotation limit the availability of real-world datasets, with most relying on synthetic tampering, which inadequately replicates real-world tampering attributes. To address this issue, we present the Real Text Manipulation (RTM) dataset, encompassing 14,250 text images, which include 5,986 manually and 5,258 automatically tampered images, created using a variety of techniques, alon"},"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":"2312.06934","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T02:10:16Z","cross_cats_sorted":[],"title_canon_sha256":"8b0578ea89c835d3e54ff3080af62f0040f7ea02db6010f194884e3a6ee62b81","abstract_canon_sha256":"cfe2a6dee8c9ba56314df703a326f0f099a2387cbb6d75d1a703b2bfd147be44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:25.305183Z","signature_b64":"HNo2FjUcmpWR4yLn0eAHVZgFPH3UY18Bkf8QkUU6oX5VeCFzcVbiVR/mLNP3hz+ZuY37ELNveKD9y8CNLElLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"294b4dc68ef3472a2714f63cc42f19812f5ca5b74c41662cc5952e8d55c9651b","last_reissued_at":"2026-07-05T07:36:25.304740Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:25.304740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Real Text Manipulation Detection: New Dataset and New Solution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongliang Luo, Jishen Zeng, Rui Yang, Xiang Bai, Xianjin Liu, Yuliang Liu, Yu Zhou","submitted_at":"2023-12-12T02:10:16Z","abstract_excerpt":"With the surge in realistic text tampering, detecting fraudulent text in images has gained prominence for maintaining information security. However, the high costs associated with professional text manipulation and annotation limit the availability of real-world datasets, with most relying on synthetic tampering, which inadequately replicates real-world tampering attributes. To address this issue, we present the Real Text Manipulation (RTM) dataset, encompassing 14,250 text images, which include 5,986 manually and 5,258 automatically tampered images, created using a variety of techniques, alon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06934","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/2312.06934/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":"2312.06934","created_at":"2026-07-05T07:36:25.304800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06934v2","created_at":"2026-07-05T07:36:25.304800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06934","created_at":"2026-07-05T07:36:25.304800+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFFU3RUO6NDS","created_at":"2026-07-05T07:36:25.304800+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFFU3RUO6NDSUJYU","created_at":"2026-07-05T07:36:25.304800+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFFU3RUO","created_at":"2026-07-05T07:36:25.304800+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25212","citing_title":"Noncrossing Duality and the Geometry of Positive Tropical Linear Spaces","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25213","citing_title":"When the Forger Is the Judge: GPT-Image-2 Cannot Recognize Its Own Faked Documents","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFFU3RUO6NDSUJYU6Y6MILYZQE","json":"https://pith.science/pith/FFFU3RUO6NDSUJYU6Y6MILYZQE.json","graph_json":"https://pith.science/api/pith-number/FFFU3RUO6NDSUJYU6Y6MILYZQE/graph.json","events_json":"https://pith.science/api/pith-number/FFFU3RUO6NDSUJYU6Y6MILYZQE/events.json","paper":"https://pith.science/paper/FFFU3RUO"},"agent_actions":{"view_html":"https://pith.science/pith/FFFU3RUO6NDSUJYU6Y6MILYZQE","download_json":"https://pith.science/pith/FFFU3RUO6NDSUJYU6Y6MILYZQE.json","view_paper":"https://pith.science/paper/FFFU3RUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06934&json=true","fetch_graph":"https://pith.science/api/pith-number/FFFU3RUO6NDSUJYU6Y6MILYZQE/graph.json","fetch_events":"https://pith.science/api/pith-number/FFFU3RUO6NDSUJYU6Y6MILYZQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFFU3RUO6NDSUJYU6Y6MILYZQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFFU3RUO6NDSUJYU6Y6MILYZQE/action/storage_attestation","attest_author":"https://pith.science/pith/FFFU3RUO6NDSUJYU6Y6MILYZQE/action/author_attestation","sign_citation":"https://pith.science/pith/FFFU3RUO6NDSUJYU6Y6MILYZQE/action/citation_signature","submit_replication":"https://pith.science/pith/FFFU3RUO6NDSUJYU6Y6MILYZQE/action/replication_record"}},"created_at":"2026-07-05T07:36:25.304800+00:00","updated_at":"2026-07-05T07:36:25.304800+00:00"}