{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6MBVS5OXRPG6UW3J2RXWFI4UEX","short_pith_number":"pith:6MBVS5OX","schema_version":"1.0","canonical_sha256":"f3035975d78bcdea5b69d46f62a39425f14133d057570e4b51335c84b0a11edb","source":{"kind":"arxiv","id":"2412.14816","version":3},"attestation_state":"computed","paper":{"title":"TextSleuth: Towards Explainable Tampered Text Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baihan Yu, Chenfan Qu, Haoxing Chen, Jian Liu, Jingjing Liu, Lianwen Jin, Weiqiang Wang","submitted_at":"2024-12-19T13:10:03Z","abstract_excerpt":"Recently, tampered text detection has attracted increasing attention due to its essential role in information security. Although existing methods can detect the tampered text region, the interpretation of such detection remains unclear, making the prediction unreliable. To address this problem, we propose to explain the basis of tampered text detection with natural language via large multimodal models. To fill the data gap for this task, we propose a large-scale, comprehensive dataset, ETTD, which contains both pixel-level annotations for tampered text region and natural language annotations d"},"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":"2412.14816","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T13:10:03Z","cross_cats_sorted":[],"title_canon_sha256":"12461bf24400e5394996cb18e6ec58c09ce392d6ce04a9f68b7d3d2cb9a70907","abstract_canon_sha256":"bdbab62b422300bd400f1fedb79b0939277533510b821d253e3de9617709321b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:18.686542Z","signature_b64":"OKRUXZVZ46P0S7eNrH9g139xORqkHDrvH7RUfUxpxsXt+5AH5GBTgjcEIvpaMYxBQW4CMIKVY5Lns3r/FPj9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3035975d78bcdea5b69d46f62a39425f14133d057570e4b51335c84b0a11edb","last_reissued_at":"2026-07-05T10:01:18.686042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:18.686042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextSleuth: Towards Explainable Tampered Text Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baihan Yu, Chenfan Qu, Haoxing Chen, Jian Liu, Jingjing Liu, Lianwen Jin, Weiqiang Wang","submitted_at":"2024-12-19T13:10:03Z","abstract_excerpt":"Recently, tampered text detection has attracted increasing attention due to its essential role in information security. Although existing methods can detect the tampered text region, the interpretation of such detection remains unclear, making the prediction unreliable. To address this problem, we propose to explain the basis of tampered text detection with natural language via large multimodal models. To fill the data gap for this task, we propose a large-scale, comprehensive dataset, ETTD, which contains both pixel-level annotations for tampered text region and natural language annotations d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14816","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/2412.14816/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":"2412.14816","created_at":"2026-07-05T10:01:18.686107+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14816v3","created_at":"2026-07-05T10:01:18.686107+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14816","created_at":"2026-07-05T10:01:18.686107+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MBVS5OXRPG6","created_at":"2026-07-05T10:01:18.686107+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MBVS5OXRPG6UW3J","created_at":"2026-07-05T10:01:18.686107+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MBVS5OX","created_at":"2026-07-05T10:01:18.686107+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16080","citing_title":"ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14091","citing_title":"Venus-DeFakerOne: Unified Fake Image Detection & Localization","ref_index":232,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02694","citing_title":"DocShield: Towards AI Document Safety via Evidence-Grounded Agentic Reasoning","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6MBVS5OXRPG6UW3J2RXWFI4UEX","json":"https://pith.science/pith/6MBVS5OXRPG6UW3J2RXWFI4UEX.json","graph_json":"https://pith.science/api/pith-number/6MBVS5OXRPG6UW3J2RXWFI4UEX/graph.json","events_json":"https://pith.science/api/pith-number/6MBVS5OXRPG6UW3J2RXWFI4UEX/events.json","paper":"https://pith.science/paper/6MBVS5OX"},"agent_actions":{"view_html":"https://pith.science/pith/6MBVS5OXRPG6UW3J2RXWFI4UEX","download_json":"https://pith.science/pith/6MBVS5OXRPG6UW3J2RXWFI4UEX.json","view_paper":"https://pith.science/paper/6MBVS5OX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14816&json=true","fetch_graph":"https://pith.science/api/pith-number/6MBVS5OXRPG6UW3J2RXWFI4UEX/graph.json","fetch_events":"https://pith.science/api/pith-number/6MBVS5OXRPG6UW3J2RXWFI4UEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MBVS5OXRPG6UW3J2RXWFI4UEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MBVS5OXRPG6UW3J2RXWFI4UEX/action/storage_attestation","attest_author":"https://pith.science/pith/6MBVS5OXRPG6UW3J2RXWFI4UEX/action/author_attestation","sign_citation":"https://pith.science/pith/6MBVS5OXRPG6UW3J2RXWFI4UEX/action/citation_signature","submit_replication":"https://pith.science/pith/6MBVS5OXRPG6UW3J2RXWFI4UEX/action/replication_record"}},"created_at":"2026-07-05T10:01:18.686107+00:00","updated_at":"2026-07-05T10:01:18.686107+00:00"}