{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WA5UWTGZSET7Y6CHZMLNBH3SIW","short_pith_number":"pith:WA5UWTGZ","schema_version":"1.0","canonical_sha256":"b03b4b4cd99127fc7847cb16d09f724597550d16d82b85c94b7a19573580459b","source":{"kind":"arxiv","id":"2406.16531","version":2},"attestation_state":"computed","paper":{"title":"GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hailin Hu, Hanting Chen, Jie Hu, Jie Yang, Mingjian Zhu, Qiangyu Yan, Quan Zhang, Simiao Li, Wei Li, Wei Liu, Xudong Huang, Yirui Chen","submitted_at":"2024-06-24T11:10:41Z","abstract_excerpt":"The extraordinary ability of generative models emerges as a new trend in image editing and generating realistic images, posing a serious threat to the trustworthiness of multimedia data and driving the research of image manipulation detection and location (IMDL). However, the lack of a large-scale data foundation makes the IMDL task unattainable. In this paper, we build a local manipulation data generation pipeline that integrates the powerful capabilities of SAM, LLM, and generative models. Upon this basis, we propose the GIM dataset, which has the following advantages: 1) Large scale, GIM in"},"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":"2406.16531","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-24T11:10:41Z","cross_cats_sorted":[],"title_canon_sha256":"6f490bdab8522e8bbf435f34c37792a1b43ad20572b06959501ff0c4a08e5898","abstract_canon_sha256":"a3e33d0bd0768015dc20ec128fdf9e935c58941f42d481ec2a0ce1ee567e5aaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:48.867578Z","signature_b64":"hCZUNbTT1NnpVZlqtGrX8AcuZmy3xBTyCFtnctz+NCST6YkmJEx73pbMStfQArh0d4qh6Yiryd2WfTQ70LxvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b03b4b4cd99127fc7847cb16d09f724597550d16d82b85c94b7a19573580459b","last_reissued_at":"2026-07-05T09:59:48.867021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:48.867021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hailin Hu, Hanting Chen, Jie Hu, Jie Yang, Mingjian Zhu, Qiangyu Yan, Quan Zhang, Simiao Li, Wei Li, Wei Liu, Xudong Huang, Yirui Chen","submitted_at":"2024-06-24T11:10:41Z","abstract_excerpt":"The extraordinary ability of generative models emerges as a new trend in image editing and generating realistic images, posing a serious threat to the trustworthiness of multimedia data and driving the research of image manipulation detection and location (IMDL). However, the lack of a large-scale data foundation makes the IMDL task unattainable. In this paper, we build a local manipulation data generation pipeline that integrates the powerful capabilities of SAM, LLM, and generative models. Upon this basis, we propose the GIM dataset, which has the following advantages: 1) Large scale, GIM in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16531","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/2406.16531/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":"2406.16531","created_at":"2026-07-05T09:59:48.867091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16531v2","created_at":"2026-07-05T09:59:48.867091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16531","created_at":"2026-07-05T09:59:48.867091+00:00"},{"alias_kind":"pith_short_12","alias_value":"WA5UWTGZSET7","created_at":"2026-07-05T09:59:48.867091+00:00"},{"alias_kind":"pith_short_16","alias_value":"WA5UWTGZSET7Y6CH","created_at":"2026-07-05T09:59:48.867091+00:00"},{"alias_kind":"pith_short_8","alias_value":"WA5UWTGZ","created_at":"2026-07-05T09:59:48.867091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.18361","citing_title":"COCO-Inpaint: A Benchmark for Detecting and Localizing Inpainting-Based Image Manipulations","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WA5UWTGZSET7Y6CHZMLNBH3SIW","json":"https://pith.science/pith/WA5UWTGZSET7Y6CHZMLNBH3SIW.json","graph_json":"https://pith.science/api/pith-number/WA5UWTGZSET7Y6CHZMLNBH3SIW/graph.json","events_json":"https://pith.science/api/pith-number/WA5UWTGZSET7Y6CHZMLNBH3SIW/events.json","paper":"https://pith.science/paper/WA5UWTGZ"},"agent_actions":{"view_html":"https://pith.science/pith/WA5UWTGZSET7Y6CHZMLNBH3SIW","download_json":"https://pith.science/pith/WA5UWTGZSET7Y6CHZMLNBH3SIW.json","view_paper":"https://pith.science/paper/WA5UWTGZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16531&json=true","fetch_graph":"https://pith.science/api/pith-number/WA5UWTGZSET7Y6CHZMLNBH3SIW/graph.json","fetch_events":"https://pith.science/api/pith-number/WA5UWTGZSET7Y6CHZMLNBH3SIW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WA5UWTGZSET7Y6CHZMLNBH3SIW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WA5UWTGZSET7Y6CHZMLNBH3SIW/action/storage_attestation","attest_author":"https://pith.science/pith/WA5UWTGZSET7Y6CHZMLNBH3SIW/action/author_attestation","sign_citation":"https://pith.science/pith/WA5UWTGZSET7Y6CHZMLNBH3SIW/action/citation_signature","submit_replication":"https://pith.science/pith/WA5UWTGZSET7Y6CHZMLNBH3SIW/action/replication_record"}},"created_at":"2026-07-05T09:59:48.867091+00:00","updated_at":"2026-07-05T09:59:48.867091+00:00"}