{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YL22ABW6B7RO2CMHFGFTONVMH4","short_pith_number":"pith:YL22ABW6","schema_version":"1.0","canonical_sha256":"c2f5a006de0fe2ed0987298b3736ac3f31e3c24f2bacbef92daf0e4f150d1043","source":{"kind":"arxiv","id":"2505.18660","version":5},"attestation_state":"computed","paper":{"title":"So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoyuan Wu, Bei Peng, Dacheng Tao, Guangliang Cheng, Ming-Hsuan Yang, Xiangtai Li, Xiaowei Huang, Xi Yang, Zhenglin Huang","submitted_at":"2025-05-24T11:53:35Z","abstract_excerpt":"Recent advances in AI-powered generative models have enabled the creation of increasingly realistic synthetic images, posing significant risks to information integrity and public trust on social media platforms. While robust detection frameworks and diverse, large-scale datasets are essential to mitigate these risks, existing academic efforts remain limited in scope: current datasets lack the diversity, scale, and realism required for social media contexts, while detection methods struggle with generalization to unseen generative technologies. To bridge this gap, we introduce So-Fake-Set, a co"},"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":"2505.18660","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-24T11:53:35Z","cross_cats_sorted":[],"title_canon_sha256":"328477c3748364edf01922ae564b4786b73674cac924a28a60fd62de6aaa1f40","abstract_canon_sha256":"a13c00d6ef0b6ee438233035d5a9e10421726b2a97b3ab467a8b73dc6344ecaa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:25:36.814790Z","signature_b64":"tKpk5gzPyQt5+P5Pz80nGFlmEJXUvN59uCviAm/XC365bUtZ76TTrtlIc15cL6YT/j5GfuWb9UM2j1SdwgqlAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2f5a006de0fe2ed0987298b3736ac3f31e3c24f2bacbef92daf0e4f150d1043","last_reissued_at":"2026-08-03T01:25:36.813055Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:25:36.813055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baoyuan Wu, Bei Peng, Dacheng Tao, Guangliang Cheng, Ming-Hsuan Yang, Xiangtai Li, Xiaowei Huang, Xi Yang, Zhenglin Huang","submitted_at":"2025-05-24T11:53:35Z","abstract_excerpt":"Recent advances in AI-powered generative models have enabled the creation of increasingly realistic synthetic images, posing significant risks to information integrity and public trust on social media platforms. While robust detection frameworks and diverse, large-scale datasets are essential to mitigate these risks, existing academic efforts remain limited in scope: current datasets lack the diversity, scale, and realism required for social media contexts, while detection methods struggle with generalization to unseen generative technologies. To bridge this gap, we introduce So-Fake-Set, a co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18660","kind":"arxiv","version":5},"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/2505.18660/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":"2505.18660","created_at":"2026-08-03T01:25:36.813986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18660v5","created_at":"2026-08-03T01:25:36.813986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18660","created_at":"2026-08-03T01:25:36.813986+00:00"},{"alias_kind":"pith_short_12","alias_value":"YL22ABW6B7RO","created_at":"2026-08-03T01:25:36.813986+00:00"},{"alias_kind":"pith_short_16","alias_value":"YL22ABW6B7RO2CMH","created_at":"2026-08-03T01:25:36.813986+00:00"},{"alias_kind":"pith_short_8","alias_value":"YL22ABW6","created_at":"2026-08-03T01:25:36.813986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":10,"sample":[{"citing_arxiv_id":"2607.07545","citing_title":"Face-Trace: Open-Set Attribution and Progressive Discovery of Synthetic Face Generators","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.28609","citing_title":"JECA^2: Judgment-Explanation Consistent Adversarial Attack against Forensic Vision-Language Models","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.30062","citing_title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2605.31192","citing_title":"The Regularizing Power of Language-Training Deepfake Detectors","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16080","citing_title":"ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2512.16300","citing_title":"Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03555","citing_title":"HEDGE: Heterogeneous Ensemble for Detection of AI-GEnerated Images in the Wild","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01638","citing_title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12307","citing_title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11487","citing_title":"NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YL22ABW6B7RO2CMHFGFTONVMH4","json":"https://pith.science/pith/YL22ABW6B7RO2CMHFGFTONVMH4.json","graph_json":"https://pith.science/api/pith-number/YL22ABW6B7RO2CMHFGFTONVMH4/graph.json","events_json":"https://pith.science/api/pith-number/YL22ABW6B7RO2CMHFGFTONVMH4/events.json","paper":"https://pith.science/paper/YL22ABW6"},"agent_actions":{"view_html":"https://pith.science/pith/YL22ABW6B7RO2CMHFGFTONVMH4","download_json":"https://pith.science/pith/YL22ABW6B7RO2CMHFGFTONVMH4.json","view_paper":"https://pith.science/paper/YL22ABW6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18660&json=true","fetch_graph":"https://pith.science/api/pith-number/YL22ABW6B7RO2CMHFGFTONVMH4/graph.json","fetch_events":"https://pith.science/api/pith-number/YL22ABW6B7RO2CMHFGFTONVMH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YL22ABW6B7RO2CMHFGFTONVMH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YL22ABW6B7RO2CMHFGFTONVMH4/action/storage_attestation","attest_author":"https://pith.science/pith/YL22ABW6B7RO2CMHFGFTONVMH4/action/author_attestation","sign_citation":"https://pith.science/pith/YL22ABW6B7RO2CMHFGFTONVMH4/action/citation_signature","submit_replication":"https://pith.science/pith/YL22ABW6B7RO2CMHFGFTONVMH4/action/replication_record"}},"created_at":"2026-08-03T01:25:36.813986+00:00","updated_at":"2026-08-03T01:25:36.813986+00:00"}