{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7EE5VYS3S4IYZGHC4RZDDTLATQ","short_pith_number":"pith:7EE5VYS3","schema_version":"1.0","canonical_sha256":"f909dae25b97118c98e2e47231cd609c1398979080987bdfcab082c1498e5296","source":{"kind":"arxiv","id":"2406.19435","version":3},"attestation_state":"computed","paper":{"title":"A Sanity Check for AI-generated Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayin Cai, Ouxiang Li, Shilin Yan, Weidi Xie, Xiaolong Jiang, Yanbin Hao, Yao Hu","submitted_at":"2024-06-27T17:59:49Z","abstract_excerpt":"With the rapid development of generative models, discerning AI-generated content has evoked increasing attention from both industry and academia. In this paper, we conduct a sanity check on \"whether the task of AI-generated image detection has been solved\". To start with, we present Chameleon dataset, consisting AIgenerated images that are genuinely challenging for human perception. To quantify the generalization of existing methods, we evaluate 9 off-the-shelf AI-generated image detectors on Chameleon dataset. Upon analysis, almost all models classify AI-generated images as real ones. Later, "},"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":"2406.19435","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-27T17:59:49Z","cross_cats_sorted":[],"title_canon_sha256":"8d2291038c0a7c5cf75464a85129ce8cb48e6b0a63150738fd53da24094177f5","abstract_canon_sha256":"7c2ac59276b3c1c080c19081384c9bc78e43ad3129430030f41b5a3de260e676"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:42.564931Z","signature_b64":"XRFWyG+2BLOValIN4/P9cW/g+rUDRemmW/YdlKdSPgobyZUBOcOxyDHo1H4JetnN5/IXh6YHLwGyjlSuhn18BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f909dae25b97118c98e2e47231cd609c1398979080987bdfcab082c1498e5296","last_reissued_at":"2026-07-05T10:14:42.564248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:42.564248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Sanity Check for AI-generated Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiayin Cai, Ouxiang Li, Shilin Yan, Weidi Xie, Xiaolong Jiang, Yanbin Hao, Yao Hu","submitted_at":"2024-06-27T17:59:49Z","abstract_excerpt":"With the rapid development of generative models, discerning AI-generated content has evoked increasing attention from both industry and academia. In this paper, we conduct a sanity check on \"whether the task of AI-generated image detection has been solved\". To start with, we present Chameleon dataset, consisting AIgenerated images that are genuinely challenging for human perception. To quantify the generalization of existing methods, we evaluate 9 off-the-shelf AI-generated image detectors on Chameleon dataset. Upon analysis, almost all models classify AI-generated images as real ones. Later, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19435","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/2406.19435/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":"2406.19435","created_at":"2026-07-05T10:14:42.564407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.19435v3","created_at":"2026-07-05T10:14:42.564407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19435","created_at":"2026-07-05T10:14:42.564407+00:00"},{"alias_kind":"pith_short_12","alias_value":"7EE5VYS3S4IY","created_at":"2026-07-05T10:14:42.564407+00:00"},{"alias_kind":"pith_short_16","alias_value":"7EE5VYS3S4IYZGHC","created_at":"2026-07-05T10:14:42.564407+00:00"},{"alias_kind":"pith_short_8","alias_value":"7EE5VYS3","created_at":"2026-07-05T10:14:42.564407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":29,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06254","citing_title":"VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection","ref_index":83,"is_internal_anchor":true},{"citing_arxiv_id":"2606.11200","citing_title":"Detecting AI-Generated Content on Social Media with Multi-modal Language Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12671","citing_title":"SalArt-VQA: Diagnosing Whether VLMs Understand Salient Artifacts in Generated Images","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10309","citing_title":"Dissect and Prune: Enhancing Robustness in AI-Generated Image Detection","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08634","citing_title":"SSAFE: Simple and Strong AI-Generated Image Detection via Frozen Vision Encoders","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04545","citing_title":"Impostor: An Agent-Curated Benchmark for Realistic AIGC Manipulation Localization","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03348","citing_title":"SynCred-Bench: Benchmarking Synthetic Credibility in AI-Generated Visual Misinformation","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02224","citing_title":"Chroma Clues: Leveraging Color Statistics to Detect Synthetic Images","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26421","citing_title":"HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27348","citing_title":"When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30062","citing_title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2412.20704","citing_title":"HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21210","citing_title":"Toward Generalizable Forgery Detection and Reasoning","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2507.10236","citing_title":"Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters?","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16080","citing_title":"ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07074","citing_title":"Decoupling Semantics and Fingerprints: A Universal Representation for AI-Generated Image Detection","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21864","citing_title":"Deepfakes: we need to re-think the concept of \"real\" images","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16136","citing_title":"How Noise Benefits AI-generated Image Detection","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12982","citing_title":"Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2602.01738","citing_title":"Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14486","citing_title":"Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09296","citing_title":"Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08226","citing_title":"SPECTRA-Net: Scalable Pipeline for Explainable Cross-domain Tensor Representations for AI-generated Images Detection","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04358","citing_title":"Intermediate Representations are Strong AI-Generated Image Detectors","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12307","citing_title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7EE5VYS3S4IYZGHC4RZDDTLATQ","json":"https://pith.science/pith/7EE5VYS3S4IYZGHC4RZDDTLATQ.json","graph_json":"https://pith.science/api/pith-number/7EE5VYS3S4IYZGHC4RZDDTLATQ/graph.json","events_json":"https://pith.science/api/pith-number/7EE5VYS3S4IYZGHC4RZDDTLATQ/events.json","paper":"https://pith.science/paper/7EE5VYS3"},"agent_actions":{"view_html":"https://pith.science/pith/7EE5VYS3S4IYZGHC4RZDDTLATQ","download_json":"https://pith.science/pith/7EE5VYS3S4IYZGHC4RZDDTLATQ.json","view_paper":"https://pith.science/paper/7EE5VYS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.19435&json=true","fetch_graph":"https://pith.science/api/pith-number/7EE5VYS3S4IYZGHC4RZDDTLATQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7EE5VYS3S4IYZGHC4RZDDTLATQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7EE5VYS3S4IYZGHC4RZDDTLATQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7EE5VYS3S4IYZGHC4RZDDTLATQ/action/storage_attestation","attest_author":"https://pith.science/pith/7EE5VYS3S4IYZGHC4RZDDTLATQ/action/author_attestation","sign_citation":"https://pith.science/pith/7EE5VYS3S4IYZGHC4RZDDTLATQ/action/citation_signature","submit_replication":"https://pith.science/pith/7EE5VYS3S4IYZGHC4RZDDTLATQ/action/replication_record"}},"created_at":"2026-07-05T10:14:42.564407+00:00","updated_at":"2026-07-05T10:14:42.564407+00:00"}