{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7BRSXXLXSPJW3C7O6NLGSS46TR","short_pith_number":"pith:7BRSXXLX","schema_version":"1.0","canonical_sha256":"f8632bdd7793d36d8beef356694b9e9c60fb57a7055f2b3b36d5c2516d88ad6f","source":{"kind":"arxiv","id":"2405.20112","version":1},"attestation_state":"computed","paper":{"title":"RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pin-Yu Chen, Tsung-Yi Ho, Zhiyuan He","submitted_at":"2024-05-30T14:49:54Z","abstract_excerpt":"The rapid advances in generative AI models have empowered the creation of highly realistic images with arbitrary content, raising concerns about potential misuse and harm, such as Deepfakes. Current research focuses on training detectors using large datasets of generated images. However, these training-based solutions are often computationally expensive and show limited generalization to unseen generated images. In this paper, we propose a training-free method to distinguish between real and AI-generated images. We first observe that real images are more robust to tiny noise perturbations than"},"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":"2405.20112","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T14:49:54Z","cross_cats_sorted":[],"title_canon_sha256":"8c71fc3d651eab427c69d129917a8b3df4b773ef23e4a71e6693d79f780cd82e","abstract_canon_sha256":"61e2025f015586c8d982845d85b143ea354d363ec8e53c4b8e0b65532163c50d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:16.232680Z","signature_b64":"6DzUiu6fhG1lquHbNLIHpTpOx8/KHIbP7WX3w/+1U2lkamasA2koNYxiYIZGMYIZt2cXBJfNlIMy1iSJPjlHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8632bdd7793d36d8beef356694b9e9c60fb57a7055f2b3b36d5c2516d88ad6f","last_reissued_at":"2026-07-05T08:25:16.232254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:16.232254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pin-Yu Chen, Tsung-Yi Ho, Zhiyuan He","submitted_at":"2024-05-30T14:49:54Z","abstract_excerpt":"The rapid advances in generative AI models have empowered the creation of highly realistic images with arbitrary content, raising concerns about potential misuse and harm, such as Deepfakes. Current research focuses on training detectors using large datasets of generated images. However, these training-based solutions are often computationally expensive and show limited generalization to unseen generated images. In this paper, we propose a training-free method to distinguish between real and AI-generated images. We first observe that real images are more robust to tiny noise perturbations than"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20112","kind":"arxiv","version":1},"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/2405.20112/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":"2405.20112","created_at":"2026-07-05T08:25:16.232308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20112v1","created_at":"2026-07-05T08:25:16.232308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20112","created_at":"2026-07-05T08:25:16.232308+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BRSXXLXSPJW","created_at":"2026-07-05T08:25:16.232308+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BRSXXLXSPJW3C7O","created_at":"2026-07-05T08:25:16.232308+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BRSXXLX","created_at":"2026-07-05T08:25:16.232308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20488","citing_title":"How Fragile Are Training-Free AI-Generated Image Detectors? A Controlled Audit of Score Direction, Preprocessing, and Compression","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06918","citing_title":"DRIFT: From Robustness Gaps to Invariance Manifolds for AI-Generated Image Detection","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20787","citing_title":"Findings of the Counter Turing Test: AI-Generated Image Detection","ref_index":16,"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":29,"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":19,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21210","citing_title":"Toward Generalizable Forgery Detection and Reasoning","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20787","citing_title":"Findings of the Counter Turing Test: AI-Generated Image Detection","ref_index":12,"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":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20787","citing_title":"Findings of the Counter Turing Test: AI-Generated Image Detection","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03390","citing_title":"Enhancing Self-Supervised Talking Head Forgery Detection via a Training-Free Dual-System Framework","ref_index":15,"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":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04358","citing_title":"Intermediate Representations are Strong AI-Generated Image Detectors","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7BRSXXLXSPJW3C7O6NLGSS46TR","json":"https://pith.science/pith/7BRSXXLXSPJW3C7O6NLGSS46TR.json","graph_json":"https://pith.science/api/pith-number/7BRSXXLXSPJW3C7O6NLGSS46TR/graph.json","events_json":"https://pith.science/api/pith-number/7BRSXXLXSPJW3C7O6NLGSS46TR/events.json","paper":"https://pith.science/paper/7BRSXXLX"},"agent_actions":{"view_html":"https://pith.science/pith/7BRSXXLXSPJW3C7O6NLGSS46TR","download_json":"https://pith.science/pith/7BRSXXLXSPJW3C7O6NLGSS46TR.json","view_paper":"https://pith.science/paper/7BRSXXLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20112&json=true","fetch_graph":"https://pith.science/api/pith-number/7BRSXXLXSPJW3C7O6NLGSS46TR/graph.json","fetch_events":"https://pith.science/api/pith-number/7BRSXXLXSPJW3C7O6NLGSS46TR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BRSXXLXSPJW3C7O6NLGSS46TR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BRSXXLXSPJW3C7O6NLGSS46TR/action/storage_attestation","attest_author":"https://pith.science/pith/7BRSXXLXSPJW3C7O6NLGSS46TR/action/author_attestation","sign_citation":"https://pith.science/pith/7BRSXXLXSPJW3C7O6NLGSS46TR/action/citation_signature","submit_replication":"https://pith.science/pith/7BRSXXLXSPJW3C7O6NLGSS46TR/action/replication_record"}},"created_at":"2026-07-05T08:25:16.232308+00:00","updated_at":"2026-07-05T08:25:16.232308+00:00"}