{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AIETJQIY26BJ4EOFQMYDWPJ25A","short_pith_number":"pith:AIETJQIY","schema_version":"1.0","canonical_sha256":"020934c118d7829e11c583303b3d3ae8018cd8de2a62e11b7fa0b119744896b5","source":{"kind":"arxiv","id":"2304.06408","version":2},"attestation_state":"computed","paper":{"title":"Intriguing properties of synthetic images: from generative adversarial networks to diffusion models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Davide Cozzolino, Giovanni Poggi, Koki Nagano, Luisa Verdoliva, Riccardo Corvi","submitted_at":"2023-04-13T11:13:19Z","abstract_excerpt":"Detecting fake images is becoming a major goal of computer vision. This need is becoming more and more pressing with the continuous improvement of synthesis methods based on Generative Adversarial Networks (GAN), and even more with the appearance of powerful methods based on Diffusion Models (DM). Towards this end, it is important to gain insight into which image features better discriminate fake images from real ones. In this paper we report on our systematic study of a large number of image generators of different families, aimed at discovering the most forensically relevant characteristics "},"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":"2304.06408","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-13T11:13:19Z","cross_cats_sorted":[],"title_canon_sha256":"fe7710d572fddc55d15bfb8f89b3986d7a180bee0766ce24f3be3d691caea831","abstract_canon_sha256":"5b92e6370124c703a504439274dfcfa998ee51c24d00c119ec781af58633b784"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:01.586009Z","signature_b64":"K2pxJtEd5tpODSeQz7Wk3mgjz+ifwJ/u1svIRizshQCBK37gbE3tEeZpdjaknuZx+PZ5VMxzGdntFhd16wR2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"020934c118d7829e11c583303b3d3ae8018cd8de2a62e11b7fa0b119744896b5","last_reissued_at":"2026-07-05T06:26:01.585520Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:01.585520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intriguing properties of synthetic images: from generative adversarial networks to diffusion models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Davide Cozzolino, Giovanni Poggi, Koki Nagano, Luisa Verdoliva, Riccardo Corvi","submitted_at":"2023-04-13T11:13:19Z","abstract_excerpt":"Detecting fake images is becoming a major goal of computer vision. This need is becoming more and more pressing with the continuous improvement of synthesis methods based on Generative Adversarial Networks (GAN), and even more with the appearance of powerful methods based on Diffusion Models (DM). Towards this end, it is important to gain insight into which image features better discriminate fake images from real ones. In this paper we report on our systematic study of a large number of image generators of different families, aimed at discovering the most forensically relevant characteristics "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06408","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/2304.06408/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":"2304.06408","created_at":"2026-07-05T06:26:01.585574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.06408v2","created_at":"2026-07-05T06:26:01.585574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06408","created_at":"2026-07-05T06:26:01.585574+00:00"},{"alias_kind":"pith_short_12","alias_value":"AIETJQIY26BJ","created_at":"2026-07-05T06:26:01.585574+00:00"},{"alias_kind":"pith_short_16","alias_value":"AIETJQIY26BJ4EOF","created_at":"2026-07-05T06:26:01.585574+00:00"},{"alias_kind":"pith_short_8","alias_value":"AIETJQIY","created_at":"2026-07-05T06:26:01.585574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28510","citing_title":"Generative AI Literacy Training Improves Intelligence Analysts' Discrimination of Real and AI-Generated Images","ref_index":3,"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":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AIETJQIY26BJ4EOFQMYDWPJ25A","json":"https://pith.science/pith/AIETJQIY26BJ4EOFQMYDWPJ25A.json","graph_json":"https://pith.science/api/pith-number/AIETJQIY26BJ4EOFQMYDWPJ25A/graph.json","events_json":"https://pith.science/api/pith-number/AIETJQIY26BJ4EOFQMYDWPJ25A/events.json","paper":"https://pith.science/paper/AIETJQIY"},"agent_actions":{"view_html":"https://pith.science/pith/AIETJQIY26BJ4EOFQMYDWPJ25A","download_json":"https://pith.science/pith/AIETJQIY26BJ4EOFQMYDWPJ25A.json","view_paper":"https://pith.science/paper/AIETJQIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.06408&json=true","fetch_graph":"https://pith.science/api/pith-number/AIETJQIY26BJ4EOFQMYDWPJ25A/graph.json","fetch_events":"https://pith.science/api/pith-number/AIETJQIY26BJ4EOFQMYDWPJ25A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AIETJQIY26BJ4EOFQMYDWPJ25A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AIETJQIY26BJ4EOFQMYDWPJ25A/action/storage_attestation","attest_author":"https://pith.science/pith/AIETJQIY26BJ4EOFQMYDWPJ25A/action/author_attestation","sign_citation":"https://pith.science/pith/AIETJQIY26BJ4EOFQMYDWPJ25A/action/citation_signature","submit_replication":"https://pith.science/pith/AIETJQIY26BJ4EOFQMYDWPJ25A/action/replication_record"}},"created_at":"2026-07-05T06:26:01.585574+00:00","updated_at":"2026-07-05T06:26:01.585574+00:00"}