{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HNLG54IYIN4QONJGZEWX7QGPD3","short_pith_number":"pith:HNLG54IY","schema_version":"1.0","canonical_sha256":"3b566ef1184379073526c92d7fc0cf1ec2dae86a37a17ff526ee03628a79df82","source":{"kind":"arxiv","id":"2507.10236","version":2},"attestation_state":"computed","paper":{"title":"Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christos Koutlis, Despina Konstantinidou, Dimitrios Karageorgiou, Emmanouil Schinas, Olga Papadopoulou, Symeon Papadopoulos","submitted_at":"2025-07-14T12:56:55Z","abstract_excerpt":"As generative Artificial Intelligence (AI) advances, the realism of AI generated imagery has reached a threshold capable of deceiving even vigilant human observers. Yet, while current AI-generated Image Detection (AID) approaches perform exceptionally well on controlled benchmark datasets, they struggle significantly with real-world cases. To study this behavior we introduce the ITW-SM dataset, a curated collection of real and AI-generated images originating from major social media platforms. We employ it to analyze the effects of key design choices typically considered when building a detecto"},"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":"2507.10236","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-14T12:56:55Z","cross_cats_sorted":[],"title_canon_sha256":"cf11aa621417f5f8f07d62875d4dd9b836aa72ee3874416f60af50d9422d543e","abstract_canon_sha256":"d1d984450dc9326ce8319530cff5c15152899db3e4025cadbb8952664ded5ccd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:34.780144Z","signature_b64":"cF0cAZ0qZ9uBIXrSxS7WSxprJh3f41K8E4UEHc+2XRUT+FbNiYMEuTLACvYj6VS8vDZL2Khc2vzsGF6J5RsQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b566ef1184379073526c92d7fc0cf1ec2dae86a37a17ff526ee03628a79df82","last_reissued_at":"2026-05-20T00:01:34.779395Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:34.779395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Navigating the Challenges of AI-Generated Image Detection in the Wild: What Truly Matters?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christos Koutlis, Despina Konstantinidou, Dimitrios Karageorgiou, Emmanouil Schinas, Olga Papadopoulou, Symeon Papadopoulos","submitted_at":"2025-07-14T12:56:55Z","abstract_excerpt":"As generative Artificial Intelligence (AI) advances, the realism of AI generated imagery has reached a threshold capable of deceiving even vigilant human observers. Yet, while current AI-generated Image Detection (AID) approaches perform exceptionally well on controlled benchmark datasets, they struggle significantly with real-world cases. To study this behavior we introduce the ITW-SM dataset, a curated collection of real and AI-generated images originating from major social media platforms. We employ it to analyze the effects of key design choices typically considered when building a detecto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10236","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/2507.10236/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":"2507.10236","created_at":"2026-05-20T00:01:34.779510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10236v2","created_at":"2026-05-20T00:01:34.779510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10236","created_at":"2026-05-20T00:01:34.779510+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNLG54IYIN4Q","created_at":"2026-05-20T00:01:34.779510+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNLG54IYIN4QONJG","created_at":"2026-05-20T00:01:34.779510+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNLG54IY","created_at":"2026-05-20T00:01:34.779510+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2604.12307","citing_title":"Boosting Robust AIGI Detection with LoRA-based Pairwise Training","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02567","citing_title":"Automated In-the-Wild Data Collection for Continual AI Generated Image Detection","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNLG54IYIN4QONJGZEWX7QGPD3","json":"https://pith.science/pith/HNLG54IYIN4QONJGZEWX7QGPD3.json","graph_json":"https://pith.science/api/pith-number/HNLG54IYIN4QONJGZEWX7QGPD3/graph.json","events_json":"https://pith.science/api/pith-number/HNLG54IYIN4QONJGZEWX7QGPD3/events.json","paper":"https://pith.science/paper/HNLG54IY"},"agent_actions":{"view_html":"https://pith.science/pith/HNLG54IYIN4QONJGZEWX7QGPD3","download_json":"https://pith.science/pith/HNLG54IYIN4QONJGZEWX7QGPD3.json","view_paper":"https://pith.science/paper/HNLG54IY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10236&json=true","fetch_graph":"https://pith.science/api/pith-number/HNLG54IYIN4QONJGZEWX7QGPD3/graph.json","fetch_events":"https://pith.science/api/pith-number/HNLG54IYIN4QONJGZEWX7QGPD3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNLG54IYIN4QONJGZEWX7QGPD3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNLG54IYIN4QONJGZEWX7QGPD3/action/storage_attestation","attest_author":"https://pith.science/pith/HNLG54IYIN4QONJGZEWX7QGPD3/action/author_attestation","sign_citation":"https://pith.science/pith/HNLG54IYIN4QONJGZEWX7QGPD3/action/citation_signature","submit_replication":"https://pith.science/pith/HNLG54IYIN4QONJGZEWX7QGPD3/action/replication_record"}},"created_at":"2026-05-20T00:01:34.779510+00:00","updated_at":"2026-05-20T00:01:34.779510+00:00"}