{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FZ5PSVKB7ZK4QVPFKXEUYSNLCF","short_pith_number":"pith:FZ5PSVKB","schema_version":"1.0","canonical_sha256":"2e7af95541fe55c855e555c94c49ab1173ef5eec195de9494214077d8c705c28","source":{"kind":"arxiv","id":"2503.18812","version":1},"attestation_state":"computed","paper":{"title":"SKDU at De-Factify 4.0: Vision Transformer with Data Augmentation for AI-Generated Image Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Neelanjan Bhowmik, Shrikant Malviya, Stamos Katsigiannis","submitted_at":"2025-03-24T15:53:54Z","abstract_excerpt":"The aim of this work is to explore the potential of pre-trained vision-language models, e.g. Vision Transformers (ViT), enhanced with advanced data augmentation strategies for the detection of AI-generated images. Our approach leverages a fine-tuned ViT model trained on the Defactify-4.0 dataset, which includes images generated by state-of-the-art models such as Stable Diffusion 2.1, Stable Diffusion XL, Stable Diffusion 3, DALL-E 3, and MidJourney. We employ perturbation techniques like flipping, rotation, Gaussian noise injection, and JPEG compression during training to improve model robustn"},"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":"2503.18812","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-24T15:53:54Z","cross_cats_sorted":[],"title_canon_sha256":"b8f0f734823d933a8a90f5c7a6e5605992f10c144c689b67dfebd3d89cb63c19","abstract_canon_sha256":"37a4eca43b0cdadded93106537a116221ff8d9c7c90a4cb8216134e80023ea52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:26.976603Z","signature_b64":"FZspX/TE41MlwbabmxQk3T659kCZQC4dkrOiDlEBHKEBOxBt2q7scUOVJWXzHu2JpwtiGJmxawHLmSaQz5mODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e7af95541fe55c855e555c94c49ab1173ef5eec195de9494214077d8c705c28","last_reissued_at":"2026-07-05T10:38:26.976077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:26.976077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SKDU at De-Factify 4.0: Vision Transformer with Data Augmentation for AI-Generated Image Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Neelanjan Bhowmik, Shrikant Malviya, Stamos Katsigiannis","submitted_at":"2025-03-24T15:53:54Z","abstract_excerpt":"The aim of this work is to explore the potential of pre-trained vision-language models, e.g. Vision Transformers (ViT), enhanced with advanced data augmentation strategies for the detection of AI-generated images. Our approach leverages a fine-tuned ViT model trained on the Defactify-4.0 dataset, which includes images generated by state-of-the-art models such as Stable Diffusion 2.1, Stable Diffusion XL, Stable Diffusion 3, DALL-E 3, and MidJourney. We employ perturbation techniques like flipping, rotation, Gaussian noise injection, and JPEG compression during training to improve model robustn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18812","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/2503.18812/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":"2503.18812","created_at":"2026-07-05T10:38:26.976136+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.18812v1","created_at":"2026-07-05T10:38:26.976136+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18812","created_at":"2026-07-05T10:38:26.976136+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZ5PSVKB7ZK4","created_at":"2026-07-05T10:38:26.976136+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZ5PSVKB7ZK4QVPF","created_at":"2026-07-05T10:38:26.976136+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZ5PSVKB","created_at":"2026-07-05T10:38:26.976136+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20787","citing_title":"Findings of the Counter Turing Test: AI-Generated Image Detection","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20787","citing_title":"Findings of the Counter Turing Test: AI-Generated Image Detection","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20787","citing_title":"Findings of the Counter Turing Test: AI-Generated Image Detection","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZ5PSVKB7ZK4QVPFKXEUYSNLCF","json":"https://pith.science/pith/FZ5PSVKB7ZK4QVPFKXEUYSNLCF.json","graph_json":"https://pith.science/api/pith-number/FZ5PSVKB7ZK4QVPFKXEUYSNLCF/graph.json","events_json":"https://pith.science/api/pith-number/FZ5PSVKB7ZK4QVPFKXEUYSNLCF/events.json","paper":"https://pith.science/paper/FZ5PSVKB"},"agent_actions":{"view_html":"https://pith.science/pith/FZ5PSVKB7ZK4QVPFKXEUYSNLCF","download_json":"https://pith.science/pith/FZ5PSVKB7ZK4QVPFKXEUYSNLCF.json","view_paper":"https://pith.science/paper/FZ5PSVKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.18812&json=true","fetch_graph":"https://pith.science/api/pith-number/FZ5PSVKB7ZK4QVPFKXEUYSNLCF/graph.json","fetch_events":"https://pith.science/api/pith-number/FZ5PSVKB7ZK4QVPFKXEUYSNLCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZ5PSVKB7ZK4QVPFKXEUYSNLCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZ5PSVKB7ZK4QVPFKXEUYSNLCF/action/storage_attestation","attest_author":"https://pith.science/pith/FZ5PSVKB7ZK4QVPFKXEUYSNLCF/action/author_attestation","sign_citation":"https://pith.science/pith/FZ5PSVKB7ZK4QVPFKXEUYSNLCF/action/citation_signature","submit_replication":"https://pith.science/pith/FZ5PSVKB7ZK4QVPFKXEUYSNLCF/action/replication_record"}},"created_at":"2026-07-05T10:38:26.976136+00:00","updated_at":"2026-07-05T10:38:26.976136+00:00"}