{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KDKXAL36QHW74VY53JGOCTJB4R","short_pith_number":"pith:KDKXAL36","schema_version":"1.0","canonical_sha256":"50d5702f7e81edfe571dda4ce14d21e460ca6b7cf8190b0b1ae92964fe551d20","source":{"kind":"arxiv","id":"2310.17419","version":3},"attestation_state":"computed","paper":{"title":"AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Yeh, Ning Yu, Wei-Chen Chiu, You-Ming Chang","submitted_at":"2023-10-26T14:23:45Z","abstract_excerpt":"Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake detection technique is developed to distinguish between real and fake images, where the existing methods typically learn classifiers in the image domain or various feature domains. However, the generalizability of deepfake detection against emerging and more advanced generative models remains challenging. In this paper, being inspired by the zero-shot advantages of Vision-Language Models (VLMs), we propose a novel ap"},"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":"2310.17419","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-26T14:23:45Z","cross_cats_sorted":[],"title_canon_sha256":"bd2ffc9e756d6051773f5b86edf77e8f19bf00ada4078d7fdc70e904e7d1fcef","abstract_canon_sha256":"eabe979649af45609dea5954730303a57a55575d0fe06404a1ccc2476e34e71e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:34.388200Z","signature_b64":"NsUqHgWzFPHAhhOGfHp63PBRm188iobSj2vBfVyuON8Z48cq6cqDGvwt+urOIWiqpaMIB7JdvYY5/LrYxXNJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50d5702f7e81edfe571dda4ce14d21e460ca6b7cf8190b0b1ae92964fe551d20","last_reissued_at":"2026-07-05T08:57:34.387758Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:34.387758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Yeh, Ning Yu, Wei-Chen Chiu, You-Ming Chang","submitted_at":"2023-10-26T14:23:45Z","abstract_excerpt":"Deep generative models can create remarkably photorealistic fake images while raising concerns about misinformation and copyright infringement, known as deepfake threats. Deepfake detection technique is developed to distinguish between real and fake images, where the existing methods typically learn classifiers in the image domain or various feature domains. However, the generalizability of deepfake detection against emerging and more advanced generative models remains challenging. In this paper, being inspired by the zero-shot advantages of Vision-Language Models (VLMs), we propose a novel ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17419","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/2310.17419/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":"2310.17419","created_at":"2026-07-05T08:57:34.387810+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17419v3","created_at":"2026-07-05T08:57:34.387810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17419","created_at":"2026-07-05T08:57:34.387810+00:00"},{"alias_kind":"pith_short_12","alias_value":"KDKXAL36QHW7","created_at":"2026-07-05T08:57:34.387810+00:00"},{"alias_kind":"pith_short_16","alias_value":"KDKXAL36QHW74VY5","created_at":"2026-07-05T08:57:34.387810+00:00"},{"alias_kind":"pith_short_8","alias_value":"KDKXAL36","created_at":"2026-07-05T08:57:34.387810+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14799","citing_title":"Can Visual Mamba Improve AI-Generated Image Detection? An In-Depth Investigation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30062","citing_title":"FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31192","citing_title":"The Regularizing Power of Language-Training Deepfake Detectors","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21210","citing_title":"Toward Generalizable Forgery Detection and Reasoning","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16080","citing_title":"ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04225","citing_title":"Locate-Then-Examine: Grounded Region Reasoning Improves Detection of AI-Generated Images","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00181","citing_title":"From Evidence to Verdict: An Agent-Based Forensic Framework for AI-Generated Image Detection","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14091","citing_title":"Venus-DeFakerOne: Unified Fake Image Detection & Localization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03833","citing_title":"SPARK-IL: Spectral Retrieval-Augmented RAG for Knowledge-driven Deepfake Detection via Incremental Learning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01638","citing_title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21904","citing_title":"UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KDKXAL36QHW74VY53JGOCTJB4R","json":"https://pith.science/pith/KDKXAL36QHW74VY53JGOCTJB4R.json","graph_json":"https://pith.science/api/pith-number/KDKXAL36QHW74VY53JGOCTJB4R/graph.json","events_json":"https://pith.science/api/pith-number/KDKXAL36QHW74VY53JGOCTJB4R/events.json","paper":"https://pith.science/paper/KDKXAL36"},"agent_actions":{"view_html":"https://pith.science/pith/KDKXAL36QHW74VY53JGOCTJB4R","download_json":"https://pith.science/pith/KDKXAL36QHW74VY53JGOCTJB4R.json","view_paper":"https://pith.science/paper/KDKXAL36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17419&json=true","fetch_graph":"https://pith.science/api/pith-number/KDKXAL36QHW74VY53JGOCTJB4R/graph.json","fetch_events":"https://pith.science/api/pith-number/KDKXAL36QHW74VY53JGOCTJB4R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KDKXAL36QHW74VY53JGOCTJB4R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KDKXAL36QHW74VY53JGOCTJB4R/action/storage_attestation","attest_author":"https://pith.science/pith/KDKXAL36QHW74VY53JGOCTJB4R/action/author_attestation","sign_citation":"https://pith.science/pith/KDKXAL36QHW74VY53JGOCTJB4R/action/citation_signature","submit_replication":"https://pith.science/pith/KDKXAL36QHW74VY53JGOCTJB4R/action/replication_record"}},"created_at":"2026-07-05T08:57:34.387810+00:00","updated_at":"2026-07-05T08:57:34.387810+00:00"}