{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CDDVU74M27J6NQG42VBAAUL22O","short_pith_number":"pith:CDDVU74M","schema_version":"1.0","canonical_sha256":"10c75a7f8cd7d3e6c0dcd54200517ad3985768f814cf4f0318142046594782b9","source":{"kind":"arxiv","id":"2303.09295","version":1},"attestation_state":"computed","paper":{"title":"DIRE for Diffusion-Generated Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hezhen Hu, Hong Chen, Houqiang Li, Jianmin Bao, Weilun Wang, Wengang Zhou, Zhendong Wang","submitted_at":"2023-03-16T13:15:03Z","abstract_excerpt":"Diffusion models have shown remarkable success in visual synthesis, but have also raised concerns about potential abuse for malicious purposes. In this paper, we seek to build a detector for telling apart real images from diffusion-generated images. We find that existing detectors struggle to detect images generated by diffusion models, even if we include generated images from a specific diffusion model in their training data. To address this issue, we propose a novel image representation called DIffusion Reconstruction Error (DIRE), which measures the error between an input image and its reco"},"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":"2303.09295","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T13:15:03Z","cross_cats_sorted":[],"title_canon_sha256":"1b4cc5c1a29a9cdfc9ec8d044b4dac065d4376311bb08082aa87f50cd05c5120","abstract_canon_sha256":"08408775b15492229b080d8f376891aa6d3e683c84c62268cbcec2c6dc73529e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:51.561791Z","signature_b64":"vPMtXpBlDlQ8YaUk3nK8m4nMK5PZ0CoWllXmFY/ZwTn/A6oWJpSuReOAQZcIPMpIwqHLKROcU2gIhFMbaCBRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10c75a7f8cd7d3e6c0dcd54200517ad3985768f814cf4f0318142046594782b9","last_reissued_at":"2026-07-05T05:51:51.561360Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:51.561360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIRE for Diffusion-Generated Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hezhen Hu, Hong Chen, Houqiang Li, Jianmin Bao, Weilun Wang, Wengang Zhou, Zhendong Wang","submitted_at":"2023-03-16T13:15:03Z","abstract_excerpt":"Diffusion models have shown remarkable success in visual synthesis, but have also raised concerns about potential abuse for malicious purposes. In this paper, we seek to build a detector for telling apart real images from diffusion-generated images. We find that existing detectors struggle to detect images generated by diffusion models, even if we include generated images from a specific diffusion model in their training data. To address this issue, we propose a novel image representation called DIffusion Reconstruction Error (DIRE), which measures the error between an input image and its reco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09295","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/2303.09295/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":"2303.09295","created_at":"2026-07-05T05:51:51.561419+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09295v1","created_at":"2026-07-05T05:51:51.561419+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09295","created_at":"2026-07-05T05:51:51.561419+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDDVU74M27J6","created_at":"2026-07-05T05:51:51.561419+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDDVU74M27J6NQG4","created_at":"2026-07-05T05:51:51.561419+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDDVU74M","created_at":"2026-07-05T05:51:51.561419+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06254","citing_title":"VendorBench-100: A Unified Cross-Paradigm Benchmark for Deepfake Image Detection","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19259","citing_title":"TextRich: A Multi-Domain Benchmark for Detecting AI-Generated Text-Rich Images from GPT-Image-2","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14799","citing_title":"Can Visual Mamba Improve AI-Generated Image Detection? An In-Depth Investigation","ref_index":76,"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":45,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12982","citing_title":"Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2404.12390","citing_title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16987","citing_title":"DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CDDVU74M27J6NQG42VBAAUL22O","json":"https://pith.science/pith/CDDVU74M27J6NQG42VBAAUL22O.json","graph_json":"https://pith.science/api/pith-number/CDDVU74M27J6NQG42VBAAUL22O/graph.json","events_json":"https://pith.science/api/pith-number/CDDVU74M27J6NQG42VBAAUL22O/events.json","paper":"https://pith.science/paper/CDDVU74M"},"agent_actions":{"view_html":"https://pith.science/pith/CDDVU74M27J6NQG42VBAAUL22O","download_json":"https://pith.science/pith/CDDVU74M27J6NQG42VBAAUL22O.json","view_paper":"https://pith.science/paper/CDDVU74M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09295&json=true","fetch_graph":"https://pith.science/api/pith-number/CDDVU74M27J6NQG42VBAAUL22O/graph.json","fetch_events":"https://pith.science/api/pith-number/CDDVU74M27J6NQG42VBAAUL22O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDDVU74M27J6NQG42VBAAUL22O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDDVU74M27J6NQG42VBAAUL22O/action/storage_attestation","attest_author":"https://pith.science/pith/CDDVU74M27J6NQG42VBAAUL22O/action/author_attestation","sign_citation":"https://pith.science/pith/CDDVU74M27J6NQG42VBAAUL22O/action/citation_signature","submit_replication":"https://pith.science/pith/CDDVU74M27J6NQG42VBAAUL22O/action/replication_record"}},"created_at":"2026-07-05T05:51:51.561419+00:00","updated_at":"2026-07-05T05:51:51.561419+00:00"}