{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OYH3WYCJARU6H5W3W54W5QLCDI","short_pith_number":"pith:OYH3WYCJ","schema_version":"1.0","canonical_sha256":"760fbb60490469e3f6dbb7796ec1621a3a892aee94ee5bbf4e89c74189eddeab","source":{"kind":"arxiv","id":"2410.11835","version":3},"attestation_state":"computed","paper":{"title":"Aligned Datasets Improve Detection of Latent Diffusion-Generated Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anirudh Sundara Rajan, Jedidiah Schloesser, Utkarsh Ojha, Yong Jae Lee","submitted_at":"2024-10-15T17:58:07Z","abstract_excerpt":"As latent diffusion models (LDMs) democratize image generation capabilities, there is a growing need to detect fake images. A good detector should focus on the generative models fingerprints while ignoring image properties such as semantic content, resolution, file format, etc. Fake image detectors are usually built in a data driven way, where a model is trained to separate real from fake images. Existing works primarily investigate network architecture choices and training recipes. In this work, we argue that in addition to these algorithmic choices, we also require a well aligned dataset of "},"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":"2410.11835","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T17:58:07Z","cross_cats_sorted":[],"title_canon_sha256":"458010f214a4a68601268609f27e56be69e9a993d0d76acb50784599a933de8b","abstract_canon_sha256":"2c79bf46fd1fdad9e79135f89572f02ef86d4b442bfb6e0c5702b55ece59deeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:16.589380Z","signature_b64":"b6GhJzqS0sTpsgCKfXvBqgGXp9sbQSNrld+aSULD3uZYJnwvIkbm4I4iULnBlzIhdm+xos9tcF214lGbqRYIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"760fbb60490469e3f6dbb7796ec1621a3a892aee94ee5bbf4e89c74189eddeab","last_reissued_at":"2026-07-05T10:20:16.588859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:16.588859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligned Datasets Improve Detection of Latent Diffusion-Generated Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anirudh Sundara Rajan, Jedidiah Schloesser, Utkarsh Ojha, Yong Jae Lee","submitted_at":"2024-10-15T17:58:07Z","abstract_excerpt":"As latent diffusion models (LDMs) democratize image generation capabilities, there is a growing need to detect fake images. A good detector should focus on the generative models fingerprints while ignoring image properties such as semantic content, resolution, file format, etc. Fake image detectors are usually built in a data driven way, where a model is trained to separate real from fake images. Existing works primarily investigate network architecture choices and training recipes. In this work, we argue that in addition to these algorithmic choices, we also require a well aligned dataset of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11835","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/2410.11835/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":"2410.11835","created_at":"2026-07-05T10:20:16.588932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11835v3","created_at":"2026-07-05T10:20:16.588932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11835","created_at":"2026-07-05T10:20:16.588932+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYH3WYCJARU6","created_at":"2026-07-05T10:20:16.588932+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYH3WYCJARU6H5W3","created_at":"2026-07-05T10:20:16.588932+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYH3WYCJ","created_at":"2026-07-05T10:20:16.588932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26421","citing_title":"HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14486","citing_title":"Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03555","citing_title":"HEDGE: Heterogeneous Ensemble for Detection of AI-GEnerated Images in the Wild","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27875","citing_title":"Frequency-Aware Semantic Fusion with Gated Injection for AI-generated Image Detection","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09296","citing_title":"Micro-Defects Expose Macro-Fakes: Detecting AI-Generated Images via Local Distributional Shifts","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYH3WYCJARU6H5W3W54W5QLCDI","json":"https://pith.science/pith/OYH3WYCJARU6H5W3W54W5QLCDI.json","graph_json":"https://pith.science/api/pith-number/OYH3WYCJARU6H5W3W54W5QLCDI/graph.json","events_json":"https://pith.science/api/pith-number/OYH3WYCJARU6H5W3W54W5QLCDI/events.json","paper":"https://pith.science/paper/OYH3WYCJ"},"agent_actions":{"view_html":"https://pith.science/pith/OYH3WYCJARU6H5W3W54W5QLCDI","download_json":"https://pith.science/pith/OYH3WYCJARU6H5W3W54W5QLCDI.json","view_paper":"https://pith.science/paper/OYH3WYCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11835&json=true","fetch_graph":"https://pith.science/api/pith-number/OYH3WYCJARU6H5W3W54W5QLCDI/graph.json","fetch_events":"https://pith.science/api/pith-number/OYH3WYCJARU6H5W3W54W5QLCDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYH3WYCJARU6H5W3W54W5QLCDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYH3WYCJARU6H5W3W54W5QLCDI/action/storage_attestation","attest_author":"https://pith.science/pith/OYH3WYCJARU6H5W3W54W5QLCDI/action/author_attestation","sign_citation":"https://pith.science/pith/OYH3WYCJARU6H5W3W54W5QLCDI/action/citation_signature","submit_replication":"https://pith.science/pith/OYH3WYCJARU6H5W3W54W5QLCDI/action/replication_record"}},"created_at":"2026-07-05T10:20:16.588932+00:00","updated_at":"2026-07-05T10:20:16.588932+00:00"}