{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KKSRF7L2D2ZTTAZF5CCMZ5UBGE","short_pith_number":"pith:KKSRF7L2","canonical_record":{"source":{"id":"2605.14486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T07:26:36Z","cross_cats_sorted":[],"title_canon_sha256":"a5721bcdbda68f2ae458540a32576325134eae2024e93b465728b57ac27f0a02","abstract_canon_sha256":"af00a987f526544a55c242081c7793d22a1c6cd33e663967795a2bbf9c2e78c4"},"schema_version":"1.0"},"canonical_sha256":"52a512fd7a1eb3398325e884ccf681310dd978b2bcc34f0b9b3d3cd60e4cfe7a","source":{"kind":"arxiv","id":"2605.14486","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14486","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14486v1","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14486","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"KKSRF7L2D2ZT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KKSRF7L2D2ZTTAZF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KKSRF7L2","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KKSRF7L2D2ZTTAZF5CCMZ5UBGE","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T07:26:36Z","cross_cats_sorted":[],"title_canon_sha256":"a5721bcdbda68f2ae458540a32576325134eae2024e93b465728b57ac27f0a02","abstract_canon_sha256":"af00a987f526544a55c242081c7793d22a1c6cd33e663967795a2bbf9c2e78c4"},"schema_version":"1.0"},"canonical_sha256":"52a512fd7a1eb3398325e884ccf681310dd978b2bcc34f0b9b3d3cd60e4cfe7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:06.491798Z","signature_b64":"yGwevubr+fGG2vCA14rIc9aKqTUsphYR20PtmQzxO93Pz+HmWaTm6r36eKVGoNkrRrLZjDblsIUUMk0FgLOmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52a512fd7a1eb3398325e884ccf681310dd978b2bcc34f0b9b3d3cd60e4cfe7a","last_reissued_at":"2026-05-17T23:39:06.491082Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:06.491082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14486","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7LZsLrU57/JM32ZZxQECWPJMlJUb/Ojt7rZU+K16OScR+EGEHJrV2lTrMBPjEOsziPT26Vq5cDjMrWLzUbftCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T18:47:20.946233Z"},"content_sha256":"5c0ea5087fdd559445be3a707da2101b6fb79085ee965e6fb93d74ed6aa59ed0","schema_version":"1.0","event_id":"sha256:5c0ea5087fdd559445be3a707da2101b6fb79085ee965e6fb93d74ed6aa59ed0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KKSRF7L2D2ZTTAZF5CCMZ5UBGE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A GAN-based upsampling method plus Separate Expert Fusion reduces artifact bias and improves generalization in AI-generated image detection.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gao Li, Wenhao Wang, Yang Yang, Yiheng Li, Zhen Lei, Zichang Tan","submitted_at":"2026-05-14T07:26:36Z","abstract_excerpt":"As the misuse of AI-generated images grows, generalizable image detection techniques are urgently needed. Recent state-of-the-art (SOTA) methods adopt aligned training datasets to reduce content, size, and format biases, empowering models to capture robust forgery cues. A common strategy is to employ reconstruction techniques, e.g., VAE and DDIM, which show remarkable results in diffusion-based methods. However, such reconstruction-based approaches typically introduce limited and homogeneous artifacts, which cannot fully capture diverse generative patterns, such as GAN-based methods. To comple"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Rather than merely benefiting GAN-generated image detection, this design introduces diverse and complementary artifact patterns that enable SEF to learn a more robust decision boundary and improve generalization across broader generative methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the proposed GAN-based upsampling produces artifact patterns that are both aligned (content/size/format) with reconstruction fakes and sufficiently distinct to provide complementary information without introducing new unmodeled biases.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A GAN-based upsampling method plus Separate Expert Fusion reduces artifact bias and improves generalization in AI-generated image detection.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7fd062025d9d7bea7f3472a20f1aeafcd4874baabd153e283353af4addf22f26"},"source":{"id":"2605.14486","kind":"arxiv","version":1},"verdict":{"id":"b99a2f40-c57d-4514-bbcb-187aa876e820","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:33:22.200340Z","strongest_claim":"Rather than merely benefiting GAN-generated image detection, this design introduces diverse and complementary artifact patterns that enable SEF to learn a more robust decision boundary and improve generalization across broader generative methods.","one_line_summary":"SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the proposed GAN-based upsampling produces artifact patterns that are both aligned (content/size/format) with reconstruction fakes and sufficiently distinct to provide complementary information without introducing new unmodeled biases.","pith_extraction_headline":"A GAN-based upsampling method plus Separate Expert Fusion reduces artifact bias and improves generalization in AI-generated image detection."},"references":{"count":68,"sample":[{"doi":"","year":2023,"title":"Synthbuster: Towards detection of diffusion model generated images.IEEE Open Journal of Signal Processing, 5:1–9, 2023","work_id":"2febba00-8ed5-42ff-a42c-45224344b8b9","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","work_id":"244e6f06-bad2-4f34-8186-ff370286427f","ref_index":2,"cited_arxiv_id":"1809.11096","is_internal_anchor":true},{"doi":"","year":2026,"title":"Zooming in on fakes: A novel dataset for localized ai-generated image detection with forgery amplification approach","work_id":"b34aecdd-ac2e-49c5-9124-c0c7fb332b03","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Emerging properties in self-supervised vision transformers","work_id":"def40bfd-07b5-4f25-94fd-883b4ac6838d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Real-time deepfake detection in the real-world","work_id":"9493fae4-3b84-47d9-9b27-12baa60d298c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":68,"snapshot_sha256":"d2dfa4238ec4a34659b0762f58bedb56d162eed7f3bc6c56bca208b86708500e","internal_anchors":8},"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"},"verdict_id":"b99a2f40-c57d-4514-bbcb-187aa876e820"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KpVyTE119iPDcNoCirjIkRQTx1KcQUvUNIzSi3cOhsTI1Wg8vkmeZP3Xq6MltG09OkJG/MZTnN9oprtr1TnxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T18:47:20.946888Z"},"content_sha256":"946b2e706fc0e911da882ea9b5e5ab348127fc5729811039081979f7c0714788","schema_version":"1.0","event_id":"sha256:946b2e706fc0e911da882ea9b5e5ab348127fc5729811039081979f7c0714788"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KKSRF7L2D2ZTTAZF5CCMZ5UBGE/bundle.json","state_url":"https://pith.science/pith/KKSRF7L2D2ZTTAZF5CCMZ5UBGE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KKSRF7L2D2ZTTAZF5CCMZ5UBGE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T18:47:20Z","links":{"resolver":"https://pith.science/pith/KKSRF7L2D2ZTTAZF5CCMZ5UBGE","bundle":"https://pith.science/pith/KKSRF7L2D2ZTTAZF5CCMZ5UBGE/bundle.json","state":"https://pith.science/pith/KKSRF7L2D2ZTTAZF5CCMZ5UBGE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KKSRF7L2D2ZTTAZF5CCMZ5UBGE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KKSRF7L2D2ZTTAZF5CCMZ5UBGE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"af00a987f526544a55c242081c7793d22a1c6cd33e663967795a2bbf9c2e78c4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T07:26:36Z","title_canon_sha256":"a5721bcdbda68f2ae458540a32576325134eae2024e93b465728b57ac27f0a02"},"schema_version":"1.0","source":{"id":"2605.14486","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14486","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14486v1","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14486","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"KKSRF7L2D2ZT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"KKSRF7L2D2ZTTAZF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"KKSRF7L2","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:946b2e706fc0e911da882ea9b5e5ab348127fc5729811039081979f7c0714788","target":"graph","created_at":"2026-05-17T23:39:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Rather than merely benefiting GAN-generated image detection, this design introduces diverse and complementary artifact patterns that enable SEF to learn a more robust decision boundary and improve generalization across broader generative methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the proposed GAN-based upsampling produces artifact patterns that are both aligned (content/size/format) with reconstruction fakes and sufficiently distinct to provide complementary information without introducing new unmodeled biases."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A GAN-based upsampling method plus Separate Expert Fusion reduces artifact bias and improves generalization in AI-generated image detection."}],"snapshot_sha256":"7fd062025d9d7bea7f3472a20f1aeafcd4874baabd153e283353af4addf22f26"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"As the misuse of AI-generated images grows, generalizable image detection techniques are urgently needed. Recent state-of-the-art (SOTA) methods adopt aligned training datasets to reduce content, size, and format biases, empowering models to capture robust forgery cues. A common strategy is to employ reconstruction techniques, e.g., VAE and DDIM, which show remarkable results in diffusion-based methods. However, such reconstruction-based approaches typically introduce limited and homogeneous artifacts, which cannot fully capture diverse generative patterns, such as GAN-based methods. To comple","authors_text":"Gao Li, Wenhao Wang, Yang Yang, Yiheng Li, Zhen Lei, Zichang Tan","cross_cats":[],"headline":"A GAN-based upsampling method plus Separate Expert Fusion reduces artifact bias and improves generalization in AI-generated image detection.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T07:26:36Z","title":"Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection"},"references":{"count":68,"internal_anchors":8,"resolved_work":68,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Synthbuster: Towards detection of diffusion model generated images.IEEE Open Journal of Signal Processing, 5:1–9, 2023","work_id":"2febba00-8ed5-42ff-a42c-45224344b8b9","year":2023},{"cited_arxiv_id":"1809.11096","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","work_id":"244e6f06-bad2-4f34-8186-ff370286427f","year":2018},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Zooming in on fakes: A novel dataset for localized ai-generated image detection with forgery amplification approach","work_id":"b34aecdd-ac2e-49c5-9124-c0c7fb332b03","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Emerging properties in self-supervised vision transformers","work_id":"def40bfd-07b5-4f25-94fd-883b4ac6838d","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Real-time deepfake detection in the real-world","work_id":"9493fae4-3b84-47d9-9b27-12baa60d298c","year":2024}],"snapshot_sha256":"d2dfa4238ec4a34659b0762f58bedb56d162eed7f3bc6c56bca208b86708500e"},"source":{"id":"2605.14486","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T02:33:22.200340Z","id":"b99a2f40-c57d-4514-bbcb-187aa876e820","model_set":{"reader":"grok-4.3"},"one_line_summary":"SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A GAN-based upsampling method plus Separate Expert Fusion reduces artifact bias and improves generalization in AI-generated image detection.","strongest_claim":"Rather than merely benefiting GAN-generated image detection, this design introduces diverse and complementary artifact patterns that enable SEF to learn a more robust decision boundary and improve generalization across broader generative methods.","weakest_assumption":"That the proposed GAN-based upsampling produces artifact patterns that are both aligned (content/size/format) with reconstruction fakes and sufficiently distinct to provide complementary information without introducing new unmodeled biases."}},"verdict_id":"b99a2f40-c57d-4514-bbcb-187aa876e820"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5c0ea5087fdd559445be3a707da2101b6fb79085ee965e6fb93d74ed6aa59ed0","target":"record","created_at":"2026-05-17T23:39:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"af00a987f526544a55c242081c7793d22a1c6cd33e663967795a2bbf9c2e78c4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T07:26:36Z","title_canon_sha256":"a5721bcdbda68f2ae458540a32576325134eae2024e93b465728b57ac27f0a02"},"schema_version":"1.0","source":{"id":"2605.14486","kind":"arxiv","version":1}},"canonical_sha256":"52a512fd7a1eb3398325e884ccf681310dd978b2bcc34f0b9b3d3cd60e4cfe7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52a512fd7a1eb3398325e884ccf681310dd978b2bcc34f0b9b3d3cd60e4cfe7a","first_computed_at":"2026-05-17T23:39:06.491082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:06.491082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yGwevubr+fGG2vCA14rIc9aKqTUsphYR20PtmQzxO93Pz+HmWaTm6r36eKVGoNkrRrLZjDblsIUUMk0FgLOmAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:06.491798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14486","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c0ea5087fdd559445be3a707da2101b6fb79085ee965e6fb93d74ed6aa59ed0","sha256:946b2e706fc0e911da882ea9b5e5ab348127fc5729811039081979f7c0714788"],"state_sha256":"deb92795d57bcb71da7165b02895f2b0f5623e8a8059fecac2396be197620c24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R+M5xJEZg/f31sG0dotv+tqtLkHe1zcJrNXVFHefAlpCzVfc79a5nrjqBTIOnsVoTS8fV6q+mN62T6UqaRyOAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T18:47:20.949453Z","bundle_sha256":"73c391b56bcad7e6aad9841ce5d0f061edf3038893ab57e56a698739679f80f6"}}