{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UQW55I5CTWMUGUCOTCVZ2SJZV5","short_pith_number":"pith:UQW55I5C","canonical_record":{"source":{"id":"2502.19716","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T03:14:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6cd9821992715a84a7ba3bd55868e2378f4c84009654633f12aa404afcd78e4c","abstract_canon_sha256":"bc1d224b881fb6abb2ec09ffc0346fcc391917b1b7e2cb4f64a3c252be179998"},"schema_version":"1.0"},"canonical_sha256":"a42ddea3a29d9943504e98ab9d4939af7632e2c32671da81b3d231be5d2e46ff","source":{"kind":"arxiv","id":"2502.19716","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19716","created_at":"2026-07-16T01:22:24Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19716v3","created_at":"2026-07-16T01:22:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19716","created_at":"2026-07-16T01:22:24Z"},{"alias_kind":"pith_short_12","alias_value":"UQW55I5CTWMU","created_at":"2026-07-16T01:22:24Z"},{"alias_kind":"pith_short_16","alias_value":"UQW55I5CTWMUGUCO","created_at":"2026-07-16T01:22:24Z"},{"alias_kind":"pith_short_8","alias_value":"UQW55I5C","created_at":"2026-07-16T01:22:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UQW55I5CTWMUGUCOTCVZ2SJZV5","target":"record","payload":{"canonical_record":{"source":{"id":"2502.19716","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T03:14:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6cd9821992715a84a7ba3bd55868e2378f4c84009654633f12aa404afcd78e4c","abstract_canon_sha256":"bc1d224b881fb6abb2ec09ffc0346fcc391917b1b7e2cb4f64a3c252be179998"},"schema_version":"1.0"},"canonical_sha256":"a42ddea3a29d9943504e98ab9d4939af7632e2c32671da81b3d231be5d2e46ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:22:24.793963Z","signature_b64":"dW7DIThFWrwz4Gy+2jcxA0l1sUwjsfyAtdjU/GXEMohr2Zpx374wou0DUsNWsAeR+D2TFHO3/6tghcMzrUVrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a42ddea3a29d9943504e98ab9d4939af7632e2c32671da81b3d231be5d2e46ff","last_reissued_at":"2026-07-16T01:22:24.793012Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:22:24.793012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.19716","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-16T01:22:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rw7JiQwoYo9oUu2n06KdYqXZjP4i5a2RnyLxkXIUkN04szifPcaH29Jeoy1bpaKsx/Oo/H24Jcodni93R50BDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:52:54.253518Z"},"content_sha256":"2f8b05f71f7253a1f688bc2deda6b2f723dba94899e9ca0ced6824a301bb55fc","schema_version":"1.0","event_id":"sha256:2f8b05f71f7253a1f688bc2deda6b2f723dba94899e9ca0ced6824a301bb55fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UQW55I5CTWMUGUCOTCVZ2SJZV5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Fully AI-generated image detectors are organized by the inductive priors they use to extract generation artifacts, with dataset choices controlling generalization.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Can Wang, Defang Chen, Jiawei Chen, Qijie Xu, Siwei Lyu","submitted_at":"2025-02-27T03:14:40Z","abstract_excerpt":"Recent advances in visual generative models have enabled the creation of highly realistic, fully AI-generated images without relying on real source content. While beneficial for many applications, these models also pose significant societal risks, as they can be easily exploited to produce convincing Deepfakes. Detecting them represents a foundational yet challenging problem in AI media forensics, requiring detectors to reliably extract the inherent artifacts imprinted by generative architectures. In this Review, we provide a systematic overview of fully AI-generated image detection. Following"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Detecting fully AI-generated images requires reliably extracting the inherent artifacts imprinted by generative architectures, and existing methods can be categorized based on the primary inductive priors leveraged to isolate artifacts while dataset design influences generalization and robustness.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the body of existing literature can be systematically and comprehensively categorized using the proposed framework of inductive priors for artifact extraction, and that this categorization accurately reflects how dataset choices affect detector performance (stated in the abstract's description of the review structure).","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A systematic review of fully AI-generated image detection that organizes prior work around dataset construction and artifact extraction methods based on inductive priors.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Fully AI-generated image detectors are organized by the inductive priors they use to extract generation artifacts, with dataset choices controlling generalization.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9df76ae16e9e497aa71343e0e37480f0345f361032e224d1135b720869d3cf92"},"source":{"id":"2502.19716","kind":"arxiv","version":3},"verdict":{"id":"f27abc3a-a5db-4977-bd65-534128cc38d1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-23T03:08:48.194150Z","strongest_claim":"Detecting fully AI-generated images requires reliably extracting the inherent artifacts imprinted by generative architectures, and existing methods can be categorized based on the primary inductive priors leveraged to isolate artifacts while dataset design influences generalization and robustness.","one_line_summary":"A systematic review of fully AI-generated image detection that organizes prior work around dataset construction and artifact extraction methods based on inductive priors.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the body of existing literature can be systematically and comprehensively categorized using the proposed framework of inductive priors for artifact extraction, and that this categorization accurately reflects how dataset choices affect detector performance (stated in the abstract's description of the review structure).","pith_extraction_headline":"Fully AI-generated image detectors are organized by the inductive priors they use to extract generation artifacts, with dataset choices controlling generalization."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.19716/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"},"verdict_id":"f27abc3a-a5db-4977-bd65-534128cc38d1"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-16T01:22:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wK96a7D8S3znwfdzG1LhnP8bFJjiaXDtNAeV8SlG6S2ZS5nJ3CWeHV1z7kf+/SkwVWSVroSd4ykooBOjvP70CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:52:54.254383Z"},"content_sha256":"5ebdb76f67f656d0d3887b23decf05a456680cecf03d0503eb33d2d3d26c88b9","schema_version":"1.0","event_id":"sha256:5ebdb76f67f656d0d3887b23decf05a456680cecf03d0503eb33d2d3d26c88b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UQW55I5CTWMUGUCOTCVZ2SJZV5/bundle.json","state_url":"https://pith.science/pith/UQW55I5CTWMUGUCOTCVZ2SJZV5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UQW55I5CTWMUGUCOTCVZ2SJZV5/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":"2026-08-04T04:52:54Z","links":{"resolver":"https://pith.science/pith/UQW55I5CTWMUGUCOTCVZ2SJZV5","bundle":"https://pith.science/pith/UQW55I5CTWMUGUCOTCVZ2SJZV5/bundle.json","state":"https://pith.science/pith/UQW55I5CTWMUGUCOTCVZ2SJZV5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UQW55I5CTWMUGUCOTCVZ2SJZV5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UQW55I5CTWMUGUCOTCVZ2SJZV5","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":"bc1d224b881fb6abb2ec09ffc0346fcc391917b1b7e2cb4f64a3c252be179998","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T03:14:40Z","title_canon_sha256":"6cd9821992715a84a7ba3bd55868e2378f4c84009654633f12aa404afcd78e4c"},"schema_version":"1.0","source":{"id":"2502.19716","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.19716","created_at":"2026-07-16T01:22:24Z"},{"alias_kind":"arxiv_version","alias_value":"2502.19716v3","created_at":"2026-07-16T01:22:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19716","created_at":"2026-07-16T01:22:24Z"},{"alias_kind":"pith_short_12","alias_value":"UQW55I5CTWMU","created_at":"2026-07-16T01:22:24Z"},{"alias_kind":"pith_short_16","alias_value":"UQW55I5CTWMUGUCO","created_at":"2026-07-16T01:22:24Z"},{"alias_kind":"pith_short_8","alias_value":"UQW55I5C","created_at":"2026-07-16T01:22:24Z"}],"graph_snapshots":[{"event_id":"sha256:5ebdb76f67f656d0d3887b23decf05a456680cecf03d0503eb33d2d3d26c88b9","target":"graph","created_at":"2026-07-16T01:22:24Z","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":"Detecting fully AI-generated images requires reliably extracting the inherent artifacts imprinted by generative architectures, and existing methods can be categorized based on the primary inductive priors leveraged to isolate artifacts while dataset design influences generalization and robustness."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the body of existing literature can be systematically and comprehensively categorized using the proposed framework of inductive priors for artifact extraction, and that this categorization accurately reflects how dataset choices affect detector performance (stated in the abstract's description of the review structure)."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A systematic review of fully AI-generated image detection that organizes prior work around dataset construction and artifact extraction methods based on inductive priors."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Fully AI-generated image detectors are organized by the inductive priors they use to extract generation artifacts, with dataset choices controlling generalization."}],"snapshot_sha256":"9df76ae16e9e497aa71343e0e37480f0345f361032e224d1135b720869d3cf92"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.19716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in visual generative models have enabled the creation of highly realistic, fully AI-generated images without relying on real source content. While beneficial for many applications, these models also pose significant societal risks, as they can be easily exploited to produce convincing Deepfakes. Detecting them represents a foundational yet challenging problem in AI media forensics, requiring detectors to reliably extract the inherent artifacts imprinted by generative architectures. In this Review, we provide a systematic overview of fully AI-generated image detection. Following","authors_text":"Can Wang, Defang Chen, Jiawei Chen, Qijie Xu, Siwei Lyu","cross_cats":["cs.LG"],"headline":"Fully AI-generated image detectors are organized by the inductive priors they use to extract generation artifacts, with dataset choices controlling generalization.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T03:14:40Z","title":"Fully AI-Generated Image Detection: Definition, Recent Advances and Challenges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19716","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-23T03:08:48.194150Z","id":"f27abc3a-a5db-4977-bd65-534128cc38d1","model_set":{"reader":"grok-4.3"},"one_line_summary":"A systematic review of fully AI-generated image detection that organizes prior work around dataset construction and artifact extraction methods based on inductive priors.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Fully AI-generated image detectors are organized by the inductive priors they use to extract generation artifacts, with dataset choices controlling generalization.","strongest_claim":"Detecting fully AI-generated images requires reliably extracting the inherent artifacts imprinted by generative architectures, and existing methods can be categorized based on the primary inductive priors leveraged to isolate artifacts while dataset design influences generalization and robustness.","weakest_assumption":"That the body of existing literature can be systematically and comprehensively categorized using the proposed framework of inductive priors for artifact extraction, and that this categorization accurately reflects how dataset choices affect detector performance (stated in the abstract's description of the review structure)."}},"verdict_id":"f27abc3a-a5db-4977-bd65-534128cc38d1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2f8b05f71f7253a1f688bc2deda6b2f723dba94899e9ca0ced6824a301bb55fc","target":"record","created_at":"2026-07-16T01:22:24Z","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":"bc1d224b881fb6abb2ec09ffc0346fcc391917b1b7e2cb4f64a3c252be179998","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T03:14:40Z","title_canon_sha256":"6cd9821992715a84a7ba3bd55868e2378f4c84009654633f12aa404afcd78e4c"},"schema_version":"1.0","source":{"id":"2502.19716","kind":"arxiv","version":3}},"canonical_sha256":"a42ddea3a29d9943504e98ab9d4939af7632e2c32671da81b3d231be5d2e46ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a42ddea3a29d9943504e98ab9d4939af7632e2c32671da81b3d231be5d2e46ff","first_computed_at":"2026-07-16T01:22:24.793012Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T01:22:24.793012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dW7DIThFWrwz4Gy+2jcxA0l1sUwjsfyAtdjU/GXEMohr2Zpx374wou0DUsNWsAeR+D2TFHO3/6tghcMzrUVrBQ==","signature_status":"signed_v1","signed_at":"2026-07-16T01:22:24.793963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.19716","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f8b05f71f7253a1f688bc2deda6b2f723dba94899e9ca0ced6824a301bb55fc","sha256:5ebdb76f67f656d0d3887b23decf05a456680cecf03d0503eb33d2d3d26c88b9"],"state_sha256":"4e6ef41be212f95368c1039317a81b270d94c32c540574ef51e212d84468603e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rgoOOfVsjPdyTUvGxY+8n8In84P8AR30zqKc7D//wbSBw43uU3RwIEPT2MeQwC6mT8oRXr9nRGs+uUOVFrJeBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:52:54.258911Z","bundle_sha256":"20e2145d63e1cc3e5ea920b13f661dcd4fbe960656fb5a727d9276a9d1f60631"}}