{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RMP537M7WDA32QLPJFEQD62SET","short_pith_number":"pith:RMP537M7","schema_version":"1.0","canonical_sha256":"8b1fddfd9fb0c1bd416f494901fb5224c6bf9a224944352a4ceb663c06b824c1","source":{"kind":"arxiv","id":"2605.22751","version":1},"attestation_state":"computed","paper":{"title":"Spectral Tail Auxiliary Learning for AI-Generated Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiahui Zhang, Wenhao Wang, Xingyi Li, Yiheng Li, Yun Cao","submitted_at":"2026-05-21T17:20:59Z","abstract_excerpt":"As generative image models evolve rapidly, the perceptual gap between generated and real images continues to narrow, making AI-generated image detection increasingly challenging. Many existing methods exploit frequency-domain cues for detection, typically described as frequency-domain artifacts or high-frequency discrepancies. However, the specific and recurring spectral regularities remain insufficiently understood and characterized. In this paper, we systematically analyze the one-dimensional radial log-power spectra of real and generated images. We find that generated images do not necessar"},"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":"2605.22751","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T17:20:59Z","cross_cats_sorted":[],"title_canon_sha256":"1b037c9071afdf6b3b20dde753e80adbef348d32ad0012fd81e0f80c30193555","abstract_canon_sha256":"582a60ffcc7ae04114f171eaab141912cf38f9b16e292ca316ec915133e0a5e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T02:04:53.254709Z","signature_b64":"cCLINtV3TWkN3EJOBUs6F12nqGJIU+U7xHEORTHmu75EAaWROxggHtKx7vPShPIubFfw1ISV5sSlN58t3SVXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b1fddfd9fb0c1bd416f494901fb5224c6bf9a224944352a4ceb663c06b824c1","last_reissued_at":"2026-05-22T02:04:53.254026Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T02:04:53.254026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spectral Tail Auxiliary Learning for AI-Generated Image Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiahui Zhang, Wenhao Wang, Xingyi Li, Yiheng Li, Yun Cao","submitted_at":"2026-05-21T17:20:59Z","abstract_excerpt":"As generative image models evolve rapidly, the perceptual gap between generated and real images continues to narrow, making AI-generated image detection increasingly challenging. Many existing methods exploit frequency-domain cues for detection, typically described as frequency-domain artifacts or high-frequency discrepancies. However, the specific and recurring spectral regularities remain insufficiently understood and characterized. In this paper, we systematically analyze the one-dimensional radial log-power spectra of real and generated images. We find that generated images do not necessar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22751","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/2605.22751/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":"2605.22751","created_at":"2026-05-22T02:04:53.254159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22751v1","created_at":"2026-05-22T02:04:53.254159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22751","created_at":"2026-05-22T02:04:53.254159+00:00"},{"alias_kind":"pith_short_12","alias_value":"RMP537M7WDA3","created_at":"2026-05-22T02:04:53.254159+00:00"},{"alias_kind":"pith_short_16","alias_value":"RMP537M7WDA32QLP","created_at":"2026-05-22T02:04:53.254159+00:00"},{"alias_kind":"pith_short_8","alias_value":"RMP537M7","created_at":"2026-05-22T02:04:53.254159+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RMP537M7WDA32QLPJFEQD62SET","json":"https://pith.science/pith/RMP537M7WDA32QLPJFEQD62SET.json","graph_json":"https://pith.science/api/pith-number/RMP537M7WDA32QLPJFEQD62SET/graph.json","events_json":"https://pith.science/api/pith-number/RMP537M7WDA32QLPJFEQD62SET/events.json","paper":"https://pith.science/paper/RMP537M7"},"agent_actions":{"view_html":"https://pith.science/pith/RMP537M7WDA32QLPJFEQD62SET","download_json":"https://pith.science/pith/RMP537M7WDA32QLPJFEQD62SET.json","view_paper":"https://pith.science/paper/RMP537M7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22751&json=true","fetch_graph":"https://pith.science/api/pith-number/RMP537M7WDA32QLPJFEQD62SET/graph.json","fetch_events":"https://pith.science/api/pith-number/RMP537M7WDA32QLPJFEQD62SET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RMP537M7WDA32QLPJFEQD62SET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RMP537M7WDA32QLPJFEQD62SET/action/storage_attestation","attest_author":"https://pith.science/pith/RMP537M7WDA32QLPJFEQD62SET/action/author_attestation","sign_citation":"https://pith.science/pith/RMP537M7WDA32QLPJFEQD62SET/action/citation_signature","submit_replication":"https://pith.science/pith/RMP537M7WDA32QLPJFEQD62SET/action/replication_record"}},"created_at":"2026-05-22T02:04:53.254159+00:00","updated_at":"2026-05-22T02:04:53.254159+00:00"}