{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MRGU775ATWYD4R6AM6NO6XOF6Q","short_pith_number":"pith:MRGU775A","schema_version":"1.0","canonical_sha256":"644d4fffa09db03e47c0679aef5dc5f42c706c7460c1012d7ac4a355e8b296c9","source":{"kind":"arxiv","id":"2606.06918","version":1},"attestation_state":"computed","paper":{"title":"DRIFT: From Robustness Gaps to Invariance Manifolds for AI-Generated Image Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhishek Ameta, Akshay Janardan Bankar, Amit Satish Unde, Ankita Chatterjee, Harshit, Sayan Banerjee, Shreyas Pandith","submitted_at":"2026-06-05T05:32:57Z","abstract_excerpt":"The rapid evolution of generative image models challenges existing AI-generated image detectors, particularly in open-world settings with unseen generators. Recent training-free approaches measure robustness gaps in frozen vision foundation models (VFMs), detecting fakes via perturbation-induced embedding drift. However, these methods rely on fixed invariance geometry inherited from pretraining and lack principled adaptation to the detection task. We instead formulate AI-generated image detection as learning a structured invariance manifold of real images under one-class supervision. Building "},"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":"2606.06918","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-05T05:32:57Z","cross_cats_sorted":[],"title_canon_sha256":"ac97756d0bcb7fb9f29693f28c29d03e7207b452bd1d3cdc4e352009a062731d","abstract_canon_sha256":"cc2f402dcc6d4e9a75df0fbc5718fa4f860bcc61afe15b29a7a9932081f6c48b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:35.891909Z","signature_b64":"iQRqgg4Dy9KgNrBYgFl9twi/s0F1G8ugqhm+KNXuonxsuwKzGEd4742t76cNIWF0rQMe4RdRplRfpeTKECUoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"644d4fffa09db03e47c0679aef5dc5f42c706c7460c1012d7ac4a355e8b296c9","last_reissued_at":"2026-06-08T01:04:35.891072Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:35.891072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DRIFT: From Robustness Gaps to Invariance Manifolds for AI-Generated Image Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhishek Ameta, Akshay Janardan Bankar, Amit Satish Unde, Ankita Chatterjee, Harshit, Sayan Banerjee, Shreyas Pandith","submitted_at":"2026-06-05T05:32:57Z","abstract_excerpt":"The rapid evolution of generative image models challenges existing AI-generated image detectors, particularly in open-world settings with unseen generators. Recent training-free approaches measure robustness gaps in frozen vision foundation models (VFMs), detecting fakes via perturbation-induced embedding drift. However, these methods rely on fixed invariance geometry inherited from pretraining and lack principled adaptation to the detection task. We instead formulate AI-generated image detection as learning a structured invariance manifold of real images under one-class supervision. Building "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06918","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/2606.06918/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":"2606.06918","created_at":"2026-06-08T01:04:35.891195+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06918v1","created_at":"2026-06-08T01:04:35.891195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06918","created_at":"2026-06-08T01:04:35.891195+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRGU775ATWYD","created_at":"2026-06-08T01:04:35.891195+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRGU775ATWYD4R6A","created_at":"2026-06-08T01:04:35.891195+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRGU775A","created_at":"2026-06-08T01:04:35.891195+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/MRGU775ATWYD4R6AM6NO6XOF6Q","json":"https://pith.science/pith/MRGU775ATWYD4R6AM6NO6XOF6Q.json","graph_json":"https://pith.science/api/pith-number/MRGU775ATWYD4R6AM6NO6XOF6Q/graph.json","events_json":"https://pith.science/api/pith-number/MRGU775ATWYD4R6AM6NO6XOF6Q/events.json","paper":"https://pith.science/paper/MRGU775A"},"agent_actions":{"view_html":"https://pith.science/pith/MRGU775ATWYD4R6AM6NO6XOF6Q","download_json":"https://pith.science/pith/MRGU775ATWYD4R6AM6NO6XOF6Q.json","view_paper":"https://pith.science/paper/MRGU775A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06918&json=true","fetch_graph":"https://pith.science/api/pith-number/MRGU775ATWYD4R6AM6NO6XOF6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/MRGU775ATWYD4R6AM6NO6XOF6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRGU775ATWYD4R6AM6NO6XOF6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRGU775ATWYD4R6AM6NO6XOF6Q/action/storage_attestation","attest_author":"https://pith.science/pith/MRGU775ATWYD4R6AM6NO6XOF6Q/action/author_attestation","sign_citation":"https://pith.science/pith/MRGU775ATWYD4R6AM6NO6XOF6Q/action/citation_signature","submit_replication":"https://pith.science/pith/MRGU775ATWYD4R6AM6NO6XOF6Q/action/replication_record"}},"created_at":"2026-06-08T01:04:35.891195+00:00","updated_at":"2026-06-08T01:04:35.891195+00:00"}