{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AS72SQJEL4GTAUJ5MBIP7NZ2J3","short_pith_number":"pith:AS72SQJE","schema_version":"1.0","canonical_sha256":"04bfa941245f0d30513d6050ffb73a4ee8bd0d99e5fb5ab522ebf9351c155e16","source":{"kind":"arxiv","id":"2606.00872","version":1},"attestation_state":"computed","paper":{"title":"Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jan Philip Walter, Margret Keuper, Shashank Agnihotri","submitted_at":"2026-05-30T20:00:25Z","abstract_excerpt":"AI-generated image detection is a moving-target problem: detectors trained on one generator often fail when a new generator appears, and only a few labeled examples are available. We study a simple image-to-table formulation for this regime, where each image is encoded by a frozen DINOv3 backbone, its CLS feature is reduced to a 500-dimensional structured row with PCA, and TabPFN performs real/fake classification by in-context tabular inference rather than task-specific classifier training. This turns fake-image detection into low-data structured prediction over learned visual features, making"},"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":"2606.00872","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-30T20:00:25Z","cross_cats_sorted":[],"title_canon_sha256":"d5785ddacd276a5a6aa06dbd8e3c1eac9dd574526059c14444d99bd0d4fddb2b","abstract_canon_sha256":"01482560cace25a90dc895e087b4f0c7b34334addf69685521e5ab1f4e5ce644"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:08.458140Z","signature_b64":"DLoEPK4mhSSD7/uSRrBsZko6kU+FizBFEk4cmzdNgtUJuJc6CLpyB9dpFA7RGzMPGZYHe3l2IjCnFABcafnyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04bfa941245f0d30513d6050ffb73a4ee8bd0d99e5fb5ab522ebf9351c155e16","last_reissued_at":"2026-06-02T01:04:08.457725Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:08.457725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Images as Tables: In-Context Learning with TabPFN for Low-Data Detection of AI-Generated Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jan Philip Walter, Margret Keuper, Shashank Agnihotri","submitted_at":"2026-05-30T20:00:25Z","abstract_excerpt":"AI-generated image detection is a moving-target problem: detectors trained on one generator often fail when a new generator appears, and only a few labeled examples are available. We study a simple image-to-table formulation for this regime, where each image is encoded by a frozen DINOv3 backbone, its CLS feature is reduced to a 500-dimensional structured row with PCA, and TabPFN performs real/fake classification by in-context tabular inference rather than task-specific classifier training. This turns fake-image detection into low-data structured prediction over learned visual features, making"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00872","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/2606.00872/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":"2606.00872","created_at":"2026-06-02T01:04:08.457782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00872v1","created_at":"2026-06-02T01:04:08.457782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00872","created_at":"2026-06-02T01:04:08.457782+00:00"},{"alias_kind":"pith_short_12","alias_value":"AS72SQJEL4GT","created_at":"2026-06-02T01:04:08.457782+00:00"},{"alias_kind":"pith_short_16","alias_value":"AS72SQJEL4GTAUJ5","created_at":"2026-06-02T01:04:08.457782+00:00"},{"alias_kind":"pith_short_8","alias_value":"AS72SQJE","created_at":"2026-06-02T01:04:08.457782+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/AS72SQJEL4GTAUJ5MBIP7NZ2J3","json":"https://pith.science/pith/AS72SQJEL4GTAUJ5MBIP7NZ2J3.json","graph_json":"https://pith.science/api/pith-number/AS72SQJEL4GTAUJ5MBIP7NZ2J3/graph.json","events_json":"https://pith.science/api/pith-number/AS72SQJEL4GTAUJ5MBIP7NZ2J3/events.json","paper":"https://pith.science/paper/AS72SQJE"},"agent_actions":{"view_html":"https://pith.science/pith/AS72SQJEL4GTAUJ5MBIP7NZ2J3","download_json":"https://pith.science/pith/AS72SQJEL4GTAUJ5MBIP7NZ2J3.json","view_paper":"https://pith.science/paper/AS72SQJE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00872&json=true","fetch_graph":"https://pith.science/api/pith-number/AS72SQJEL4GTAUJ5MBIP7NZ2J3/graph.json","fetch_events":"https://pith.science/api/pith-number/AS72SQJEL4GTAUJ5MBIP7NZ2J3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AS72SQJEL4GTAUJ5MBIP7NZ2J3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AS72SQJEL4GTAUJ5MBIP7NZ2J3/action/storage_attestation","attest_author":"https://pith.science/pith/AS72SQJEL4GTAUJ5MBIP7NZ2J3/action/author_attestation","sign_citation":"https://pith.science/pith/AS72SQJEL4GTAUJ5MBIP7NZ2J3/action/citation_signature","submit_replication":"https://pith.science/pith/AS72SQJEL4GTAUJ5MBIP7NZ2J3/action/replication_record"}},"created_at":"2026-06-02T01:04:08.457782+00:00","updated_at":"2026-06-02T01:04:08.457782+00:00"}