{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BNWGMZUIJHSC36FQSCQNCWW3C2","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":"4576a47cf54c745786dd16994825354533e991089a0db18b3e7868e8918b8116","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T16:58:42Z","title_canon_sha256":"ee75c75d8105aa1e6834cb625d366a8108e112c246fa74dd0c549a07f1b219fe"},"schema_version":"1.0","source":{"id":"2410.08113","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08113","created_at":"2026-07-05T10:31:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08113v1","created_at":"2026-07-05T10:31:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08113","created_at":"2026-07-05T10:31:24Z"},{"alias_kind":"pith_short_12","alias_value":"BNWGMZUIJHSC","created_at":"2026-07-05T10:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"BNWGMZUIJHSC36FQ","created_at":"2026-07-05T10:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"BNWGMZUI","created_at":"2026-07-05T10:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:ff9352e08671952a352f00d38bea78555b87fc6c65ae2b88e4cdb6978b945f64","target":"graph","created_at":"2026-07-05T10:31:24Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.08113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Growing amount and quality of AI-generated texts makes detecting such content more difficult. In most real-world scenarios, the domain (style and topic) of generated data and the generator model are not known in advance. In this work, we focus on the robustness of classifier-based detectors of AI-generated text, namely their ability to transfer to unseen generators or semantic domains. We investigate the geometry of the embedding space of Transformer-based text encoders and show that clearing out harmful linear subspaces helps to train a robust classifier, ignoring domain-specific spurious fea","authors_text":"Eduard Tulchinskii, German Magai, Irina Piontkovskaya, Kristian Kuznetsov, Laida Kushnareva, Sergey Nikolenko, Serguei Barannikov","cross_cats":["cs.AI","cs.IT","math.IT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T16:58:42Z","title":"Robust AI-Generated Text Detection by Restricted Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08113","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:87253fab32eb3466ad3605f0f506e89e65defbe19207e7a0fb4209276dd3f198","target":"record","created_at":"2026-07-05T10:31:24Z","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":"4576a47cf54c745786dd16994825354533e991089a0db18b3e7868e8918b8116","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T16:58:42Z","title_canon_sha256":"ee75c75d8105aa1e6834cb625d366a8108e112c246fa74dd0c549a07f1b219fe"},"schema_version":"1.0","source":{"id":"2410.08113","kind":"arxiv","version":1}},"canonical_sha256":"0b6c66668849e42df8b090a0d15adb16b4367fa2638bdfe9a732676bbd342111","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b6c66668849e42df8b090a0d15adb16b4367fa2638bdfe9a732676bbd342111","first_computed_at":"2026-07-05T10:31:24.955213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:24.955213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O/jW/VCVWm3dhTV9IU4Vp4hk8Xo2cDwkDEWkdyYcaG0rLdwCjkjXdvr+D1+5zfAL5J2c0mcinN41jP1R5gc/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:24.955780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08113","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87253fab32eb3466ad3605f0f506e89e65defbe19207e7a0fb4209276dd3f198","sha256:ff9352e08671952a352f00d38bea78555b87fc6c65ae2b88e4cdb6978b945f64"],"state_sha256":"4e5cc1b61ec6c890a6427a4bb4d689b74efd5a39ba58d2f9bd98eefe2d09982a"}