{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M4ZCIMTOEYJT6GSEBA6FLVY3ZJ","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":"576f9b213aa6a9fcc2bcdc82f786a92707af58bbc64a6fc42620e337fd963a02","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T00:35:54Z","title_canon_sha256":"6597ce8a4bea34fb770c04b01bd61d948464f00203abb3b7d5ce93b7070ed65d"},"schema_version":"1.0","source":{"id":"2606.08893","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08893","created_at":"2026-06-09T02:07:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08893v1","created_at":"2026-06-09T02:07:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08893","created_at":"2026-06-09T02:07:45Z"},{"alias_kind":"pith_short_12","alias_value":"M4ZCIMTOEYJT","created_at":"2026-06-09T02:07:45Z"},{"alias_kind":"pith_short_16","alias_value":"M4ZCIMTOEYJT6GSE","created_at":"2026-06-09T02:07:45Z"},{"alias_kind":"pith_short_8","alias_value":"M4ZCIMTO","created_at":"2026-06-09T02:07:45Z"}],"graph_snapshots":[{"event_id":"sha256:d4ce3ca1d877dd026e0963b43211bbacbab14d49e15ac9bf36c8e7dff06aa5f1","target":"graph","created_at":"2026-06-09T02:07:45Z","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/2606.08893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A small transformer encoder is trained to map Terminal-Wrench trajectories onto a unit sphere where embedding distance approximates the $L_1$ distance between reward and metadata signals. A linear probe on top of that embedding detects reward hacking on the cleaned test split with AUC $0.9467$ and TPR@5%FPR $0.8296$, matching the TW sanitized LLM-as-judge AUC ($0.9510$ on the cleaned split) and exceeding its TPR@5%FPR ($0.7130$ vs $0.8296$) on the same information condition, at roughly four orders of magnitude lower per-trajectory cost. The encoder is not a pure behavior reader: stripping natu","authors_text":"Iv\\'an Belenky, Joaqu\\'in Itria, Steven Johns","cross_cats":["cs.AI","cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T00:35:54Z","title":"Cheap Reward Hacking Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08893","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":"sha256:29358f0b330385dc8bab4d866ef8265456c3da30c9e82a0842c053ad8cd7e2e0","target":"record","created_at":"2026-06-09T02:07:45Z","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":"576f9b213aa6a9fcc2bcdc82f786a92707af58bbc64a6fc42620e337fd963a02","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T00:35:54Z","title_canon_sha256":"6597ce8a4bea34fb770c04b01bd61d948464f00203abb3b7d5ce93b7070ed65d"},"schema_version":"1.0","source":{"id":"2606.08893","kind":"arxiv","version":1}},"canonical_sha256":"673224326e26133f1a44083c55d71bca7f86832afe205b797249ef50fe83b467","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"673224326e26133f1a44083c55d71bca7f86832afe205b797249ef50fe83b467","first_computed_at":"2026-06-09T02:07:45.655852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:45.655852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iFNOe5BKmngw+PShvESMXkoa5Qc4qyWDs0xRRvj96kASP3qU+KrikuPFdXT7QdzG/MrI4cGV2ZHxL4/p2v5RDw==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:45.656711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08893","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29358f0b330385dc8bab4d866ef8265456c3da30c9e82a0842c053ad8cd7e2e0","sha256:d4ce3ca1d877dd026e0963b43211bbacbab14d49e15ac9bf36c8e7dff06aa5f1"],"state_sha256":"2c635fdb87c81ff0db9a383a7f005c89f49fbbb1709cd9ad5c2b5e763ced7ed0"}