{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:P5H23MBQ22NRWCMGHCELTWIJ2S","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":"defde27fce502e3e7ebc00d28ba2f59566050630026203fc391d16df36281a81","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-21T10:57:09Z","title_canon_sha256":"b4ad81fd13a950b828ba651e0f071216f8a9f3bea3f67a3e9cb19e378491b53e"},"schema_version":"1.0","source":{"id":"2607.18966","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18966","created_at":"2026-07-22T01:23:22Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18966v1","created_at":"2026-07-22T01:23:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18966","created_at":"2026-07-22T01:23:22Z"},{"alias_kind":"pith_short_12","alias_value":"P5H23MBQ22NR","created_at":"2026-07-22T01:23:22Z"},{"alias_kind":"pith_short_16","alias_value":"P5H23MBQ22NRWCMG","created_at":"2026-07-22T01:23:22Z"},{"alias_kind":"pith_short_8","alias_value":"P5H23MBQ","created_at":"2026-07-22T01:23:22Z"}],"graph_snapshots":[{"event_id":"sha256:078ffc9378d418e495015ab92fd630924bb8904c9a8df438cbd9694355e81ccc","target":"graph","created_at":"2026-07-22T01:23:22Z","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/2607.18966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models trained with reinforcement learning may learn to optimize the grader's judgment rather than the intended objective. This \"reward-seeking\" is difficult to measure because a model that pursues the grader's judgment and one that pursues the intended objective behave identically whenever the grader rewards the intended behavior. We measure reward-seeking using Contrastive Synthetic Document Finetuning to change a model's beliefs about what the grader rewards, putting those beliefs in conflict with what users or developers want, and measuring the rate at which the model adopts each ","authors_text":"Alexander Meinke, Axel H{\\o}jmark, Bronson Schoen, Evgenia Nitishinskaya, Felix Hofst\\\"atter, Jason Wolfe, J\\'er\\'emy Scheurer, Theodore Ehrenborg","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-21T10:57:09Z","title":"Measuring Reward-Seeking via Contrastive Belief Updates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18966","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":"sha256:7274facf7947a66323dfb1c65089d8d6761a65b498ad43db473da05cd3e011ec","target":"record","created_at":"2026-07-22T01:23:22Z","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":"defde27fce502e3e7ebc00d28ba2f59566050630026203fc391d16df36281a81","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-21T10:57:09Z","title_canon_sha256":"b4ad81fd13a950b828ba651e0f071216f8a9f3bea3f67a3e9cb19e378491b53e"},"schema_version":"1.0","source":{"id":"2607.18966","kind":"arxiv","version":1}},"canonical_sha256":"7f4fadb030d69b1b09863888b9d909d4b01c52bcc10ea49ae455fd2731577a1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f4fadb030d69b1b09863888b9d909d4b01c52bcc10ea49ae455fd2731577a1f","first_computed_at":"2026-07-22T01:23:22.215176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:23:22.215176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b+DHnVD7vmgAJ5zXxL7mZT9P8ABt9ZscMX7ws7pIvhDpIYDKku5tu2wER/LdqKXIwgSWH5zKUYndUK1XXjZYDg==","signature_status":"signed_v1","signed_at":"2026-07-22T01:23:22.216086Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18966","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7274facf7947a66323dfb1c65089d8d6761a65b498ad43db473da05cd3e011ec","sha256:078ffc9378d418e495015ab92fd630924bb8904c9a8df438cbd9694355e81ccc"],"state_sha256":"f1080db57e2817bab74e69cdd016bb9a6c4c2e8dc0275dae83aff895a7986deb"}