{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TMQYUJLVSFOTOY7BF4SBVCLE3H","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":"ccf27647ca044b771adc0168f87d893d0e04b23eaff44601efae0d2ea2b80720","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:46:52Z","title_canon_sha256":"ff5952a0782a4f82d008f6b9aa8b23f902160f2a4cf95d62571be7febb17754b"},"schema_version":"1.0","source":{"id":"2605.20744","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20744","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20744v1","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20744","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"pith_short_12","alias_value":"TMQYUJLVSFOT","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"pith_short_16","alias_value":"TMQYUJLVSFOTOY7B","created_at":"2026-05-21T01:04:51Z"},{"alias_kind":"pith_short_8","alias_value":"TMQYUJLV","created_at":"2026-05-21T01:04:51Z"}],"graph_snapshots":[{"event_id":"sha256:b560707d1304d2f413f02b086c13a101c9c2f977d43ba200ff8a0f1b40f8d9d3","target":"graph","created_at":"2026-05-21T01:04:51Z","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/2605.20744/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning autonomous agents with human intent remains a central challenge in modern AI. A key manifestation of this challenge is reward hacking, whereby agents appear successful under the evaluation signal while violating the intended objective. Reward hacking has been observed across a wide range of settings, yet methods for reliably measuring it at scale remain lacking. In this work, we introduce a new evaluation paradigm for measuring reward hacking. Whereas prior studies have primarily analyzed it post hoc by inspecting agent trajectories, we instead embed detectable reward hacking opportun","authors_text":"Amit Roth, Ankur Samanta, Matan Halevy, Yoav Levine, Yonathan Efroni","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:46:52Z","title":"Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20744","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":"sha256:3a98bfbeb834e1e7192df4fbc832ac0e8cc5371245ce8db8a30dcc433982f2ff","target":"record","created_at":"2026-05-21T01:04:51Z","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":"ccf27647ca044b771adc0168f87d893d0e04b23eaff44601efae0d2ea2b80720","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T05:46:52Z","title_canon_sha256":"ff5952a0782a4f82d008f6b9aa8b23f902160f2a4cf95d62571be7febb17754b"},"schema_version":"1.0","source":{"id":"2605.20744","kind":"arxiv","version":1}},"canonical_sha256":"9b218a2575915d3763e12f241a8964d9e9f4f45121078606b7defffe5879c306","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b218a2575915d3763e12f241a8964d9e9f4f45121078606b7defffe5879c306","first_computed_at":"2026-05-21T01:04:51.881137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:51.881137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CYmHEX1hz3d5oMnBRDC63UGf5M44O1XbRuozZHrvcmbc/i0oxMPMyZLTIrEyGqGq9PAy3MWgOgdnMUE3axVBDA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:51.881903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20744","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a98bfbeb834e1e7192df4fbc832ac0e8cc5371245ce8db8a30dcc433982f2ff","sha256:b560707d1304d2f413f02b086c13a101c9c2f977d43ba200ff8a0f1b40f8d9d3"],"state_sha256":"80932e31e6f895b336aca9ae6e6e991aca70fb03bfa59806922cf17a6950df90"}