{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EHWLZ5Z3KU6S72UJJ3HURVUSLL","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":"7e66ea653842ecaa03a6492655c9d36ee39b19a91e7679a81903f877ee0e1ae5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-22T23:35:49Z","title_canon_sha256":"11db789717a56a15ef3776ed2f3237a59cd409572652bf77bcb9b6f46f154ffa"},"schema_version":"1.0","source":{"id":"2606.24014","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24014","created_at":"2026-06-24T01:14:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24014v1","created_at":"2026-06-24T01:14:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24014","created_at":"2026-06-24T01:14:38Z"},{"alias_kind":"pith_short_12","alias_value":"EHWLZ5Z3KU6S","created_at":"2026-06-24T01:14:38Z"},{"alias_kind":"pith_short_16","alias_value":"EHWLZ5Z3KU6S72UJ","created_at":"2026-06-24T01:14:38Z"},{"alias_kind":"pith_short_8","alias_value":"EHWLZ5Z3","created_at":"2026-06-24T01:14:38Z"}],"graph_snapshots":[{"event_id":"sha256:1842eac9900054156b810dc4c59c1dcc913e8e6eb1217770ec6c8ad9f708b1df","target":"graph","created_at":"2026-06-24T01:14:38Z","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/2606.24014/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As AI systems are deployed across increasingly diverse and high-stakes settings, model alignment must generalize beyond the tasks and domains seen during training. This is especially important for reinforcement learning (RL), which can introduce unexpected misalignment through reward hacking, deception, or other unintended strategies. We study whether RL on beneficial behavior, instantiated in realistic domains, can produce broad and persistent alignment generalization beyond the training distribution. We construct a dataset of realistic situations designed to measure and train beneficial trai","authors_text":"Akshay V. Jagadeesh, Ali Malik, Foivos Tsimpourlas, Johannes Heidecke, Karan Singhal, Khaled Saab, Mikhail Trofimov, Rahul K. Arora","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-22T23:35:49Z","title":"Reinforcement Learning Towards Broadly and Persistently Beneficial Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24014","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:b8fc0d8f454262eb01b7a24acc099cda6e22095d6acb6828923685a8d5a53c45","target":"record","created_at":"2026-06-24T01:14:38Z","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":"7e66ea653842ecaa03a6492655c9d36ee39b19a91e7679a81903f877ee0e1ae5","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-22T23:35:49Z","title_canon_sha256":"11db789717a56a15ef3776ed2f3237a59cd409572652bf77bcb9b6f46f154ffa"},"schema_version":"1.0","source":{"id":"2606.24014","kind":"arxiv","version":1}},"canonical_sha256":"21ecbcf73b553d2fea894ecf48d6925ad3dfd8b2d922a7b9d34d2f69eb225a92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21ecbcf73b553d2fea894ecf48d6925ad3dfd8b2d922a7b9d34d2f69eb225a92","first_computed_at":"2026-06-24T01:14:38.192490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:38.192490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sPsDUsu9Ik/qbxhMAdCAHWGn32S9tcvCD3ULkAO2bL2We6PC0GK6n3/JgjIg+nj8ebU/j2qHLOykdXPPlC9WDQ==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:38.192938Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24014","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8fc0d8f454262eb01b7a24acc099cda6e22095d6acb6828923685a8d5a53c45","sha256:1842eac9900054156b810dc4c59c1dcc913e8e6eb1217770ec6c8ad9f708b1df"],"state_sha256":"79f1a9ae23d904e25ddb630da2ff25a37c0e6ba26e11e220471fb3828f103074"}