{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MRW6BJ2IGHQXBYNXL5QJ2TJPCQ","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":"e138757baea20df8eb4cbe2ac9b4a355d14ebd1895c3d9a73c426cab3a17ba30","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T17:50:27Z","title_canon_sha256":"ab95ac02e67827161183e5ba84c0409decc3345e06a42faec1c239d2b4d45013"},"schema_version":"1.0","source":{"id":"2605.18721","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18721","created_at":"2026-05-20T00:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18721v1","created_at":"2026-05-20T00:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18721","created_at":"2026-05-20T00:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"MRW6BJ2IGHQX","created_at":"2026-05-20T00:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"MRW6BJ2IGHQXBYNX","created_at":"2026-05-20T00:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"MRW6BJ2I","created_at":"2026-05-20T00:06:16Z"}],"graph_snapshots":[{"event_id":"sha256:2108269a4d4cd7021d061731a025e93075bc1b7d1f209d1593518644e6609c5f","target":"graph","created_at":"2026-05-20T00:06:16Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.039302Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18721/integrity.json","findings":[],"snapshot_sha256":"836cd941d4dc2c1550c5cab0f70809201a6dea4f339037c7f7f7e36140c9602b","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Post-training has split large language model (LLM) alignment into two largely disconnected tracks. Online reinforcement learning (RL) with verifiable rewards drives emergent reasoning on math and code but depends on a programmatic verifier that cannot reach open-ended tasks, while preference optimization handles open-ended generation yet forgoes the continuous exploration that powers online RL. Closing this gap requires a verifier for open-ended quality, but a scalar reward model is the wrong shape for the job. Quality is multi-dimensional, and any scalar score is an incomplete proxy that lets","authors_text":"Ahsan Bilal, Andreas Haupt, Arslan Chaudhry, Emily Fox, John M. Cioffi, Muhammad Ahmed Mohsin, Muhammad Umer, Sanmi Koyejo","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T17:50:27Z","title":"General Preference Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18721","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":"sha256:9c3dd24d131a82fe724c515c706901a944e0dc3ef61b552ea80fe81d13329e52","target":"record","created_at":"2026-05-20T00:06:16Z","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":"e138757baea20df8eb4cbe2ac9b4a355d14ebd1895c3d9a73c426cab3a17ba30","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T17:50:27Z","title_canon_sha256":"ab95ac02e67827161183e5ba84c0409decc3345e06a42faec1c239d2b4d45013"},"schema_version":"1.0","source":{"id":"2605.18721","kind":"arxiv","version":1}},"canonical_sha256":"646de0a74831e170e1b75f609d4d2f1429f7858cc6538c1545464904b46fafa2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"646de0a74831e170e1b75f609d4d2f1429f7858cc6538c1545464904b46fafa2","first_computed_at":"2026-05-20T00:06:16.966016Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:06:16.966016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m7MtiTbHS9QYbwA9sm2lkxfdfa9WOKDDc7BFCD3Qwy4zIg+geIb2960FDcgnmw+BozYCHwSnOXzwmaZTzQm3Ag==","signature_status":"signed_v1","signed_at":"2026-05-20T00:06:16.966829Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18721","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c3dd24d131a82fe724c515c706901a944e0dc3ef61b552ea80fe81d13329e52","sha256:2108269a4d4cd7021d061731a025e93075bc1b7d1f209d1593518644e6609c5f"],"state_sha256":"0c735632cadffa341e3718a69af3fc9ca821acd74bbeffd8c1976f0c86f49f08"}