{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6Z6SGOOZBIBMZHMB5M3QWTPNA2","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":"76b87c27153b95e3a0e89147aa1f92e16e1a4018b1e8c40f199c55f833538cb2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-18T09:44:12Z","title_canon_sha256":"b2a44c01ec7db09138c2c61daf2e316cb91e6441afb0e01ac61ab9663faa5bae"},"schema_version":"1.0","source":{"id":"2606.20008","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20008","created_at":"2026-06-19T16:13:00Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20008v1","created_at":"2026-06-19T16:13:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20008","created_at":"2026-06-19T16:13:00Z"},{"alias_kind":"pith_short_12","alias_value":"6Z6SGOOZBIBM","created_at":"2026-06-19T16:13:00Z"},{"alias_kind":"pith_short_16","alias_value":"6Z6SGOOZBIBMZHMB","created_at":"2026-06-19T16:13:00Z"},{"alias_kind":"pith_short_8","alias_value":"6Z6SGOOZ","created_at":"2026-06-19T16:13:00Z"}],"graph_snapshots":[{"event_id":"sha256:c5875f2917978a6fdfef0f0d9e23734d203c5ae6c337d033824ab75eff1d3ffd","target":"graph","created_at":"2026-06-19T16:13:00Z","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/2606.20008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards has become a central tool for improving the reasoning ability of large language models, but current methods face a trade-off between simplicity and credit assignment. Group-relative methods such as GRPO avoid training a critic, but typically assign a trajectory-level advantage to every token. Actor-critic methods provide denser learning signals, but require a learned value function with its own training instability. We introduce VIMPO, a critic-free policy optimization method that derives a policy-implied value function from the optimality conditi","authors_text":"Aosong Feng, Dawn Song, Sergey Levine, Xuandong Zhao, Zhewei Kang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-18T09:44:12Z","title":"VIMPO: Value-Implicit Policy Optimization for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20008","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":"sha256:3498db49003fb0702b10049c4df69e4d778d3ad436d8408dad25bd9d2ad2598e","target":"record","created_at":"2026-06-19T16:13:00Z","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":"76b87c27153b95e3a0e89147aa1f92e16e1a4018b1e8c40f199c55f833538cb2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-18T09:44:12Z","title_canon_sha256":"b2a44c01ec7db09138c2c61daf2e316cb91e6441afb0e01ac61ab9663faa5bae"},"schema_version":"1.0","source":{"id":"2606.20008","kind":"arxiv","version":1}},"canonical_sha256":"f67d2339d90a02cc9d81eb370b4ded069ebb1131243f75b4dbd88b0150171590","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f67d2339d90a02cc9d81eb370b4ded069ebb1131243f75b4dbd88b0150171590","first_computed_at":"2026-06-19T16:13:00.500424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:13:00.500424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8711B4kobtOD+qNRWDOIcl/t8BC5LBM1LqbS1uqyxirFeIwg0VCEyZP66YHKeY7nm4CqOKrKVaduu/LCrUVWDw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:13:00.500773Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20008","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3498db49003fb0702b10049c4df69e4d778d3ad436d8408dad25bd9d2ad2598e","sha256:c5875f2917978a6fdfef0f0d9e23734d203c5ae6c337d033824ab75eff1d3ffd"],"state_sha256":"8bba4cbd901645c7cc6ebbbcc61994d51a4b653b5e984cfbbd188a37f03d864a"}