{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HVIUSVTD4GCUGDRNAQIR5ABBNM","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":"b5ec6043c5b95acd9224bb74a153e367e69030ac7183da4370893736fa37d1d9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T09:08:29Z","title_canon_sha256":"906154250532658ef23c5a700b1d59a55b9b67d7d671bd2687400cb2017e1e2c"},"schema_version":"1.0","source":{"id":"2606.09887","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09887","created_at":"2026-06-10T00:08:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09887v1","created_at":"2026-06-10T00:08:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09887","created_at":"2026-06-10T00:08:31Z"},{"alias_kind":"pith_short_12","alias_value":"HVIUSVTD4GCU","created_at":"2026-06-10T00:08:31Z"},{"alias_kind":"pith_short_16","alias_value":"HVIUSVTD4GCUGDRN","created_at":"2026-06-10T00:08:31Z"},{"alias_kind":"pith_short_8","alias_value":"HVIUSVTD","created_at":"2026-06-10T00:08:31Z"}],"graph_snapshots":[{"event_id":"sha256:c501086d33553849ecff252d2399058a1f0671a968dda1dfc2c20a2bbdb965ca","target":"graph","created_at":"2026-06-10T00:08:31Z","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/2606.09887/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) for large language models usually supervises reasoning with scalar outcome rewards, such as binary correctness. Such rewards provide an optimization direction but rarely explain how a model should revise its mistaken reasoning, which can encourage shortcut learning and brittle policies. We propose \\textbf{SocraticPO} (Socratic Policy Optimization), a policy-optimization framework that augments RL rollouts with Socratic-style natural-language guidance. During rollout, the student first answers independently; if the answer is incorrect, a teacher diagnoses the attempt","authors_text":"Enhong Chen, Jiayu Liu, Jie Ouyang, Jing Sha, Qi Liu, Qingchuan Li, Shijin Wang, Tingyue Pan, Xianquan Wang, Zhenya Huang, Zirui Liu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T09:08:29Z","title":"SocraticPO: Policy Optimization via Interactive Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09887","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:fcc7ddda4d1089d80d0144b1ee03d260bb10811db47f83e9ca78bd365f440c93","target":"record","created_at":"2026-06-10T00:08:31Z","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":"b5ec6043c5b95acd9224bb74a153e367e69030ac7183da4370893736fa37d1d9","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T09:08:29Z","title_canon_sha256":"906154250532658ef23c5a700b1d59a55b9b67d7d671bd2687400cb2017e1e2c"},"schema_version":"1.0","source":{"id":"2606.09887","kind":"arxiv","version":1}},"canonical_sha256":"3d51495663e185430e2d04111e80216b1e3054e222fabb83d098cdbe79d35561","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d51495663e185430e2d04111e80216b1e3054e222fabb83d098cdbe79d35561","first_computed_at":"2026-06-10T00:08:31.391589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T00:08:31.391589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FoI0YX33ZMJOX7Ne/MC+rs9Bd4sUbf9wD6puyNO46fIjwJgBrsm5iPfHTfdrtuzBW3jrtTccidEYJOhbe2+JDQ==","signature_status":"signed_v1","signed_at":"2026-06-10T00:08:31.392554Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09887","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcc7ddda4d1089d80d0144b1ee03d260bb10811db47f83e9ca78bd365f440c93","sha256:c501086d33553849ecff252d2399058a1f0671a968dda1dfc2c20a2bbdb965ca"],"state_sha256":"d5ca3a29e158c0e201b19326c3ff68bfd29628269313b786fbeee0242c11fc0c"}