{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5UX7KIXH6WMWOVHZQL44663UVZ","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":"82f9fc13f486fd7560461c14718a49fafc93245f57c70fe204244655db11abca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-28T08:20:22Z","title_canon_sha256":"35a1100591d2e87ae803b35c3cddf54f9ad0277d5045b639159fe73298985a43"},"schema_version":"1.0","source":{"id":"2509.23730","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.23730","created_at":"2026-05-29T02:05:36Z"},{"alias_kind":"arxiv_version","alias_value":"2509.23730v2","created_at":"2026-05-29T02:05:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.23730","created_at":"2026-05-29T02:05:36Z"},{"alias_kind":"pith_short_12","alias_value":"5UX7KIXH6WMW","created_at":"2026-05-29T02:05:36Z"},{"alias_kind":"pith_short_16","alias_value":"5UX7KIXH6WMWOVHZ","created_at":"2026-05-29T02:05:36Z"},{"alias_kind":"pith_short_8","alias_value":"5UX7KIXH","created_at":"2026-05-29T02:05:36Z"}],"graph_snapshots":[{"event_id":"sha256:4a237b93095d01b178b2dc4b024ad9b501d61a219fece08515b98f5e3d03ab7a","target":"graph","created_at":"2026-05-29T02:05:36Z","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/2509.23730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have recently advanced in reasoning when optimized with reinforcement learning (RL) under verifiable rewards. Existing methods primarily rely on outcome-based supervision to strengthen internal LLM reasoning, often leading to inefficient exploration and sparse rewards. To mitigate this issue, we propose Expert-Assisted Policy Optimization (EAPO), a novel RL framework that enhances exploration by incorporating multi-turn interactions with external experts during training. Unlike prior methods, where policies reason in isolation, EAPO incentivizes the policy to adapt","authors_text":"Cong Ma, Huaixiao Tou, Kai Jia, Minghao Li, Shiye Lei, Siyao Song, Ying Zeng, Zhihao Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-28T08:20:22Z","title":"EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.23730","kind":"arxiv","version":2},"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":"sha256:23cc35220ee7470de37045cb7876368ba0dd1571fb657a6e76403a1124ca017d","target":"record","created_at":"2026-05-29T02:05:36Z","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":"82f9fc13f486fd7560461c14718a49fafc93245f57c70fe204244655db11abca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-28T08:20:22Z","title_canon_sha256":"35a1100591d2e87ae803b35c3cddf54f9ad0277d5045b639159fe73298985a43"},"schema_version":"1.0","source":{"id":"2509.23730","kind":"arxiv","version":2}},"canonical_sha256":"ed2ff522e7f5996754f982f9cf7b74ae76cc89a1268b464893723a4a01637887","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed2ff522e7f5996754f982f9cf7b74ae76cc89a1268b464893723a4a01637887","first_computed_at":"2026-05-29T02:05:36.522538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:36.522538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8EqIU7ePw/mDLFbIpznIE5ob5xf89kxcXOYHUhnAhQSjgSK73EHO9IWa1mFwWqZpE7blWDa+EqKT7kyj7zEGBA==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:36.522978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.23730","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23cc35220ee7470de37045cb7876368ba0dd1571fb657a6e76403a1124ca017d","sha256:4a237b93095d01b178b2dc4b024ad9b501d61a219fece08515b98f5e3d03ab7a"],"state_sha256":"56568f99594f0e7396aaceb01fb053373c3b6028d78f695b4b8cc2f132ab9458"}