{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ETLMTPQULN3JDQL5B32J3JHGH4","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":"2351ab5669bab64439a82c120bda169444f891bb04a4c2b3ce7a2366d4a8e5bc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T13:00:59Z","title_canon_sha256":"97e0ac1a758cdf2f7a248d466735479e00afa327231364a0703fec5ed8c54e07"},"schema_version":"1.0","source":{"id":"2608.05987","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.05987","created_at":"2026-08-07T00:54:52Z"},{"alias_kind":"arxiv_version","alias_value":"2608.05987v1","created_at":"2026-08-07T00:54:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05987","created_at":"2026-08-07T00:54:52Z"},{"alias_kind":"pith_short_12","alias_value":"ETLMTPQULN3J","created_at":"2026-08-07T00:54:52Z"},{"alias_kind":"pith_short_16","alias_value":"ETLMTPQULN3JDQL5","created_at":"2026-08-07T00:54:52Z"},{"alias_kind":"pith_short_8","alias_value":"ETLMTPQU","created_at":"2026-08-07T00:54:52Z"}],"graph_snapshots":[{"event_id":"sha256:764693b5949271be6ab99d8ff9c57a6710e9b4cc721804659bae57ae05055fc7","target":"graph","created_at":"2026-08-07T00:54:52Z","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/2608.05987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) with verifiable rewards constructs trajectory-level advantage estimates, yet it often fails to credit the few pivotal decisions that determine outcomes in long-horizon, multi-turn agentic tasks. Recent work introduces privileged self-distillation for credit assignment, providing denser supervision, but it remains unclear how such local signals should represent sequential credit. We propose AgentOPSD, a critic-free, recursive method for turn-level credit assignment in agentic reinforcement learning. AgentOPSD aggregates token-level teacher-student log-probability gap","authors_text":"Jie Wu, Jinyang Wu, Linji Hao, Qi Gu, Xunliang Cai, Yongliang Shen, Yueqing Sun, Yujiu Yang, Zhengxi Lu, Zhengzhou Cai, Zhiyuan Yao, Ziang Ye, Zi-Han Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T13:00:59Z","title":"AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05987","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":"sha256:14db2e54470b0afb3e75d5204d8430cc4f1285858a36797315015d5b3b5510c6","target":"record","created_at":"2026-08-07T00:54:52Z","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":"2351ab5669bab64439a82c120bda169444f891bb04a4c2b3ce7a2366d4a8e5bc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T13:00:59Z","title_canon_sha256":"97e0ac1a758cdf2f7a248d466735479e00afa327231364a0703fec5ed8c54e07"},"schema_version":"1.0","source":{"id":"2608.05987","kind":"arxiv","version":1}},"canonical_sha256":"24d6c9be145b7691c17d0ef49da4e63f246b1e7a16bd406c7856b1edc8ecda67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24d6c9be145b7691c17d0ef49da4e63f246b1e7a16bd406c7856b1edc8ecda67","first_computed_at":"2026-08-07T00:54:52.278478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-07T00:54:52.278478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3JJ7Zq3/e7kyS2BK9tr+8A7bFFg9YWreuclaBcJIssyG9NBgzqFqfMQl4B3gAq7sOi+GMM4O2LpiF7mH4CXGDA==","signature_status":"signed_v1","signed_at":"2026-08-07T00:54:52.280245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.05987","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14db2e54470b0afb3e75d5204d8430cc4f1285858a36797315015d5b3b5510c6","sha256:764693b5949271be6ab99d8ff9c57a6710e9b4cc721804659bae57ae05055fc7"],"state_sha256":"f18ebc476b3efe3b0d330911314f80191a8fa19a4b5267470497a849e8a7e914"}