{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ETLMTPQULN3JDQL5B32J3JHGH4","short_pith_number":"pith:ETLMTPQU","schema_version":"1.0","canonical_sha256":"24d6c9be145b7691c17d0ef49da4e63f246b1e7a16bd406c7856b1edc8ecda67","source":{"kind":"arxiv","id":"2608.05987","version":1},"attestation_state":"computed","paper":{"title":"AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","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","submitted_at":"2026-08-06T13:00:59Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.05987","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-06T13:00:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"97e0ac1a758cdf2f7a248d466735479e00afa327231364a0703fec5ed8c54e07","abstract_canon_sha256":"2351ab5669bab64439a82c120bda169444f891bb04a4c2b3ce7a2366d4a8e5bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T00:54:52.280245Z","signature_b64":"3JJ7Zq3/e7kyS2BK9tr+8A7bFFg9YWreuclaBcJIssyG9NBgzqFqfMQl4B3gAq7sOi+GMM4O2LpiF7mH4CXGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24d6c9be145b7691c17d0ef49da4e63f246b1e7a16bd406c7856b1edc8ecda67","last_reissued_at":"2026-08-07T00:54:52.278478Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T00:54:52.278478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","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","submitted_at":"2026-08-06T13:00:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.05987","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.05987/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.05987","created_at":"2026-08-07T00:54:52.280166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.05987v1","created_at":"2026-08-07T00:54:52.280166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.05987","created_at":"2026-08-07T00:54:52.280166+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETLMTPQULN3J","created_at":"2026-08-07T00:54:52.280166+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETLMTPQULN3JDQL5","created_at":"2026-08-07T00:54:52.280166+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETLMTPQU","created_at":"2026-08-07T00:54:52.280166+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ETLMTPQULN3JDQL5B32J3JHGH4","json":"https://pith.science/pith/ETLMTPQULN3JDQL5B32J3JHGH4.json","graph_json":"https://pith.science/api/pith-number/ETLMTPQULN3JDQL5B32J3JHGH4/graph.json","events_json":"https://pith.science/api/pith-number/ETLMTPQULN3JDQL5B32J3JHGH4/events.json","paper":"https://pith.science/paper/ETLMTPQU"},"agent_actions":{"view_html":"https://pith.science/pith/ETLMTPQULN3JDQL5B32J3JHGH4","download_json":"https://pith.science/pith/ETLMTPQULN3JDQL5B32J3JHGH4.json","view_paper":"https://pith.science/paper/ETLMTPQU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.05987&json=true","fetch_graph":"https://pith.science/api/pith-number/ETLMTPQULN3JDQL5B32J3JHGH4/graph.json","fetch_events":"https://pith.science/api/pith-number/ETLMTPQULN3JDQL5B32J3JHGH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETLMTPQULN3JDQL5B32J3JHGH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETLMTPQULN3JDQL5B32J3JHGH4/action/storage_attestation","attest_author":"https://pith.science/pith/ETLMTPQULN3JDQL5B32J3JHGH4/action/author_attestation","sign_citation":"https://pith.science/pith/ETLMTPQULN3JDQL5B32J3JHGH4/action/citation_signature","submit_replication":"https://pith.science/pith/ETLMTPQULN3JDQL5B32J3JHGH4/action/replication_record"}},"created_at":"2026-08-07T00:54:52.280166+00:00","updated_at":"2026-08-07T00:54:52.280166+00:00"}