{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GYUUNYSLU4Z7ZZYCIGS44JHN6Q","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":"b8e058b486fc86f630ffdaa63f134025635a1c0209aaa99df507687de2e64465","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T08:12:47Z","title_canon_sha256":"89ea7d9958648adb41e0bba207e399edeea8255f0f5bee5ecfd54b0a1269c645"},"schema_version":"1.0","source":{"id":"2606.22995","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22995","created_at":"2026-06-23T03:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22995v1","created_at":"2026-06-23T03:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22995","created_at":"2026-06-23T03:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"GYUUNYSLU4Z7","created_at":"2026-06-23T03:14:06Z"},{"alias_kind":"pith_short_16","alias_value":"GYUUNYSLU4Z7ZZYC","created_at":"2026-06-23T03:14:06Z"},{"alias_kind":"pith_short_8","alias_value":"GYUUNYSL","created_at":"2026-06-23T03:14:06Z"}],"graph_snapshots":[{"event_id":"sha256:75f2b2749f0b8ed2620358c74a31547bde8aa041e72de2267aab281a3f6853f5","target":"graph","created_at":"2026-06-23T03:14:06Z","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/2606.22995/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group-based Reinforcement Learning (RL) has significantly enhanced Large Language Models (LLMs) in agentic scenarios. To achieve finer-grained policy updates, recent agentic RL frameworks have shifted from trajectory-level to step-level training. However, long-horizon agentic RL suffers from severe reward sparsity and delay, as feedback is often deferred for dozens of interaction steps. While existing step-level frameworks refine training granularity, their credit assignment remains coarse-grained and still treats agent exploration as isolated, linear trajectories. This oversimplified perspect","authors_text":"Feng Sun, Furu Wei, Haizhen Huang, MingHui Song, Qi Zhang, Shaohan Huang, Weiwei Deng, Yunan Wang, Zihan Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T08:12:47Z","title":"Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22995","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":"sha256:6a97764e61974789e00cb0a83b414fb45af9e9e688ab654dff24e024602f2ed3","target":"record","created_at":"2026-06-23T03:14:06Z","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":"b8e058b486fc86f630ffdaa63f134025635a1c0209aaa99df507687de2e64465","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-22T08:12:47Z","title_canon_sha256":"89ea7d9958648adb41e0bba207e399edeea8255f0f5bee5ecfd54b0a1269c645"},"schema_version":"1.0","source":{"id":"2606.22995","kind":"arxiv","version":1}},"canonical_sha256":"362946e24ba733fce70241a5ce24edf42e2dda56b224a825129bdc38df876dce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"362946e24ba733fce70241a5ce24edf42e2dda56b224a825129bdc38df876dce","first_computed_at":"2026-06-23T03:14:06.231716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T03:14:06.231716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6lZvwiN3v6CJ+2InTegpBRs/d4MImel2cGBkbjg50kuaaYUUa4+EJq8gsoqaKnid91YHWpBwOFQEGrmO5BbTDA==","signature_status":"signed_v1","signed_at":"2026-06-23T03:14:06.232055Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22995","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a97764e61974789e00cb0a83b414fb45af9e9e688ab654dff24e024602f2ed3","sha256:75f2b2749f0b8ed2620358c74a31547bde8aa041e72de2267aab281a3f6853f5"],"state_sha256":"91bf6fe7a42bab628844f303acb1335ac1cd7246594c158b6e524d48701d8159"}