{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6DNHLJBGAQWZXLBXRZ6ALXJDCR","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":"50de466ecb6b3608eef26040b1933225f003563067ae5247725260f15424ceb3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T17:47:07Z","title_canon_sha256":"b4fef21b94de3e3abd2a6e6a7a1e7ff3590263b390f6a11f6a4234bdb8ed0571"},"schema_version":"1.0","source":{"id":"2606.12384","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12384","created_at":"2026-06-11T02:09:49Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12384v1","created_at":"2026-06-11T02:09:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12384","created_at":"2026-06-11T02:09:49Z"},{"alias_kind":"pith_short_12","alias_value":"6DNHLJBGAQWZ","created_at":"2026-06-11T02:09:49Z"},{"alias_kind":"pith_short_16","alias_value":"6DNHLJBGAQWZXLBX","created_at":"2026-06-11T02:09:49Z"},{"alias_kind":"pith_short_8","alias_value":"6DNHLJBG","created_at":"2026-06-11T02:09:49Z"}],"graph_snapshots":[{"event_id":"sha256:cd36003994e895ef5c95661beb57b7671542bc4c7f54b24d27fd09a3d75a80eb","target":"graph","created_at":"2026-06-11T02:09:49Z","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/2606.12384/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large language model agents. However, most existing methods assign credit over coarse heuristic units, such as tool-call boundaries or fixed workflows, making it difficult to identify which intermediate decisions influence downstream outcomes. In this work, we study agentic RL from two perspectives: \\textit{where to branch and how to assign credit after branching}. Our pilot analysis shows that influential decision points are broadly distributed throughout the generated se","authors_text":"Guanhua Chen, Pengkun Wang, Shidong Yang, Xiangxiang Chu, Xucong Wang, Yong Wang, Yuxiang Ji, Ziyu Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T17:47:07Z","title":"APPO: Agentic Procedural Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12384","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":"sha256:07d45e3a411b6a49f7ef910c963707e506039c3d2367c871cb5a6acdf6f1c3d2","target":"record","created_at":"2026-06-11T02:09:49Z","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":"50de466ecb6b3608eef26040b1933225f003563067ae5247725260f15424ceb3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T17:47:07Z","title_canon_sha256":"b4fef21b94de3e3abd2a6e6a7a1e7ff3590263b390f6a11f6a4234bdb8ed0571"},"schema_version":"1.0","source":{"id":"2606.12384","kind":"arxiv","version":1}},"canonical_sha256":"f0da75a426042d9bac378e7c05dd231458487c74d6b4865bd232b6cb1d26856f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0da75a426042d9bac378e7c05dd231458487c74d6b4865bd232b6cb1d26856f","first_computed_at":"2026-06-11T02:09:49.296584Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T02:09:49.296584Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tpt9ASaFmQfJQ0VimYyTwFKVDxnYw32JWi98od88KHKUTjlnpR+XquGxh4MeUltevV5P9Z2KVxomY6y15wuYAQ==","signature_status":"signed_v1","signed_at":"2026-06-11T02:09:49.297014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12384","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07d45e3a411b6a49f7ef910c963707e506039c3d2367c871cb5a6acdf6f1c3d2","sha256:cd36003994e895ef5c95661beb57b7671542bc4c7f54b24d27fd09a3d75a80eb"],"state_sha256":"5b7dc074552ca5fb9f35a09f20f1a7883ac94fb654b668df882279572310d9b2"}