{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZQCYESS7QRSAJ6BWIVK6QJ45KR","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":"1968f4e8826b2339d22282ad080b9a067891a4cb05c0552143cd3f2dc25feeb8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-17T04:16:58Z","title_canon_sha256":"fb9584574dd4f89aa8c7c0481cdd6e4f5c2ee95336772adca4c0479aac2729e5"},"schema_version":"1.0","source":{"id":"2607.15610","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15610","created_at":"2026-07-20T01:19:00Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15610v1","created_at":"2026-07-20T01:19:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15610","created_at":"2026-07-20T01:19:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZQCYESS7QRSA","created_at":"2026-07-20T01:19:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZQCYESS7QRSAJ6BW","created_at":"2026-07-20T01:19:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZQCYESS7","created_at":"2026-07-20T01:19:00Z"}],"graph_snapshots":[{"event_id":"sha256:86bc1cf57e02bc60b98f4842d2a60d923cf2038b2c61e11fb7f63ed94b7a8041","target":"graph","created_at":"2026-07-20T01:19:00Z","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/2607.15610/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has become a key approach for training LLM agents, yet popular methods such as GRPO/RLOO rely on multiple independently sampled complete trajectories for advantage estimation. In long-horizon agentic tasks, such a uniform rollout strategy can waste budget on uninformative dead-end attempts, while promising intermediate states do not receive sufficient exploration. The multi-turn structure of agentic trajectories, with interleaved actions and observations, naturally supports organizing a trajectory group as a tree, where each turn serves as a decision point for explo","authors_text":"Changlong Yu, Hongye Jin, Jingbo Shang, Linwei Li, Qingyu Yin, Rongmei Lin, Sha Li, Shuyi Guan, Xin Liu, Xintong Li, Yuwei Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-17T04:16:58Z","title":"Process Reward Informed Tree Rollout for Effective Multi-Turn RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15610","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:a89105d5328da9b905bf0bb716c2ccaae93efdc2cbc57f3557ba15ec5555799b","target":"record","created_at":"2026-07-20T01:19:00Z","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":"1968f4e8826b2339d22282ad080b9a067891a4cb05c0552143cd3f2dc25feeb8","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-17T04:16:58Z","title_canon_sha256":"fb9584574dd4f89aa8c7c0481cdd6e4f5c2ee95336772adca4c0479aac2729e5"},"schema_version":"1.0","source":{"id":"2607.15610","kind":"arxiv","version":1}},"canonical_sha256":"cc05824a5f846404f8364555e8279d54407f053da80e3951ea6b827524142e55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc05824a5f846404f8364555e8279d54407f053da80e3951ea6b827524142e55","first_computed_at":"2026-07-20T01:19:00.094622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T01:19:00.094622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qeFoebDxLkZKlVIpduN1L7Hmw+qXkTesRK4XMYQwS0H3SGuy4qwX8xU5nQ4agNfW8oPhu2TKPLRfyQJzGT4JBw==","signature_status":"signed_v1","signed_at":"2026-07-20T01:19:00.095566Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15610","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a89105d5328da9b905bf0bb716c2ccaae93efdc2cbc57f3557ba15ec5555799b","sha256:86bc1cf57e02bc60b98f4842d2a60d923cf2038b2c61e11fb7f63ed94b7a8041"],"state_sha256":"05c0dddd44bd528275cdb76933c25802163f610739a7c3951ee2b91334645912"}