{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VGWMCXOXY7FOFEOELU7FBFGGUM","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":"12fb5d7cda3346a09ac24f0f7a1a96e2f129842a7dccec3d3d62ad38fcfab744","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-30T08:53:41Z","title_canon_sha256":"3dc77d301413ff029929fd57e44047e1a49b6186e1a39c6844defad82424e48b"},"schema_version":"1.0","source":{"id":"2510.26270","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.26270","created_at":"2026-05-29T01:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2510.26270v2","created_at":"2026-05-29T01:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.26270","created_at":"2026-05-29T01:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"VGWMCXOXY7FO","created_at":"2026-05-29T01:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"VGWMCXOXY7FOFEOE","created_at":"2026-05-29T01:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"VGWMCXOX","created_at":"2026-05-29T01:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:a97804398e8c86adc74b716266ba992a6109f9afdb2974f9952eab1f53564def","target":"graph","created_at":"2026-05-29T01:04:57Z","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/2510.26270/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-step LLM agents in interactive environments represent a crucial step toward long-horizon decision-making. To train such agents, group-based reinforcement learning is widely adopted, which reinforces trajectories with higher relative performance within the group. However, in most existing methods, every step within a trajectory and every trajectory with the same terminal reward receive identical credit, regardless of their actual contributions. Since different states play different structural roles in an online state-transition graph built from sampled trajectories, their impacts should b","authors_text":"Jiazhen Yuan, Jinquan Hang, Wei Zhao, Zhengbiao Bai, Zhike Gong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-30T08:53:41Z","title":"Graph-Enhanced Policy Optimization in LLM Agent Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.26270","kind":"arxiv","version":2},"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":"sha256:3951298f3dbd45f0d67085df7b182d31cfc9eb68cf67eb6737bd3997b6c4e0e4","target":"record","created_at":"2026-05-29T01:04:57Z","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":"12fb5d7cda3346a09ac24f0f7a1a96e2f129842a7dccec3d3d62ad38fcfab744","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-10-30T08:53:41Z","title_canon_sha256":"3dc77d301413ff029929fd57e44047e1a49b6186e1a39c6844defad82424e48b"},"schema_version":"1.0","source":{"id":"2510.26270","kind":"arxiv","version":2}},"canonical_sha256":"a9acc15dd7c7cae291c45d3e5094c6a318496f9c03fd20236246f9c1a045c983","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9acc15dd7c7cae291c45d3e5094c6a318496f9c03fd20236246f9c1a045c983","first_computed_at":"2026-05-29T01:04:57.559509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:04:57.559509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ggZYj16PfSvkNiDfjnXRAtmzhEH3tFS3K52SmW3TMZger2bmEiNh/BuMR9oxXQtmFCb9sTT4fwTlWSt6VQx4CQ==","signature_status":"signed_v1","signed_at":"2026-05-29T01:04:57.560030Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.26270","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3951298f3dbd45f0d67085df7b182d31cfc9eb68cf67eb6737bd3997b6c4e0e4","sha256:a97804398e8c86adc74b716266ba992a6109f9afdb2974f9952eab1f53564def"],"state_sha256":"7a4eba9eb4018ac69782c4eaa2c649a446d7e7eda16d9b0a8191dd46e28b1e77"}