{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WF3DS6WHGQB47OYLDOZ6QOIKRU","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":"1dfe2806e5d619c201db4592db771803405fcb705dfc7591b6b29546a0b3ec3d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T14:02:13Z","title_canon_sha256":"f406dc07c5cc8cc1893ffb8a67134db49bf6695c2d870c070874179bbde40e63"},"schema_version":"1.0","source":{"id":"2606.25852","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25852","created_at":"2026-06-25T01:18:41Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25852v1","created_at":"2026-06-25T01:18:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25852","created_at":"2026-06-25T01:18:41Z"},{"alias_kind":"pith_short_12","alias_value":"WF3DS6WHGQB4","created_at":"2026-06-25T01:18:41Z"},{"alias_kind":"pith_short_16","alias_value":"WF3DS6WHGQB47OYL","created_at":"2026-06-25T01:18:41Z"},{"alias_kind":"pith_short_8","alias_value":"WF3DS6WH","created_at":"2026-06-25T01:18:41Z"}],"graph_snapshots":[{"event_id":"sha256:929059cd959acb74334256651e6a08f5d1ca5a0ad94526fb10bcf27aa5e57853","target":"graph","created_at":"2026-06-25T01:18:41Z","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/2606.25852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Group-based reinforcement learning effectively post-trains LLM agents for long-horizon, sparse-reward tasks by deriving step-level credit from trajectory outcomes. However, this ties a step's credit to its rollout's final outcome: semantically near-identical intermediate steps receive opposite credit depending on whether their trajectory eventually succeeded or failed. Such semantic credit inconsistency sends conflicting gradients to similar actions and wastes the partially-correct progress inside failed rollouts. Motivated by this, we propose Semantic Consistency Policy Optimization (SCPO), a","authors_text":"Junzhuo Li, Peng Xu, Sijia Chen, Xuming Hu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T14:02:13Z","title":"Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25852","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":"sha256:3d0951a9fabaeaa1e2ffcb8ed498316386706045fb78193f13f239d054522799","target":"record","created_at":"2026-06-25T01:18:41Z","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":"1dfe2806e5d619c201db4592db771803405fcb705dfc7591b6b29546a0b3ec3d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T14:02:13Z","title_canon_sha256":"f406dc07c5cc8cc1893ffb8a67134db49bf6695c2d870c070874179bbde40e63"},"schema_version":"1.0","source":{"id":"2606.25852","kind":"arxiv","version":1}},"canonical_sha256":"b176397ac73403cfbb0b1bb3e8390a8d1fea44afdc7043100908940d4a16c61c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b176397ac73403cfbb0b1bb3e8390a8d1fea44afdc7043100908940d4a16c61c","first_computed_at":"2026-06-25T01:18:41.109079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:41.109079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y0WpvHhuM5GJYvMnEOlsdifQMQRNGjPL5ZhabwkihujEq6VjYoWoZALr5qTliYRVLVSsjigw0gUh+ZtJbtYMAA==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:41.109463Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25852","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d0951a9fabaeaa1e2ffcb8ed498316386706045fb78193f13f239d054522799","sha256:929059cd959acb74334256651e6a08f5d1ca5a0ad94526fb10bcf27aa5e57853"],"state_sha256":"69be6bf1489ccd7a8b1309bfdf867b374699b711482fcb4fc47e94c20face705"}