{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FT5WDVUJYQW43C45EFCI655JXW","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":"e04b5de85c6211bb7c55631c6a97e838346de5c92271afb052d2af917e59ede4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T08:54:09Z","title_canon_sha256":"8ef2a7f2bc4a8e87a669f56b95ec035379be1f810e42f60f1119b4667207bb85"},"schema_version":"1.0","source":{"id":"2606.05885","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05885","created_at":"2026-06-05T01:15:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05885v1","created_at":"2026-06-05T01:15:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05885","created_at":"2026-06-05T01:15:06Z"},{"alias_kind":"pith_short_12","alias_value":"FT5WDVUJYQW4","created_at":"2026-06-05T01:15:06Z"},{"alias_kind":"pith_short_16","alias_value":"FT5WDVUJYQW43C45","created_at":"2026-06-05T01:15:06Z"},{"alias_kind":"pith_short_8","alias_value":"FT5WDVUJ","created_at":"2026-06-05T01:15:06Z"}],"graph_snapshots":[{"event_id":"sha256:3fa34a17008a1a1f0a3308de5fac8b0ee58c32109df95d622c096eba4822de45","target":"graph","created_at":"2026-06-05T01:15:06Z","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/2606.05885/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-horizon LLM agents require reinforcement learning methods that can assign credit to intermediate decisions under sparse and delayed rewards. Recent group-based methods such as GiGPO improve over GRPO by constructing step-level advantages at repeated anchor states. However, we show that such dense credit can be statistically unreliable: under limited rollouts, rare but lucky actions may receive overly large advantages, producing divergent anchor bias and late-stage training oscillation. We propose Evidence-Calibrated Policy Optimization (ECPO), a critic-free policy optimization algorithm t","authors_text":"Lu Chen, Qi Zhou, Wenjing Duan, Yuanfan Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T08:54:09Z","title":"When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05885","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":"sha256:3692bbcd0b67070bf3fb91a66989b43cb9e3a05f356d34a3a461a9f04f2064ef","target":"record","created_at":"2026-06-05T01:15:06Z","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":"e04b5de85c6211bb7c55631c6a97e838346de5c92271afb052d2af917e59ede4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-04T08:54:09Z","title_canon_sha256":"8ef2a7f2bc4a8e87a669f56b95ec035379be1f810e42f60f1119b4667207bb85"},"schema_version":"1.0","source":{"id":"2606.05885","kind":"arxiv","version":1}},"canonical_sha256":"2cfb61d689c42dcd8b9d21448f77a9bd9c56d53ac53989d78de87fd4c1c28fad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cfb61d689c42dcd8b9d21448f77a9bd9c56d53ac53989d78de87fd4c1c28fad","first_computed_at":"2026-06-05T01:15:06.785605Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:06.785605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TqMLFdoo3BwiIaRqCJHILgT4an0A5Nbd2gufgR+mrncSAT2oBSjHQ36YFl403XBt1I/DHmfHmJwpalzz/0T2Bg==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:06.785998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05885","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3692bbcd0b67070bf3fb91a66989b43cb9e3a05f356d34a3a461a9f04f2064ef","sha256:3fa34a17008a1a1f0a3308de5fac8b0ee58c32109df95d622c096eba4822de45"],"state_sha256":"1834df3cd0ff425f256d88993d5049bb854ea8298a69203e6c2da0e3e927a21c"}