{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HWUKEYRDQBQ5N2GFPVHR3YOUXW","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":"ae4bbbd674652aa50f24b6642f3355a8405f073043f35e63d43867a67dbc787b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T08:32:42Z","title_canon_sha256":"6a46da055506b587a9ade8f0c83d7bb34279bfcf7f5748b51dd9f2479182c990"},"schema_version":"1.0","source":{"id":"2606.25556","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25556","created_at":"2026-06-25T01:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25556v1","created_at":"2026-06-25T01:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25556","created_at":"2026-06-25T01:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"HWUKEYRDQBQ5","created_at":"2026-06-25T01:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"HWUKEYRDQBQ5N2GF","created_at":"2026-06-25T01:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"HWUKEYRD","created_at":"2026-06-25T01:18:08Z"}],"graph_snapshots":[{"event_id":"sha256:6a7c07d4bbedb3862324465c8a6a800314d9b9790d0675beb39ad78bb4cdf980","target":"graph","created_at":"2026-06-25T01:18:08Z","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/2606.25556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stepwise group-based RL is an attractive way to train long-horizon LLM agents without a learned critic: it reuses multiple sampled rollouts to estimate local advantages. Its weakness is less visible but more fundamental: every group-relative estimator assumes that the steps it compares are equivalent for credit assignment. We show that current agentic variants violate this assumption through a state-action credit mismatch. The observation-hash partition is overly fine on the state side, creating singleton groups with zero step-level signal, while a single within-group mean is too coarse on the","authors_text":"Ding Cao, Hanyang Wang, Ke Zeng, Tianxiang Zhao, Weijieying Ren, Yuxiang Zhang, Zhizhao Zeng","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T08:32:42Z","title":"BiPACE: Bisimulation-Guided Policy Optimization with Action Counterfactual Estimation for LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25556","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:d722f4c174b3f7ace72835a425ce7f256d44d942b6bfa99572c853514d4fd2d6","target":"record","created_at":"2026-06-25T01:18:08Z","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":"ae4bbbd674652aa50f24b6642f3355a8405f073043f35e63d43867a67dbc787b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T08:32:42Z","title_canon_sha256":"6a46da055506b587a9ade8f0c83d7bb34279bfcf7f5748b51dd9f2479182c990"},"schema_version":"1.0","source":{"id":"2606.25556","kind":"arxiv","version":1}},"canonical_sha256":"3da8a262238061d6e8c57d4f1de1d4bd9ddcad8bdf61ee05cf1d42a1e360d157","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3da8a262238061d6e8c57d4f1de1d4bd9ddcad8bdf61ee05cf1d42a1e360d157","first_computed_at":"2026-06-25T01:18:08.736800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:08.736800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hsa0ctEFPUAOFKBjGw5id6sBTZXMUqIWZbbMLqeWOFCSiiB/Z6GyAxl+xOIL39w3FI0rkxUIaUR3g6UYx9TPDQ==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:08.737246Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25556","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d722f4c174b3f7ace72835a425ce7f256d44d942b6bfa99572c853514d4fd2d6","sha256:6a7c07d4bbedb3862324465c8a6a800314d9b9790d0675beb39ad78bb4cdf980"],"state_sha256":"e7bfbb82e95f72a6ed6f80d5c04aa2763074c0516d4d6a834854bb8f8137087c"}