{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A4GFOSJIJQGZKUW6MFIGSKM4G5","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":"fdce1864c4851a27b584b112c98bd68859d84d24e62649629bdc830db825eb39","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T16:19:36Z","title_canon_sha256":"a9adf4dbc058dfbabe8383a9db4445ac0f357872e0bdadb595e86aa6ea2628db"},"schema_version":"1.0","source":{"id":"2606.05263","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05263","created_at":"2026-06-05T00:13:50Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05263v1","created_at":"2026-06-05T00:13:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05263","created_at":"2026-06-05T00:13:50Z"},{"alias_kind":"pith_short_12","alias_value":"A4GFOSJIJQGZ","created_at":"2026-06-05T00:13:50Z"},{"alias_kind":"pith_short_16","alias_value":"A4GFOSJIJQGZKUW6","created_at":"2026-06-05T00:13:50Z"},{"alias_kind":"pith_short_8","alias_value":"A4GFOSJI","created_at":"2026-06-05T00:13:50Z"}],"graph_snapshots":[{"event_id":"sha256:9d703a8e51f1c1f8ba1907b30583d13c459f6529c6ed47370c2c5e6fffcdcfec","target":"graph","created_at":"2026-06-05T00:13:50Z","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/2606.05263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards improves reasoning and tool use, yet long-horizon language agents still learn unsupported evidence chains, belief drift, and shortcut actions that satisfy terminal checks. Existing process rewards are mostly correlational: they reward retrieval-, reflection-, or verification-like steps without estimating whether the step contributes to final verified success under a specified intervention. We propose CVT-RL, a constrained policy-gradient algorithm with dense verifiable rewards, intervention-validity gating, and a policy-conditioned counterfactual ","authors_text":"Renwei Meng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T16:19:36Z","title":"Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05263","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":"sha256:423e93b30bd58f821c942d8dfec38c90ce5b635e5f2d8b4a73b4a2c79826fd88","target":"record","created_at":"2026-06-05T00:13:50Z","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":"fdce1864c4851a27b584b112c98bd68859d84d24e62649629bdc830db825eb39","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T16:19:36Z","title_canon_sha256":"a9adf4dbc058dfbabe8383a9db4445ac0f357872e0bdadb595e86aa6ea2628db"},"schema_version":"1.0","source":{"id":"2606.05263","kind":"arxiv","version":1}},"canonical_sha256":"070c5749284c0d9552de615069299c3749bde171b8880d3402f24d49b339d149","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"070c5749284c0d9552de615069299c3749bde171b8880d3402f24d49b339d149","first_computed_at":"2026-06-05T00:13:50.850006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T00:13:50.850006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f6tOtfne7o/qOU51EX8MqOPxKvDezwIkcuttM171sTPm4rwfY0RuDLQbNd9eOvKil7p6fdeijlVdcGTS4GwvBA==","signature_status":"signed_v1","signed_at":"2026-06-05T00:13:50.850485Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05263","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:423e93b30bd58f821c942d8dfec38c90ce5b635e5f2d8b4a73b4a2c79826fd88","sha256:9d703a8e51f1c1f8ba1907b30583d13c459f6529c6ed47370c2c5e6fffcdcfec"],"state_sha256":"95dcc467233bfe59f3407fffe8674a7b738688b981829554e55850ab22ef1a3d"}