{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2CRNFYLZXWMN7MNXQCJ5HQYKB4","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":"975660d157ca21bd779636db0248c8e38b498b287e89447b289dfc468f491d55","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T04:01:36Z","title_canon_sha256":"8fbe3cf741cd977cfb0297d79216881df6a4483dafa8f7af6c17d24a261c7696"},"schema_version":"1.0","source":{"id":"2608.01667","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.01667","created_at":"2026-08-04T02:06:22Z"},{"alias_kind":"arxiv_version","alias_value":"2608.01667v1","created_at":"2026-08-04T02:06:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01667","created_at":"2026-08-04T02:06:22Z"},{"alias_kind":"pith_short_12","alias_value":"2CRNFYLZXWMN","created_at":"2026-08-04T02:06:22Z"},{"alias_kind":"pith_short_16","alias_value":"2CRNFYLZXWMN7MNX","created_at":"2026-08-04T02:06:22Z"},{"alias_kind":"pith_short_8","alias_value":"2CRNFYLZ","created_at":"2026-08-04T02:06:22Z"}],"graph_snapshots":[{"event_id":"sha256:2eb993d565875719a40a70a5a1a6a8afa944347e8de7bb7713a4cfcc138b3c7f","target":"graph","created_at":"2026-08-04T02:06:22Z","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/2608.01667/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Verifier-guided reinforcement learning has become a powerful paradigm for improving LLM reasoning. In multi-turn settings, models receive a verifier score after each turn and iteratively refine their outputs. Although such scores provide dense feedback, they do not directly provide dense credit: a score measures the quality of the current output, while credit should measure how the current turn changes the refinement trajectory. We propose TCPO, a turn-level credit assignment method for verifier-guided multi-turn RL. TCPO casts credit assignment as score-to-credit conversion and constructs tur","authors_text":"Sicong Liao, Yaohua Tang, Zhi Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T04:01:36Z","title":"TCPO: Turn-Level Credit Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01667","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":"sha256:77dd1478977d8194d09cb43d27438cc0f270109ad9a99a2dff01c083d443474b","target":"record","created_at":"2026-08-04T02:06:22Z","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":"975660d157ca21bd779636db0248c8e38b498b287e89447b289dfc468f491d55","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T04:01:36Z","title_canon_sha256":"8fbe3cf741cd977cfb0297d79216881df6a4483dafa8f7af6c17d24a261c7696"},"schema_version":"1.0","source":{"id":"2608.01667","kind":"arxiv","version":1}},"canonical_sha256":"d0a2d2e179bd98dfb1b78093d3c30a0f2dc406f25485527e18c22e526496dbe2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0a2d2e179bd98dfb1b78093d3c30a0f2dc406f25485527e18c22e526496dbe2","first_computed_at":"2026-08-04T02:06:22.745442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:06:22.745442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q5ake8ti3DF5X3ZVBJslZjtuyAiVCGWO2B56N0lFyLgMuiVzrqTF0YTs0z0Ijlb6/S3t+NlQZnE5vpMbCnZnDw==","signature_status":"signed_v1","signed_at":"2026-08-04T02:06:22.751355Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.01667","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77dd1478977d8194d09cb43d27438cc0f270109ad9a99a2dff01c083d443474b","sha256:2eb993d565875719a40a70a5a1a6a8afa944347e8de7bb7713a4cfcc138b3c7f"],"state_sha256":"f7961ae55f6349d6c851e6ed41c7efdcf4cab1bb8766b3011be5b1213ab1e03e"}