{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UKYKHLTEXMPMSHIYPT2HB7HYKO","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":"c99105ad5253b28de443ad9930f03a0a30784b190f0f115bb36726ba4f3f2ca6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-28T05:39:01Z","title_canon_sha256":"619964cba9320c2b0069af3314c80806b3cefdfa5d42f0e253dbcbc2065eb3c6"},"schema_version":"1.0","source":{"id":"2607.25308","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.25308","created_at":"2026-07-29T01:25:08Z"},{"alias_kind":"arxiv_version","alias_value":"2607.25308v1","created_at":"2026-07-29T01:25:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25308","created_at":"2026-07-29T01:25:08Z"},{"alias_kind":"pith_short_12","alias_value":"UKYKHLTEXMPM","created_at":"2026-07-29T01:25:08Z"},{"alias_kind":"pith_short_16","alias_value":"UKYKHLTEXMPMSHIY","created_at":"2026-07-29T01:25:08Z"},{"alias_kind":"pith_short_8","alias_value":"UKYKHLTE","created_at":"2026-07-29T01:25:08Z"}],"graph_snapshots":[{"event_id":"sha256:7fb344be8a7bf2bbd706d37524a2a4a14b6403a543ae26dfb0df4f28dc2cd90d","target":"graph","created_at":"2026-07-29T01:25:08Z","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/2607.25308/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making, yet reinforcement learning with verifiable rewards (RLVR) relies on sparse final rewards that reveal little about which decisions determine success. Denser process signals could supply this missing turn-level credit, but existing sources are hard to keep both cheap and accurate. We observe that changes in a game solver's state value reveal whether an action advances the state toward success. Building on this insight, we propose CAST (Credit Assignment from Solver Teachers),","authors_text":"Fuli Feng, Han-Jia Ye, Lan-Zhe Guo, Qi Gu, Wentao Shi, Xunliang Cai, Yi-Kai Zhang, Yuchun Miao, Yueqing Sun, Yu Wang, Ziang Ye","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-28T05:39:01Z","title":"CAST: Game Solvers as Turn-Level Teachers for LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25308","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:b0f2c1edeab2b72da62090551983bc5c8de9241085325ef46d95b7bec22c2032","target":"record","created_at":"2026-07-29T01:25:08Z","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":"c99105ad5253b28de443ad9930f03a0a30784b190f0f115bb36726ba4f3f2ca6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-28T05:39:01Z","title_canon_sha256":"619964cba9320c2b0069af3314c80806b3cefdfa5d42f0e253dbcbc2065eb3c6"},"schema_version":"1.0","source":{"id":"2607.25308","kind":"arxiv","version":1}},"canonical_sha256":"a2b0a3ae64bb1ec91d187cf470fcf85395e11d315673a6c7acb72c318b1671e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2b0a3ae64bb1ec91d187cf470fcf85395e11d315673a6c7acb72c318b1671e5","first_computed_at":"2026-07-29T01:25:08.257095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T01:25:08.257095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"deNYRjvu0azQ+wWhWkt+jGxz9imLs2dIwzZW7PHKOWdH26vtH5LHjt6p/A2EXuTcMf5Qfjxqbcu/ySYWl2R0AA==","signature_status":"signed_v1","signed_at":"2026-07-29T01:25:08.257991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.25308","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0f2c1edeab2b72da62090551983bc5c8de9241085325ef46d95b7bec22c2032","sha256:7fb344be8a7bf2bbd706d37524a2a4a14b6403a543ae26dfb0df4f28dc2cd90d"],"state_sha256":"966adb6f29e7e064c8a97f398b7726e622fc74aca99d6b2a59643ec40aa9c1b6"}