{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KFQSQRHQEQI4OFMQEPE24YUYEL","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":"866904669e9d9865bf22b3165fbffa0db096056fda842ccd5cba59e5422374a9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-27T08:45:06Z","title_canon_sha256":"076aea2ce5b000dfd95eea1efe543fc26b05f9aa124546a65599142d05cdd711"},"schema_version":"1.0","source":{"id":"2504.19162","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.19162","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2504.19162v2","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19162","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"KFQSQRHQEQI4","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"KFQSQRHQEQI4OFMQ","created_at":"2026-07-05T11:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"KFQSQRHQ","created_at":"2026-07-05T11:04:50Z"}],"graph_snapshots":[{"event_id":"sha256:74e0f85bde9c6889885cab4ead8b678adcad3a294548f3a998690dcbe866441d","target":"graph","created_at":"2026-07-05T11:04:50Z","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/2504.19162/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating the step-by-step reliability of large language model (LLM) reasoning, such as Chain-of-Thought, remains challenging due to the difficulty and cost of obtaining high-quality step-level supervision. In this paper, we introduce Self-Play Critic (SPC), a novel approach where a critic model evolves its ability to assess reasoning steps through adversarial self-play games, eliminating the need for manual step-level annotation. SPC involves fine-tuning two copies of a base model to play two roles, namely a \"sneaky generator\" that deliberately produces erroneous steps designed to be difficu","authors_text":"Bang Zhang, Jiaqi Chen, Kwan-Yee K. Wong, Peisong Wang, Ruotian Ma, Xiaodan Liang, Xiaolong Li, Zhaopeng Tu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-27T08:45:06Z","title":"SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19162","kind":"arxiv","version":2},"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":"sha256:0464874c6961a684851242439bd8421def7aa1c14e0fa093ec04592804047f6b","target":"record","created_at":"2026-07-05T11:04:50Z","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":"866904669e9d9865bf22b3165fbffa0db096056fda842ccd5cba59e5422374a9","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-27T08:45:06Z","title_canon_sha256":"076aea2ce5b000dfd95eea1efe543fc26b05f9aa124546a65599142d05cdd711"},"schema_version":"1.0","source":{"id":"2504.19162","kind":"arxiv","version":2}},"canonical_sha256":"51612844f02411c7159023c9ae629822dd3c7eae750a248d533ab0e396e359bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51612844f02411c7159023c9ae629822dd3c7eae750a248d533ab0e396e359bc","first_computed_at":"2026-07-05T11:04:50.017982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:50.017982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/ggw92uDS7FqVD4wCnRMPQz2IssJkvVKm2IHpZlrPPDvvE4Q/LJRlQpZ5f+LXjggklAKRCjAGLhU/+kxwWGfBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:50.018520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.19162","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0464874c6961a684851242439bd8421def7aa1c14e0fa093ec04592804047f6b","sha256:74e0f85bde9c6889885cab4ead8b678adcad3a294548f3a998690dcbe866441d"],"state_sha256":"8df58f68a1538d462a4bf3246f017c0c67835324d5056fbc43584d42e88f625c"}