{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Z2ZXZ4DYHZFZG3AOZGKARP42SS","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":"41b120f2e21c38bec3cbff489674596316b9f4fa3599c686b07d374c5455e571","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-29T18:25:46Z","title_canon_sha256":"d746b183660e26cbd2c1045ce9f413f969c06b7e9e46f48e68b7cfc165683004"},"schema_version":"1.0","source":{"id":"2310.00074","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00074","created_at":"2026-07-05T09:50:44Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00074v3","created_at":"2026-07-05T09:50:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00074","created_at":"2026-07-05T09:50:44Z"},{"alias_kind":"pith_short_12","alias_value":"Z2ZXZ4DYHZFZ","created_at":"2026-07-05T09:50:44Z"},{"alias_kind":"pith_short_16","alias_value":"Z2ZXZ4DYHZFZG3AO","created_at":"2026-07-05T09:50:44Z"},{"alias_kind":"pith_short_8","alias_value":"Z2ZXZ4DY","created_at":"2026-07-05T09:50:44Z"}],"graph_snapshots":[{"event_id":"sha256:9d0b35783522f332f208fa905269549e27073d3df0b2749bd4ecae8375074750","target":"graph","created_at":"2026-07-05T09:50:44Z","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/2310.00074/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To comprehensively gauge the capacity of current models for complex reasoning, it is crucial to assess their step-by-step reasoning in a scalable manner. Established reference-based evaluation metrics rely on human-annotated reasoning chains as references to assess the model-derived chains. However, such \"gold-standard\" human-written reasoning chains may not be unique and their acquisition is often labor-intensive. Existing reference-free reasoning evaluation metrics, while eliminating the need for human-crafted reasoning chains as references, often require fine-tuning with human-derived chain","authors_text":"Dan Roth, Hangfeng He, Hongming Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-29T18:25:46Z","title":"SocREval: Large Language Models with the Socratic Method for Reference-Free Reasoning Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00074","kind":"arxiv","version":3},"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":"sha256:8898f6909d2a353e01b95c1480214ebf06b82311bd3409df6e594e6eca29d249","target":"record","created_at":"2026-07-05T09:50:44Z","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":"41b120f2e21c38bec3cbff489674596316b9f4fa3599c686b07d374c5455e571","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-29T18:25:46Z","title_canon_sha256":"d746b183660e26cbd2c1045ce9f413f969c06b7e9e46f48e68b7cfc165683004"},"schema_version":"1.0","source":{"id":"2310.00074","kind":"arxiv","version":3}},"canonical_sha256":"ceb37cf0783e4b936c0ec99408bf9a94b627cb6a8f605d0b08d31ee63a690863","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ceb37cf0783e4b936c0ec99408bf9a94b627cb6a8f605d0b08d31ee63a690863","first_computed_at":"2026-07-05T09:50:44.514564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:44.514564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"12ox2uV/CexSq1Od3ORHQgsusN+l2y3e9wy4TquzuY8Dwjk4HwOD28+g0jCsQswDUon3c207ZGTbQJVvEnzwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:44.515096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.00074","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8898f6909d2a353e01b95c1480214ebf06b82311bd3409df6e594e6eca29d249","sha256:9d0b35783522f332f208fa905269549e27073d3df0b2749bd4ecae8375074750"],"state_sha256":"1885f17b8b30a557a51c19a79942caacd3f4d3dd1a1a3108e9b7efcc37dbfa3b"}