{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Z2ZXZ4DYHZFZG3AOZGKARP42SS","short_pith_number":"pith:Z2ZXZ4DY","schema_version":"1.0","canonical_sha256":"ceb37cf0783e4b936c0ec99408bf9a94b627cb6a8f605d0b08d31ee63a690863","source":{"kind":"arxiv","id":"2310.00074","version":3},"attestation_state":"computed","paper":{"title":"SocREval: Large Language Models with the Socratic Method for Reference-Free Reasoning Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dan Roth, Hangfeng He, Hongming Zhang","submitted_at":"2023-09-29T18:25:46Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.00074","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-29T18:25:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d746b183660e26cbd2c1045ce9f413f969c06b7e9e46f48e68b7cfc165683004","abstract_canon_sha256":"41b120f2e21c38bec3cbff489674596316b9f4fa3599c686b07d374c5455e571"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:44.515096Z","signature_b64":"12ox2uV/CexSq1Od3ORHQgsusN+l2y3e9wy4TquzuY8Dwjk4HwOD28+g0jCsQswDUon3c207ZGTbQJVvEnzwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ceb37cf0783e4b936c0ec99408bf9a94b627cb6a8f605d0b08d31ee63a690863","last_reissued_at":"2026-07-05T09:50:44.514564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:44.514564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SocREval: Large Language Models with the Socratic Method for Reference-Free Reasoning Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dan Roth, Hangfeng He, Hongming Zhang","submitted_at":"2023-09-29T18:25:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00074","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2310.00074/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.00074","created_at":"2026-07-05T09:50:44.514623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00074v3","created_at":"2026-07-05T09:50:44.514623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00074","created_at":"2026-07-05T09:50:44.514623+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z2ZXZ4DYHZFZ","created_at":"2026-07-05T09:50:44.514623+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z2ZXZ4DYHZFZG3AO","created_at":"2026-07-05T09:50:44.514623+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z2ZXZ4DY","created_at":"2026-07-05T09:50:44.514623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09564","citing_title":"ACE-Bench: A Lightweight Benchmark for Evaluating Azure SDK Usage Correctness","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2406.06608","citing_title":"The Prompt Report: A Systematic Survey of Prompt Engineering Techniques","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z2ZXZ4DYHZFZG3AOZGKARP42SS","json":"https://pith.science/pith/Z2ZXZ4DYHZFZG3AOZGKARP42SS.json","graph_json":"https://pith.science/api/pith-number/Z2ZXZ4DYHZFZG3AOZGKARP42SS/graph.json","events_json":"https://pith.science/api/pith-number/Z2ZXZ4DYHZFZG3AOZGKARP42SS/events.json","paper":"https://pith.science/paper/Z2ZXZ4DY"},"agent_actions":{"view_html":"https://pith.science/pith/Z2ZXZ4DYHZFZG3AOZGKARP42SS","download_json":"https://pith.science/pith/Z2ZXZ4DYHZFZG3AOZGKARP42SS.json","view_paper":"https://pith.science/paper/Z2ZXZ4DY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00074&json=true","fetch_graph":"https://pith.science/api/pith-number/Z2ZXZ4DYHZFZG3AOZGKARP42SS/graph.json","fetch_events":"https://pith.science/api/pith-number/Z2ZXZ4DYHZFZG3AOZGKARP42SS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z2ZXZ4DYHZFZG3AOZGKARP42SS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z2ZXZ4DYHZFZG3AOZGKARP42SS/action/storage_attestation","attest_author":"https://pith.science/pith/Z2ZXZ4DYHZFZG3AOZGKARP42SS/action/author_attestation","sign_citation":"https://pith.science/pith/Z2ZXZ4DYHZFZG3AOZGKARP42SS/action/citation_signature","submit_replication":"https://pith.science/pith/Z2ZXZ4DYHZFZG3AOZGKARP42SS/action/replication_record"}},"created_at":"2026-07-05T09:50:44.514623+00:00","updated_at":"2026-07-05T09:50:44.514623+00:00"}