{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OJ3IIR3LA6REQIAPNB4JRKAB27","short_pith_number":"pith:OJ3IIR3L","schema_version":"1.0","canonical_sha256":"727684476b07a248200f687898a801d7fb7588406f32e4077b42288439131272","source":{"kind":"arxiv","id":"2402.00559","version":4},"attestation_state":"computed","paper":{"title":"A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alon Jacovi, Bernd Bohnet, Jonathan Herzig, Michael Collins, Michael Tseng, Mor Geva, Or Honovich, Roee Aharoni, Yonatan Bitton","submitted_at":"2024-02-01T12:46:45Z","abstract_excerpt":"Prompting language models to provide step-by-step answers (e.g., \"Chain-of-Thought\") is the prominent approach for complex reasoning tasks, where more accurate reasoning chains typically improve downstream task performance. Recent literature discusses automatic methods to verify reasoning to evaluate and improve their correctness. However, no fine-grained step-level datasets are available to enable thorough evaluation of such verification methods, hindering progress in this direction. We introduce REVEAL: Reasoning Verification Evaluation, a dataset to benchmark automatic verifiers of complex "},"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":"2402.00559","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T12:46:45Z","cross_cats_sorted":[],"title_canon_sha256":"25a11054195d5072a495d3444926a813b937168eef2650d52a0f6af15898f9b3","abstract_canon_sha256":"9f2a0454184b7a1dbeb3d01897e589e52201abafc85234ca92b9ec45af9da31f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:12.354772Z","signature_b64":"JHs0Wssrji1NUhGMj4tQJbmhqZV9v12jRN7WAy0bbE31cHn24gE98/EAU4VharLq6zjVLTd4h3JgkIfcT8VgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"727684476b07a248200f687898a801d7fb7588406f32e4077b42288439131272","last_reissued_at":"2026-07-05T08:21:12.354280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:12.354280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Chain-of-Thought Is as Strong as Its Weakest Link: A Benchmark for Verifiers of Reasoning Chains","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alon Jacovi, Bernd Bohnet, Jonathan Herzig, Michael Collins, Michael Tseng, Mor Geva, Or Honovich, Roee Aharoni, Yonatan Bitton","submitted_at":"2024-02-01T12:46:45Z","abstract_excerpt":"Prompting language models to provide step-by-step answers (e.g., \"Chain-of-Thought\") is the prominent approach for complex reasoning tasks, where more accurate reasoning chains typically improve downstream task performance. Recent literature discusses automatic methods to verify reasoning to evaluate and improve their correctness. However, no fine-grained step-level datasets are available to enable thorough evaluation of such verification methods, hindering progress in this direction. We introduce REVEAL: Reasoning Verification Evaluation, a dataset to benchmark automatic verifiers of complex "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00559","kind":"arxiv","version":4},"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/2402.00559/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":"2402.00559","created_at":"2026-07-05T08:21:12.354340+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00559v4","created_at":"2026-07-05T08:21:12.354340+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00559","created_at":"2026-07-05T08:21:12.354340+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJ3IIR3LA6RE","created_at":"2026-07-05T08:21:12.354340+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJ3IIR3LA6REQIAP","created_at":"2026-07-05T08:21:12.354340+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJ3IIR3L","created_at":"2026-07-05T08:21:12.354340+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03660","citing_title":"From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2602.08324","citing_title":"Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19228","citing_title":"Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04942","citing_title":"TDA-RC: Task-Driven Alignment for Knowledge-Based Reasoning Chains in Large Language Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15727","citing_title":"Structured Abductive-Deductive-Inductive Reasoning for LLMs via Algebraic Invariants","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OJ3IIR3LA6REQIAPNB4JRKAB27","json":"https://pith.science/pith/OJ3IIR3LA6REQIAPNB4JRKAB27.json","graph_json":"https://pith.science/api/pith-number/OJ3IIR3LA6REQIAPNB4JRKAB27/graph.json","events_json":"https://pith.science/api/pith-number/OJ3IIR3LA6REQIAPNB4JRKAB27/events.json","paper":"https://pith.science/paper/OJ3IIR3L"},"agent_actions":{"view_html":"https://pith.science/pith/OJ3IIR3LA6REQIAPNB4JRKAB27","download_json":"https://pith.science/pith/OJ3IIR3LA6REQIAPNB4JRKAB27.json","view_paper":"https://pith.science/paper/OJ3IIR3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00559&json=true","fetch_graph":"https://pith.science/api/pith-number/OJ3IIR3LA6REQIAPNB4JRKAB27/graph.json","fetch_events":"https://pith.science/api/pith-number/OJ3IIR3LA6REQIAPNB4JRKAB27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJ3IIR3LA6REQIAPNB4JRKAB27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJ3IIR3LA6REQIAPNB4JRKAB27/action/storage_attestation","attest_author":"https://pith.science/pith/OJ3IIR3LA6REQIAPNB4JRKAB27/action/author_attestation","sign_citation":"https://pith.science/pith/OJ3IIR3LA6REQIAPNB4JRKAB27/action/citation_signature","submit_replication":"https://pith.science/pith/OJ3IIR3LA6REQIAPNB4JRKAB27/action/replication_record"}},"created_at":"2026-07-05T08:21:12.354340+00:00","updated_at":"2026-07-05T08:21:12.354340+00:00"}