{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5UCKQ5ZRWHXOJCHBNN32PAJH2O","short_pith_number":"pith:5UCKQ5ZR","schema_version":"1.0","canonical_sha256":"ed04a87731b1eee488e16b77a78127d3a2cf801268c820ac060102554aa29e36","source":{"kind":"arxiv","id":"2206.02336","version":3},"attestation_state":"computed","paper":{"title":"Making Large Language Models Better Reasoners with Step-Aware Verifier","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bei Chen, Jian-Guang Lou, Qiang Fu, Shizhuo Zhang, Weizhu Chen, Yifei Li, Zeqi Lin","submitted_at":"2022-06-06T03:38:36Z","abstract_excerpt":"Few-shot learning is a challenging task that requires language models to generalize from limited examples. Large language models like GPT-3 and PaLM have made impressive progress in this area, but they still face difficulties in reasoning tasks such as GSM8K, a benchmark for arithmetic problems. To improve their reasoning skills, previous work has proposed to guide the language model with prompts that elicit a series of reasoning steps before giving the final answer, achieving a significant improvement on GSM8K from 17.9% to 58.1% in problem-solving rate. In this paper, we present DIVERSE (Div"},"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":"2206.02336","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-06T03:38:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"47737b7ea36eb36375d5c8b18fde75ad1beeb1fd4a51398c1384afebc6f1514e","abstract_canon_sha256":"edf1dfbb3188a926dbf60fb28a2a39ed64fcd6b97cc458eb1bcc0c946e112457"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:15.588272Z","signature_b64":"5uv0RrjdwRK/JZn3b/xsT7uUMghpgqHa3724QAuvzYRV8wqR3uhviYVZykLNlrZE7ei4E9PPIQRDHVbZINTvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed04a87731b1eee488e16b77a78127d3a2cf801268c820ac060102554aa29e36","last_reissued_at":"2026-07-05T06:13:15.587742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:15.587742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making Large Language Models Better Reasoners with Step-Aware Verifier","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bei Chen, Jian-Guang Lou, Qiang Fu, Shizhuo Zhang, Weizhu Chen, Yifei Li, Zeqi Lin","submitted_at":"2022-06-06T03:38:36Z","abstract_excerpt":"Few-shot learning is a challenging task that requires language models to generalize from limited examples. Large language models like GPT-3 and PaLM have made impressive progress in this area, but they still face difficulties in reasoning tasks such as GSM8K, a benchmark for arithmetic problems. To improve their reasoning skills, previous work has proposed to guide the language model with prompts that elicit a series of reasoning steps before giving the final answer, achieving a significant improvement on GSM8K from 17.9% to 58.1% in problem-solving rate. In this paper, we present DIVERSE (Div"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02336","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/2206.02336/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":"2206.02336","created_at":"2026-07-05T06:13:15.587806+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.02336v3","created_at":"2026-07-05T06:13:15.587806+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02336","created_at":"2026-07-05T06:13:15.587806+00:00"},{"alias_kind":"pith_short_12","alias_value":"5UCKQ5ZRWHXO","created_at":"2026-07-05T06:13:15.587806+00:00"},{"alias_kind":"pith_short_16","alias_value":"5UCKQ5ZRWHXOJCHB","created_at":"2026-07-05T06:13:15.587806+00:00"},{"alias_kind":"pith_short_8","alias_value":"5UCKQ5ZR","created_at":"2026-07-05T06:13:15.587806+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2211.14275","citing_title":"Solving math word problems with process- and outcome-based feedback","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2410.13181","citing_title":"AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21168","citing_title":"Diverse LLMs or Diverse Question Interpretations? That is the Ensembling Question","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2305.14992","citing_title":"Reasoning with Language Model is Planning with World Model","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2305.04091","citing_title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2207.10397","citing_title":"CodeT: Code Generation with Generated Tests","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2406.06592","citing_title":"Improve Mathematical Reasoning in Language Models by Automated Process Supervision","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09679","citing_title":"Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":161,"is_internal_anchor":false},{"citing_arxiv_id":"2302.00923","citing_title":"Multimodal Chain-of-Thought Reasoning in Language Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2305.10403","citing_title":"PaLM 2 Technical Report","ref_index":267,"is_internal_anchor":false},{"citing_arxiv_id":"2210.09261","citing_title":"Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2305.20050","citing_title":"Let's Verify Step by Step","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5UCKQ5ZRWHXOJCHBNN32PAJH2O","json":"https://pith.science/pith/5UCKQ5ZRWHXOJCHBNN32PAJH2O.json","graph_json":"https://pith.science/api/pith-number/5UCKQ5ZRWHXOJCHBNN32PAJH2O/graph.json","events_json":"https://pith.science/api/pith-number/5UCKQ5ZRWHXOJCHBNN32PAJH2O/events.json","paper":"https://pith.science/paper/5UCKQ5ZR"},"agent_actions":{"view_html":"https://pith.science/pith/5UCKQ5ZRWHXOJCHBNN32PAJH2O","download_json":"https://pith.science/pith/5UCKQ5ZRWHXOJCHBNN32PAJH2O.json","view_paper":"https://pith.science/paper/5UCKQ5ZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.02336&json=true","fetch_graph":"https://pith.science/api/pith-number/5UCKQ5ZRWHXOJCHBNN32PAJH2O/graph.json","fetch_events":"https://pith.science/api/pith-number/5UCKQ5ZRWHXOJCHBNN32PAJH2O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5UCKQ5ZRWHXOJCHBNN32PAJH2O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5UCKQ5ZRWHXOJCHBNN32PAJH2O/action/storage_attestation","attest_author":"https://pith.science/pith/5UCKQ5ZRWHXOJCHBNN32PAJH2O/action/author_attestation","sign_citation":"https://pith.science/pith/5UCKQ5ZRWHXOJCHBNN32PAJH2O/action/citation_signature","submit_replication":"https://pith.science/pith/5UCKQ5ZRWHXOJCHBNN32PAJH2O/action/replication_record"}},"created_at":"2026-07-05T06:13:15.587806+00:00","updated_at":"2026-07-05T06:13:15.587806+00:00"}