{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BTFPWZQG7MM74P64X4FBU2WQXC","short_pith_number":"pith:BTFPWZQG","schema_version":"1.0","canonical_sha256":"0ccafb6606fb19fe3fdcbf0a1a6ad0b88ff4e80ffa261dd724c3cbaf0856fb58","source":{"kind":"arxiv","id":"2308.09267","version":4},"attestation_state":"computed","paper":{"title":"GraphReason: Enhancing Reasoning Capabilities of Large Language Models through A Graph-Based Verification Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lang Cao","submitted_at":"2023-08-18T03:12:59Z","abstract_excerpt":"Large Language Models (LLMs) have showcased impressive reasoning capabilities, particularly when guided by specifically designed prompts in complex reasoning tasks such as math word problems. These models typically solve tasks using a chain-of-thought approach, which not only bolsters their reasoning abilities but also provides valuable insights into their problem-solving process. However, there is still significant room for enhancing the reasoning abilities of LLMs. Some studies suggest that the integration of an LLM output verifier can boost reasoning accuracy without necessitating additiona"},"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":"2308.09267","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-18T03:12:59Z","cross_cats_sorted":[],"title_canon_sha256":"73c0fac9f099f80e22bc833b087b3a87f8a3cced96c7ceed023966f1c8e945ab","abstract_canon_sha256":"3538ab348bb1505baec0fa335ae960568b72c049c101ecf5bc65eb9f17fc2763"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:16.344775Z","signature_b64":"teGpxzRYYUojj9iAhB8WwsBD9L7sVJqF5whu93whBTbgvi/Ukr+ujB92x62xgHTVWB+R/cnHpF1U0/ZAjOCABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ccafb6606fb19fe3fdcbf0a1a6ad0b88ff4e80ffa261dd724c3cbaf0856fb58","last_reissued_at":"2026-07-05T08:10:16.344253Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:16.344253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphReason: Enhancing Reasoning Capabilities of Large Language Models through A Graph-Based Verification Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lang Cao","submitted_at":"2023-08-18T03:12:59Z","abstract_excerpt":"Large Language Models (LLMs) have showcased impressive reasoning capabilities, particularly when guided by specifically designed prompts in complex reasoning tasks such as math word problems. These models typically solve tasks using a chain-of-thought approach, which not only bolsters their reasoning abilities but also provides valuable insights into their problem-solving process. However, there is still significant room for enhancing the reasoning abilities of LLMs. Some studies suggest that the integration of an LLM output verifier can boost reasoning accuracy without necessitating additiona"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09267","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/2308.09267/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":"2308.09267","created_at":"2026-07-05T08:10:16.344327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.09267v4","created_at":"2026-07-05T08:10:16.344327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09267","created_at":"2026-07-05T08:10:16.344327+00:00"},{"alias_kind":"pith_short_12","alias_value":"BTFPWZQG7MM7","created_at":"2026-07-05T08:10:16.344327+00:00"},{"alias_kind":"pith_short_16","alias_value":"BTFPWZQG7MM74P64","created_at":"2026-07-05T08:10:16.344327+00:00"},{"alias_kind":"pith_short_8","alias_value":"BTFPWZQG","created_at":"2026-07-05T08:10:16.344327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19228","citing_title":"Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BTFPWZQG7MM74P64X4FBU2WQXC","json":"https://pith.science/pith/BTFPWZQG7MM74P64X4FBU2WQXC.json","graph_json":"https://pith.science/api/pith-number/BTFPWZQG7MM74P64X4FBU2WQXC/graph.json","events_json":"https://pith.science/api/pith-number/BTFPWZQG7MM74P64X4FBU2WQXC/events.json","paper":"https://pith.science/paper/BTFPWZQG"},"agent_actions":{"view_html":"https://pith.science/pith/BTFPWZQG7MM74P64X4FBU2WQXC","download_json":"https://pith.science/pith/BTFPWZQG7MM74P64X4FBU2WQXC.json","view_paper":"https://pith.science/paper/BTFPWZQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.09267&json=true","fetch_graph":"https://pith.science/api/pith-number/BTFPWZQG7MM74P64X4FBU2WQXC/graph.json","fetch_events":"https://pith.science/api/pith-number/BTFPWZQG7MM74P64X4FBU2WQXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BTFPWZQG7MM74P64X4FBU2WQXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BTFPWZQG7MM74P64X4FBU2WQXC/action/storage_attestation","attest_author":"https://pith.science/pith/BTFPWZQG7MM74P64X4FBU2WQXC/action/author_attestation","sign_citation":"https://pith.science/pith/BTFPWZQG7MM74P64X4FBU2WQXC/action/citation_signature","submit_replication":"https://pith.science/pith/BTFPWZQG7MM74P64X4FBU2WQXC/action/replication_record"}},"created_at":"2026-07-05T08:10:16.344327+00:00","updated_at":"2026-07-05T08:10:16.344327+00:00"}