{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:445JYXTPT5SBQTKGXNVAB4XWJI","short_pith_number":"pith:445JYXTP","schema_version":"1.0","canonical_sha256":"e73a9c5e6f9f64184d46bb6a00f2f64a2b193abbed363437782274fff302e4a3","source":{"kind":"arxiv","id":"2306.07932","version":2},"attestation_state":"computed","paper":{"title":"Human-in-the-Loop through Chain-of-Thought","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baobao Chang, Wenjuan Han, Zefan Cai","submitted_at":"2023-06-10T04:31:57Z","abstract_excerpt":"While the emergence of powerful language models along with Chain-of-thought prompting has made automation more and more omnipresent, it sometimes demonstrates its weakness in long-term or multi-step logical reasoning. For example, users don't always get desirable answers for complex mathematical problems without human involvement. Against this background, we present the Manual Correction System (MCS) -- a human-in-the-loop system enhanced by Chain-of-Thought prompting, which explores how manual correction of sub-logics in rationales can improve LLM's reasoning performance. Moving one step forw"},"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":"2306.07932","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-10T04:31:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"04f5c09e195a89f635c68dfd948f36fd05f506a895c176306f80039db011ff9c","abstract_canon_sha256":"f61101cd04757ac5f9736ebef4a11f5372b7b9a3a507a2c5dfc758543abe166b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:00.876974Z","signature_b64":"m96bBuexyVel2oYL4MUsEz71mj4cPJraU+H+H7Kg69EdGlIly3BizSvnUan67dltH0KtVfB/EFAS8jS96TCsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e73a9c5e6f9f64184d46bb6a00f2f64a2b193abbed363437782274fff302e4a3","last_reissued_at":"2026-07-05T06:24:00.876604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:00.876604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-in-the-Loop through Chain-of-Thought","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baobao Chang, Wenjuan Han, Zefan Cai","submitted_at":"2023-06-10T04:31:57Z","abstract_excerpt":"While the emergence of powerful language models along with Chain-of-thought prompting has made automation more and more omnipresent, it sometimes demonstrates its weakness in long-term or multi-step logical reasoning. For example, users don't always get desirable answers for complex mathematical problems without human involvement. Against this background, we present the Manual Correction System (MCS) -- a human-in-the-loop system enhanced by Chain-of-Thought prompting, which explores how manual correction of sub-logics in rationales can improve LLM's reasoning performance. Moving one step forw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07932","kind":"arxiv","version":2},"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/2306.07932/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":"2306.07932","created_at":"2026-07-05T06:24:00.876661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07932v2","created_at":"2026-07-05T06:24:00.876661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07932","created_at":"2026-07-05T06:24:00.876661+00:00"},{"alias_kind":"pith_short_12","alias_value":"445JYXTPT5SB","created_at":"2026-07-05T06:24:00.876661+00:00"},{"alias_kind":"pith_short_16","alias_value":"445JYXTPT5SBQTKG","created_at":"2026-07-05T06:24:00.876661+00:00"},{"alias_kind":"pith_short_8","alias_value":"445JYXTP","created_at":"2026-07-05T06:24:00.876661+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18380","citing_title":"QSTRBench: a New Benchmark to Evaluate the Ability of Language Models to Reason with Qualitative Spatial and Temporal Calculi","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2305.17926","citing_title":"Large Language Models are not Fair Evaluators","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/445JYXTPT5SBQTKGXNVAB4XWJI","json":"https://pith.science/pith/445JYXTPT5SBQTKGXNVAB4XWJI.json","graph_json":"https://pith.science/api/pith-number/445JYXTPT5SBQTKGXNVAB4XWJI/graph.json","events_json":"https://pith.science/api/pith-number/445JYXTPT5SBQTKGXNVAB4XWJI/events.json","paper":"https://pith.science/paper/445JYXTP"},"agent_actions":{"view_html":"https://pith.science/pith/445JYXTPT5SBQTKGXNVAB4XWJI","download_json":"https://pith.science/pith/445JYXTPT5SBQTKGXNVAB4XWJI.json","view_paper":"https://pith.science/paper/445JYXTP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07932&json=true","fetch_graph":"https://pith.science/api/pith-number/445JYXTPT5SBQTKGXNVAB4XWJI/graph.json","fetch_events":"https://pith.science/api/pith-number/445JYXTPT5SBQTKGXNVAB4XWJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/445JYXTPT5SBQTKGXNVAB4XWJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/445JYXTPT5SBQTKGXNVAB4XWJI/action/storage_attestation","attest_author":"https://pith.science/pith/445JYXTPT5SBQTKGXNVAB4XWJI/action/author_attestation","sign_citation":"https://pith.science/pith/445JYXTPT5SBQTKGXNVAB4XWJI/action/citation_signature","submit_replication":"https://pith.science/pith/445JYXTPT5SBQTKGXNVAB4XWJI/action/replication_record"}},"created_at":"2026-07-05T06:24:00.876661+00:00","updated_at":"2026-07-05T06:24:00.876661+00:00"}