{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B3YVAH5HSQVGIOAEYO5NW7HAN7","short_pith_number":"pith:B3YVAH5H","schema_version":"1.0","canonical_sha256":"0ef1501fa7942a643804c3badb7ce06fccca3b554f686be2dd9ca4611332cd9e","source":{"kind":"arxiv","id":"2310.13552","version":2},"attestation_state":"computed","paper":{"title":"Self-prompted Chain-of-Thought on Large Language Models for Open-domain Multi-hop Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Jinyuan Wang, Junlong Li","submitted_at":"2023-10-20T14:51:10Z","abstract_excerpt":"In open-domain question-answering (ODQA), most existing questions require single-hop reasoning on commonsense. To further extend this task, we officially introduce open-domain multi-hop reasoning (ODMR) by answering multi-hop questions with explicit reasoning steps in open-domain setting. Recently, large language models (LLMs) have found significant utility in facilitating ODQA without external corpus. Furthermore, chain-of-thought (CoT) prompting boosts the reasoning capability of LLMs to a greater extent with manual or automated paradigms. However, existing automated methods lack of quality "},"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":"2310.13552","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-20T14:51:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d0c1df7e3a40b75f8d1e7b5d6483da6e1f17abfbefbb7fb4563ae17a50b5b197","abstract_canon_sha256":"14f098131e57520948e82db361c85e993fc4fd9cbdd53d29b01cd9411d339bfb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:33.104681Z","signature_b64":"SLlUacfpWO/hzRBw5cDv9hahxAijjzJLSpo6W5SKz0HT4jZmpZdDNT/FEx13KOzIcTPa17AVAq1b5oojFZZXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ef1501fa7942a643804c3badb7ce06fccca3b554f686be2dd9ca4611332cd9e","last_reissued_at":"2026-07-05T07:03:33.104210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:33.104210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-prompted Chain-of-Thought on Large Language Models for Open-domain Multi-hop Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Jinyuan Wang, Junlong Li","submitted_at":"2023-10-20T14:51:10Z","abstract_excerpt":"In open-domain question-answering (ODQA), most existing questions require single-hop reasoning on commonsense. To further extend this task, we officially introduce open-domain multi-hop reasoning (ODMR) by answering multi-hop questions with explicit reasoning steps in open-domain setting. Recently, large language models (LLMs) have found significant utility in facilitating ODQA without external corpus. Furthermore, chain-of-thought (CoT) prompting boosts the reasoning capability of LLMs to a greater extent with manual or automated paradigms. However, existing automated methods lack of quality "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13552","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/2310.13552/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":"2310.13552","created_at":"2026-07-05T07:03:33.104268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.13552v2","created_at":"2026-07-05T07:03:33.104268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13552","created_at":"2026-07-05T07:03:33.104268+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3YVAH5HSQVG","created_at":"2026-07-05T07:03:33.104268+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3YVAH5HSQVGIOAE","created_at":"2026-07-05T07:03:33.104268+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3YVAH5H","created_at":"2026-07-05T07:03:33.104268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21119","citing_title":"MammoExpert: Benchmarking Chain-of-Thought Reasoning in Mammography Diagnosis","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B3YVAH5HSQVGIOAEYO5NW7HAN7","json":"https://pith.science/pith/B3YVAH5HSQVGIOAEYO5NW7HAN7.json","graph_json":"https://pith.science/api/pith-number/B3YVAH5HSQVGIOAEYO5NW7HAN7/graph.json","events_json":"https://pith.science/api/pith-number/B3YVAH5HSQVGIOAEYO5NW7HAN7/events.json","paper":"https://pith.science/paper/B3YVAH5H"},"agent_actions":{"view_html":"https://pith.science/pith/B3YVAH5HSQVGIOAEYO5NW7HAN7","download_json":"https://pith.science/pith/B3YVAH5HSQVGIOAEYO5NW7HAN7.json","view_paper":"https://pith.science/paper/B3YVAH5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.13552&json=true","fetch_graph":"https://pith.science/api/pith-number/B3YVAH5HSQVGIOAEYO5NW7HAN7/graph.json","fetch_events":"https://pith.science/api/pith-number/B3YVAH5HSQVGIOAEYO5NW7HAN7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3YVAH5HSQVGIOAEYO5NW7HAN7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3YVAH5HSQVGIOAEYO5NW7HAN7/action/storage_attestation","attest_author":"https://pith.science/pith/B3YVAH5HSQVGIOAEYO5NW7HAN7/action/author_attestation","sign_citation":"https://pith.science/pith/B3YVAH5HSQVGIOAEYO5NW7HAN7/action/citation_signature","submit_replication":"https://pith.science/pith/B3YVAH5HSQVGIOAEYO5NW7HAN7/action/replication_record"}},"created_at":"2026-07-05T07:03:33.104268+00:00","updated_at":"2026-07-05T07:03:33.104268+00:00"}