{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IQIGHEPOQH6NFECUPI2VEYFZKO","short_pith_number":"pith:IQIGHEPO","schema_version":"1.0","canonical_sha256":"44106391ee81fcd290547a355260b9539a8844cc77cb9d8f30032efeba12a123","source":{"kind":"arxiv","id":"2402.00658","version":3},"attestation_state":"computed","paper":{"title":"Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chengwei Qin, Fangkai Jiao, Nancy F. Chen, Shafiq Joty, Zhengyuan Liu","submitted_at":"2024-02-01T15:18:33Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated significant potential in handling complex reasoning tasks through step-by-step rationale generation. However, recent studies have raised concerns regarding the hallucination and flaws in their reasoning process. Substantial efforts are being made to improve the reliability and faithfulness of the generated rationales. Some approaches model reasoning as planning, while others focus on annotating for process supervision. Nevertheless, the planning-based search process often results in high latency due to the frequent assessment of intermediate reaso"},"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":"2402.00658","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-02-01T15:18:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"66a2355fc08de77ad3874da0f5c59163756a74838c938cb0bb1455df0e9d0011","abstract_canon_sha256":"44843f464076d282a563dfaa2ee7b6eb8b0762d5610eab0cbf9f8c401f724b07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:39.843063Z","signature_b64":"8ies0r2a+wuuKMj3dQi1QZ9F5yFkJszbVgH8PD6qGmQNhoexsMvoaLO1i4W3X5ZQ9sBcXxRrNoFEgwfTWXY3Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44106391ee81fcd290547a355260b9539a8844cc77cb9d8f30032efeba12a123","last_reissued_at":"2026-07-05T09:20:39.842578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:39.842578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chengwei Qin, Fangkai Jiao, Nancy F. Chen, Shafiq Joty, Zhengyuan Liu","submitted_at":"2024-02-01T15:18:33Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated significant potential in handling complex reasoning tasks through step-by-step rationale generation. However, recent studies have raised concerns regarding the hallucination and flaws in their reasoning process. Substantial efforts are being made to improve the reliability and faithfulness of the generated rationales. Some approaches model reasoning as planning, while others focus on annotating for process supervision. Nevertheless, the planning-based search process often results in high latency due to the frequent assessment of intermediate reaso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00658","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/2402.00658/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":"2402.00658","created_at":"2026-07-05T09:20:39.842639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00658v3","created_at":"2026-07-05T09:20:39.842639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00658","created_at":"2026-07-05T09:20:39.842639+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQIGHEPOQH6N","created_at":"2026-07-05T09:20:39.842639+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQIGHEPOQH6NFECU","created_at":"2026-07-05T09:20:39.842639+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQIGHEPO","created_at":"2026-07-05T09:20:39.842639+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14107","citing_title":"DiagnosisArena: Benchmarking Diagnostic Reasoning for Large Language Models","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IQIGHEPOQH6NFECUPI2VEYFZKO","json":"https://pith.science/pith/IQIGHEPOQH6NFECUPI2VEYFZKO.json","graph_json":"https://pith.science/api/pith-number/IQIGHEPOQH6NFECUPI2VEYFZKO/graph.json","events_json":"https://pith.science/api/pith-number/IQIGHEPOQH6NFECUPI2VEYFZKO/events.json","paper":"https://pith.science/paper/IQIGHEPO"},"agent_actions":{"view_html":"https://pith.science/pith/IQIGHEPOQH6NFECUPI2VEYFZKO","download_json":"https://pith.science/pith/IQIGHEPOQH6NFECUPI2VEYFZKO.json","view_paper":"https://pith.science/paper/IQIGHEPO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00658&json=true","fetch_graph":"https://pith.science/api/pith-number/IQIGHEPOQH6NFECUPI2VEYFZKO/graph.json","fetch_events":"https://pith.science/api/pith-number/IQIGHEPOQH6NFECUPI2VEYFZKO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQIGHEPOQH6NFECUPI2VEYFZKO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQIGHEPOQH6NFECUPI2VEYFZKO/action/storage_attestation","attest_author":"https://pith.science/pith/IQIGHEPOQH6NFECUPI2VEYFZKO/action/author_attestation","sign_citation":"https://pith.science/pith/IQIGHEPOQH6NFECUPI2VEYFZKO/action/citation_signature","submit_replication":"https://pith.science/pith/IQIGHEPOQH6NFECUPI2VEYFZKO/action/replication_record"}},"created_at":"2026-07-05T09:20:39.842639+00:00","updated_at":"2026-07-05T09:20:39.842639+00:00"}