{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:I64F7CI2MFDIRAQHVUUST3L5TM","short_pith_number":"pith:I64F7CI2","schema_version":"1.0","canonical_sha256":"47b85f891a6146888207ad2929ed7d9b38dde062f51b9774faea187ac78a5f9e","source":{"kind":"arxiv","id":"2305.02556","version":1},"attestation_state":"computed","paper":{"title":"Faithful Question Answering with Monte-Carlo Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changshui Zhang, Dong Yu, Hongming Zhang, Hong Zhao, Ruixin Hong","submitted_at":"2023-05-04T05:21:36Z","abstract_excerpt":"Although large language models demonstrate remarkable question-answering performances, revealing the intermediate reasoning steps that the models faithfully follow remains challenging. In this paper, we propose FAME (FAithful question answering with MontE-carlo planning) to answer questions based on faithful reasoning steps. The reasoning steps are organized as a structured entailment tree, which shows how premises are used to produce intermediate conclusions that can prove the correctness of the answer. We formulate the task as a discrete decision-making problem and solve it through the inter"},"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":"2305.02556","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-04T05:21:36Z","cross_cats_sorted":[],"title_canon_sha256":"e78e5175b49b8e60cd782f50dea871aa16570c0239e1d5722787d004a90a36ec","abstract_canon_sha256":"5d893c21f7a8df977ec9a748c0e613be249b9423ef409776703fc125bf37fe9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:02.462666Z","signature_b64":"fHVKJrbxRb+TmB8JaYN4E/pf8WgT44qj1O5CK/D5t0j2Ni+T/0tMiomxYj4SVM1luBwl0IGUOl6cTYkjP4CZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47b85f891a6146888207ad2929ed7d9b38dde062f51b9774faea187ac78a5f9e","last_reissued_at":"2026-07-05T06:07:02.462305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:02.462305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faithful Question Answering with Monte-Carlo Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changshui Zhang, Dong Yu, Hongming Zhang, Hong Zhao, Ruixin Hong","submitted_at":"2023-05-04T05:21:36Z","abstract_excerpt":"Although large language models demonstrate remarkable question-answering performances, revealing the intermediate reasoning steps that the models faithfully follow remains challenging. In this paper, we propose FAME (FAithful question answering with MontE-carlo planning) to answer questions based on faithful reasoning steps. The reasoning steps are organized as a structured entailment tree, which shows how premises are used to produce intermediate conclusions that can prove the correctness of the answer. We formulate the task as a discrete decision-making problem and solve it through the inter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02556","kind":"arxiv","version":1},"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/2305.02556/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":"2305.02556","created_at":"2026-07-05T06:07:02.462374+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.02556v1","created_at":"2026-07-05T06:07:02.462374+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02556","created_at":"2026-07-05T06:07:02.462374+00:00"},{"alias_kind":"pith_short_12","alias_value":"I64F7CI2MFDI","created_at":"2026-07-05T06:07:02.462374+00:00"},{"alias_kind":"pith_short_16","alias_value":"I64F7CI2MFDIRAQH","created_at":"2026-07-05T06:07:02.462374+00:00"},{"alias_kind":"pith_short_8","alias_value":"I64F7CI2","created_at":"2026-07-05T06:07:02.462374+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.16118","citing_title":"Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04449","citing_title":"GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I64F7CI2MFDIRAQHVUUST3L5TM","json":"https://pith.science/pith/I64F7CI2MFDIRAQHVUUST3L5TM.json","graph_json":"https://pith.science/api/pith-number/I64F7CI2MFDIRAQHVUUST3L5TM/graph.json","events_json":"https://pith.science/api/pith-number/I64F7CI2MFDIRAQHVUUST3L5TM/events.json","paper":"https://pith.science/paper/I64F7CI2"},"agent_actions":{"view_html":"https://pith.science/pith/I64F7CI2MFDIRAQHVUUST3L5TM","download_json":"https://pith.science/pith/I64F7CI2MFDIRAQHVUUST3L5TM.json","view_paper":"https://pith.science/paper/I64F7CI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.02556&json=true","fetch_graph":"https://pith.science/api/pith-number/I64F7CI2MFDIRAQHVUUST3L5TM/graph.json","fetch_events":"https://pith.science/api/pith-number/I64F7CI2MFDIRAQHVUUST3L5TM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I64F7CI2MFDIRAQHVUUST3L5TM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I64F7CI2MFDIRAQHVUUST3L5TM/action/storage_attestation","attest_author":"https://pith.science/pith/I64F7CI2MFDIRAQHVUUST3L5TM/action/author_attestation","sign_citation":"https://pith.science/pith/I64F7CI2MFDIRAQHVUUST3L5TM/action/citation_signature","submit_replication":"https://pith.science/pith/I64F7CI2MFDIRAQHVUUST3L5TM/action/replication_record"}},"created_at":"2026-07-05T06:07:02.462374+00:00","updated_at":"2026-07-05T06:07:02.462374+00:00"}