{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WXQH65645HCS5AXZ42OENMOPUW","short_pith_number":"pith:WXQH6564","schema_version":"1.0","canonical_sha256":"b5e07f77dce9c52e82f9e69c46b1cfa5ad4181095b7470e0ea3af32412979852","source":{"kind":"arxiv","id":"2406.11341","version":3},"attestation_state":"computed","paper":{"title":"A Systematic Analysis of Large Language Models as Soft Reasoners: The Case of Syllogistic Inferences","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Albert Gatt, Leonardo Bertolazzi, Raffaella Bernardi","submitted_at":"2024-06-17T08:59:04Z","abstract_excerpt":"The reasoning abilities of Large Language Models (LLMs) are becoming a central focus of study in NLP. In this paper, we consider the case of syllogistic reasoning, an area of deductive reasoning studied extensively in logic and cognitive psychology. Previous research has shown that pre-trained LLMs exhibit reasoning biases, such as $\\textit{content effects}$, avoid answering that $\\textit{no conclusion follows}$, display human-like difficulties, and struggle with multi-step reasoning. We contribute to this research line by systematically investigating the effects of chain-of-thought reasoning,"},"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":"2406.11341","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T08:59:04Z","cross_cats_sorted":[],"title_canon_sha256":"880df3f87e4299c30b665916f7cd2cced79a113a4ec61683717ed5665b35e8b6","abstract_canon_sha256":"0acb8a8a3b92c3bbe561d15fea3d733cc8f646685e43a89d4698c9c946b10f8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:45.558933Z","signature_b64":"3ZFoReClCOQZxj/KfWdgyAmE4RhvE3rI9ITL3MiiB44Wu0+6BMREL2fF3FN36X4qaeNNbK4nYXTjiojPe7LwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5e07f77dce9c52e82f9e69c46b1cfa5ad4181095b7470e0ea3af32412979852","last_reissued_at":"2026-07-05T09:21:45.558498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:45.558498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Systematic Analysis of Large Language Models as Soft Reasoners: The Case of Syllogistic Inferences","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Albert Gatt, Leonardo Bertolazzi, Raffaella Bernardi","submitted_at":"2024-06-17T08:59:04Z","abstract_excerpt":"The reasoning abilities of Large Language Models (LLMs) are becoming a central focus of study in NLP. In this paper, we consider the case of syllogistic reasoning, an area of deductive reasoning studied extensively in logic and cognitive psychology. Previous research has shown that pre-trained LLMs exhibit reasoning biases, such as $\\textit{content effects}$, avoid answering that $\\textit{no conclusion follows}$, display human-like difficulties, and struggle with multi-step reasoning. We contribute to this research line by systematically investigating the effects of chain-of-thought reasoning,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11341","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/2406.11341/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":"2406.11341","created_at":"2026-07-05T09:21:45.558555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11341v3","created_at":"2026-07-05T09:21:45.558555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11341","created_at":"2026-07-05T09:21:45.558555+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXQH65645HCS","created_at":"2026-07-05T09:21:45.558555+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXQH65645HCS5AXZ","created_at":"2026-07-05T09:21:45.558555+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXQH6564","created_at":"2026-07-05T09:21:45.558555+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15748","citing_title":"Critique of Impure Reason: Unveiling the reasoning behaviour of medical Large Language Models","ref_index":89,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WXQH65645HCS5AXZ42OENMOPUW","json":"https://pith.science/pith/WXQH65645HCS5AXZ42OENMOPUW.json","graph_json":"https://pith.science/api/pith-number/WXQH65645HCS5AXZ42OENMOPUW/graph.json","events_json":"https://pith.science/api/pith-number/WXQH65645HCS5AXZ42OENMOPUW/events.json","paper":"https://pith.science/paper/WXQH6564"},"agent_actions":{"view_html":"https://pith.science/pith/WXQH65645HCS5AXZ42OENMOPUW","download_json":"https://pith.science/pith/WXQH65645HCS5AXZ42OENMOPUW.json","view_paper":"https://pith.science/paper/WXQH6564","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11341&json=true","fetch_graph":"https://pith.science/api/pith-number/WXQH65645HCS5AXZ42OENMOPUW/graph.json","fetch_events":"https://pith.science/api/pith-number/WXQH65645HCS5AXZ42OENMOPUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXQH65645HCS5AXZ42OENMOPUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXQH65645HCS5AXZ42OENMOPUW/action/storage_attestation","attest_author":"https://pith.science/pith/WXQH65645HCS5AXZ42OENMOPUW/action/author_attestation","sign_citation":"https://pith.science/pith/WXQH65645HCS5AXZ42OENMOPUW/action/citation_signature","submit_replication":"https://pith.science/pith/WXQH65645HCS5AXZ42OENMOPUW/action/replication_record"}},"created_at":"2026-07-05T09:21:45.558555+00:00","updated_at":"2026-07-05T09:21:45.558555+00:00"}