{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SBJH2K4V3D6WUS5UU3V6NIK7AD","short_pith_number":"pith:SBJH2K4V","schema_version":"1.0","canonical_sha256":"90527d2b95d8fd6a4bb4a6ebe6a15f00cd68393f1eaa47092cc818e4ce99e62f","source":{"kind":"arxiv","id":"2406.18762","version":2},"attestation_state":"computed","paper":{"title":"Categorical Syllogisms Revisited: A Review of the Logical Reasoning Abilities of LLMs for Analyzing Categorical Syllogism","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jimmy Lin, Shi Zong","submitted_at":"2024-06-26T21:17:20Z","abstract_excerpt":"There have been a huge number of benchmarks proposed to evaluate how large language models (LLMs) behave for logic inference tasks. However, it remains an open question how to properly evaluate this ability. In this paper, we provide a systematic overview of prior works on the logical reasoning ability of LLMs for analyzing categorical syllogisms. We first investigate all the possible variations for the categorical syllogisms from a purely logical perspective and then examine the underlying configurations (i.e., mood and figure) tested by the existing datasets. Our results indicate that compar"},"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":"2406.18762","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T21:17:20Z","cross_cats_sorted":[],"title_canon_sha256":"eb3344725f9ef110a073beab3ea232eac706e9e746b2e525c5edc21df7ce4418","abstract_canon_sha256":"a385c728d3883da29a2cad82e1d843c2349395eaa521fc0b43bdb596bd3114a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:55.664660Z","signature_b64":"4UCVjWWBUo6OMghosYPKGkGg00jmCeJXbArFZTi6RmIoBjq459LWa9ukObzUxJcbQHr7lxhbadbEymuYhL42DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90527d2b95d8fd6a4bb4a6ebe6a15f00cd68393f1eaa47092cc818e4ce99e62f","last_reissued_at":"2026-07-05T09:47:55.664210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:55.664210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Categorical Syllogisms Revisited: A Review of the Logical Reasoning Abilities of LLMs for Analyzing Categorical Syllogism","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jimmy Lin, Shi Zong","submitted_at":"2024-06-26T21:17:20Z","abstract_excerpt":"There have been a huge number of benchmarks proposed to evaluate how large language models (LLMs) behave for logic inference tasks. However, it remains an open question how to properly evaluate this ability. In this paper, we provide a systematic overview of prior works on the logical reasoning ability of LLMs for analyzing categorical syllogisms. We first investigate all the possible variations for the categorical syllogisms from a purely logical perspective and then examine the underlying configurations (i.e., mood and figure) tested by the existing datasets. Our results indicate that compar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18762","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/2406.18762/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":"2406.18762","created_at":"2026-07-05T09:47:55.664281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18762v2","created_at":"2026-07-05T09:47:55.664281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18762","created_at":"2026-07-05T09:47:55.664281+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBJH2K4V3D6W","created_at":"2026-07-05T09:47:55.664281+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBJH2K4V3D6WUS5U","created_at":"2026-07-05T09:47:55.664281+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBJH2K4V","created_at":"2026-07-05T09:47:55.664281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09589","citing_title":"Logical forms complement probability in understanding language model (and human) performance","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SBJH2K4V3D6WUS5UU3V6NIK7AD","json":"https://pith.science/pith/SBJH2K4V3D6WUS5UU3V6NIK7AD.json","graph_json":"https://pith.science/api/pith-number/SBJH2K4V3D6WUS5UU3V6NIK7AD/graph.json","events_json":"https://pith.science/api/pith-number/SBJH2K4V3D6WUS5UU3V6NIK7AD/events.json","paper":"https://pith.science/paper/SBJH2K4V"},"agent_actions":{"view_html":"https://pith.science/pith/SBJH2K4V3D6WUS5UU3V6NIK7AD","download_json":"https://pith.science/pith/SBJH2K4V3D6WUS5UU3V6NIK7AD.json","view_paper":"https://pith.science/paper/SBJH2K4V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18762&json=true","fetch_graph":"https://pith.science/api/pith-number/SBJH2K4V3D6WUS5UU3V6NIK7AD/graph.json","fetch_events":"https://pith.science/api/pith-number/SBJH2K4V3D6WUS5UU3V6NIK7AD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBJH2K4V3D6WUS5UU3V6NIK7AD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBJH2K4V3D6WUS5UU3V6NIK7AD/action/storage_attestation","attest_author":"https://pith.science/pith/SBJH2K4V3D6WUS5UU3V6NIK7AD/action/author_attestation","sign_citation":"https://pith.science/pith/SBJH2K4V3D6WUS5UU3V6NIK7AD/action/citation_signature","submit_replication":"https://pith.science/pith/SBJH2K4V3D6WUS5UU3V6NIK7AD/action/replication_record"}},"created_at":"2026-07-05T09:47:55.664281+00:00","updated_at":"2026-07-05T09:47:55.664281+00:00"}