{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FERP7UN3IEHUJRI2Y3JU3QG6UR","short_pith_number":"pith:FERP7UN3","schema_version":"1.0","canonical_sha256":"2922ffd1bb410f44c51ac6d34dc0dea4423380b83f7a65ca7895e1f8f0b93256","source":{"kind":"arxiv","id":"2605.12918","version":1},"attestation_state":"computed","paper":{"title":"CommonWhy: A Dataset for Evaluating Entity-Based Causal Commonsense Reasoning in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CommonWhy introduces 15,000 why questions that test whether LLMs can combine specific entity facts with causal commonsense inference","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Armin Toroghi, Faeze Moradi Kalarde, Scott Sanner","submitted_at":"2026-05-13T02:47:21Z","abstract_excerpt":"To effectively interact with the real world, Large Language Models (LLMs) require entity-based commonsense reasoning, a challenging task that necessitates integrating factual knowledge about specific entities with commonsense inference. Existing datasets for evaluating LLM entity-based commonsense reasoning have largely focused on True/False or multiple-choice questions, leaving the explicit assessment of the model's ability in abductive reasoning about causes and effects and generating explanations largely unexamined. In this work, we introduce CommonWhy, a dataset of 15,000 why questions des"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.12918","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T02:47:21Z","cross_cats_sorted":[],"title_canon_sha256":"3abb3e7e165af69dcb2ed63b40b440f667de36b49ab7f513f7642a9b5477c766","abstract_canon_sha256":"9592c8faa0e8b886c12b3b87214f6e419c5f622aa759dae31d6810543695b969"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:10.303242Z","signature_b64":"uwykyFt4qYhdDfmJ24Y1Vvqi0YZwOfDdNxcMLdi94Dsa/orSES2e+61muo0D17s01Vr5IRdwpJ4p1j1AzjE3Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2922ffd1bb410f44c51ac6d34dc0dea4423380b83f7a65ca7895e1f8f0b93256","last_reissued_at":"2026-05-18T03:09:10.302646Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:10.302646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CommonWhy: A Dataset for Evaluating Entity-Based Causal Commonsense Reasoning in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"CommonWhy introduces 15,000 why questions that test whether LLMs can combine specific entity facts with causal commonsense inference","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Armin Toroghi, Faeze Moradi Kalarde, Scott Sanner","submitted_at":"2026-05-13T02:47:21Z","abstract_excerpt":"To effectively interact with the real world, Large Language Models (LLMs) require entity-based commonsense reasoning, a challenging task that necessitates integrating factual knowledge about specific entities with commonsense inference. Existing datasets for evaluating LLM entity-based commonsense reasoning have largely focused on True/False or multiple-choice questions, leaving the explicit assessment of the model's ability in abductive reasoning about causes and effects and generating explanations largely unexamined. In this work, we introduce CommonWhy, a dataset of 15,000 why questions des"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments with state-of-the-art LLMs and LLM-based KGQA methods reveal their significant shortcomings, including frequent factual hallucinations and failures in causal reasoning.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The questions in CommonWhy require genuine integration of entity facts with causal commonsense reasoning rather than being solvable through superficial patterns learned during training.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CommonWhy is a new dataset of 15,000 why-questions for evaluating LLMs on entity-based causal commonsense reasoning grounded in Wikidata.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CommonWhy introduces 15,000 why questions that test whether LLMs can combine specific entity facts with causal commonsense inference","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"168942156c9252f35eef4703d0a82277946ad9fd4eb8f7b6c4486af0c4859e92"},"source":{"id":"2605.12918","kind":"arxiv","version":1},"verdict":{"id":"3898ed84-657f-4b26-82d9-5efa14541b33","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:29:27.984212Z","strongest_claim":"Experiments with state-of-the-art LLMs and LLM-based KGQA methods reveal their significant shortcomings, including frequent factual hallucinations and failures in causal reasoning.","one_line_summary":"CommonWhy is a new dataset of 15,000 why-questions for evaluating LLMs on entity-based causal commonsense reasoning grounded in Wikidata.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The questions in CommonWhy require genuine integration of entity facts with causal commonsense reasoning rather than being solvable through superficial patterns learned during training.","pith_extraction_headline":"CommonWhy introduces 15,000 why questions that test whether LLMs can combine specific entity facts with causal commonsense inference"},"references":{"count":70,"sample":[{"doi":"","year":2005,"title":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. InProceedings of the acl workshop on intrinsic and extrinsic eval","work_id":"a32d6304-97ed-46fc-b35e-43f83cb5451e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"CommAI: Evaluating the first steps towards a useful general AI","work_id":"e668a18c-b63a-4658-aaaf-8ee976ba8d0e","ref_index":2,"cited_arxiv_id":"1701.08954","is_internal_anchor":true},{"doi":"","year":2013,"title":"Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. 2013. Seman- tic parsing on freebase from question-answer pairs. InProceedings of the 2013 conference on empirical methods in natural langua","work_id":"ba594b62-da85-4be6-8345-1820b66064a3","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2013,"title":"Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. 2013. Semantic Parsing on Freebase from Question-Answer Pairs. InProceedings of the 2013 Conference on Empirical Methods in Natural Language","work_id":"a9a8461f-af0f-446a-bf88-c98eb912f05f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"A is B” fail to learn “B is A","work_id":"e5438272-90bc-42ce-b08e-4f225459ecec","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":70,"snapshot_sha256":"daeb71380d12607fc77b9a974812d71deefc70c673faba9a67b39a96531e0e95","internal_anchors":3},"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":"2605.12918","created_at":"2026-05-18T03:09:10.302739+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.12918v1","created_at":"2026-05-18T03:09:10.302739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12918","created_at":"2026-05-18T03:09:10.302739+00:00"},{"alias_kind":"pith_short_12","alias_value":"FERP7UN3IEHU","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"FERP7UN3IEHUJRI2","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"FERP7UN3","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR","json":"https://pith.science/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR.json","graph_json":"https://pith.science/api/pith-number/FERP7UN3IEHUJRI2Y3JU3QG6UR/graph.json","events_json":"https://pith.science/api/pith-number/FERP7UN3IEHUJRI2Y3JU3QG6UR/events.json","paper":"https://pith.science/paper/FERP7UN3"},"agent_actions":{"view_html":"https://pith.science/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR","download_json":"https://pith.science/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR.json","view_paper":"https://pith.science/paper/FERP7UN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.12918&json=true","fetch_graph":"https://pith.science/api/pith-number/FERP7UN3IEHUJRI2Y3JU3QG6UR/graph.json","fetch_events":"https://pith.science/api/pith-number/FERP7UN3IEHUJRI2Y3JU3QG6UR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR/action/storage_attestation","attest_author":"https://pith.science/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR/action/author_attestation","sign_citation":"https://pith.science/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR/action/citation_signature","submit_replication":"https://pith.science/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR/action/replication_record"}},"created_at":"2026-05-18T03:09:10.302739+00:00","updated_at":"2026-05-18T03:09:10.302739+00:00"}