{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FERP7UN3IEHUJRI2Y3JU3QG6UR","short_pith_number":"pith:FERP7UN3","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"},"canonical_sha256":"2922ffd1bb410f44c51ac6d34dc0dea4423380b83f7a65ca7895e1f8f0b93256","source":{"kind":"arxiv","id":"2605.12918","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12918","created_at":"2026-05-18T03:09:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12918v1","created_at":"2026-05-18T03:09:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12918","created_at":"2026-05-18T03:09:10Z"},{"alias_kind":"pith_short_12","alias_value":"FERP7UN3IEHU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"FERP7UN3IEHUJRI2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"FERP7UN3","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FERP7UN3IEHUJRI2Y3JU3QG6UR","target":"record","payload":{"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"},"canonical_sha256":"2922ffd1bb410f44c51ac6d34dc0dea4423380b83f7a65ca7895e1f8f0b93256","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"},"source_kind":"arxiv","source_id":"2605.12918","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5Mp02bEjlo1qSn33wbjyGBSI1RJR2tPEPS2vtY74mOgLx71kvt5kNYUzB4QdONc712eLrmaJuv7Bmug0TvLXBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T05:59:39.616495Z"},"content_sha256":"8e1981da29ef666e1b825f6f939701547e204f001c22b8ccc5eb6166aaae6aef","schema_version":"1.0","event_id":"sha256:8e1981da29ef666e1b825f6f939701547e204f001c22b8ccc5eb6166aaae6aef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FERP7UN3IEHUJRI2Y3JU3QG6UR","target":"graph","payload":{"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"},"verdict_id":"3898ed84-657f-4b26-82d9-5efa14541b33"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MC5Ewhw74o6fK2N5W2E2/59+/qi8CmzUtISauGe/+fpkxnlkb8gw+ool40HKX8L0PC3+n5kNo7RbFSXjMlx8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T05:59:39.617472Z"},"content_sha256":"125c624a26d0f6df00e3c32710e5bc8e996df0a5774e4dc5e2c480b15f2ef606","schema_version":"1.0","event_id":"sha256:125c624a26d0f6df00e3c32710e5bc8e996df0a5774e4dc5e2c480b15f2ef606"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR/bundle.json","state_url":"https://pith.science/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-07T05:59:39Z","links":{"resolver":"https://pith.science/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR","bundle":"https://pith.science/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR/bundle.json","state":"https://pith.science/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FERP7UN3IEHUJRI2Y3JU3QG6UR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FERP7UN3IEHUJRI2Y3JU3QG6UR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9592c8faa0e8b886c12b3b87214f6e419c5f622aa759dae31d6810543695b969","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T02:47:21Z","title_canon_sha256":"3abb3e7e165af69dcb2ed63b40b440f667de36b49ab7f513f7642a9b5477c766"},"schema_version":"1.0","source":{"id":"2605.12918","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12918","created_at":"2026-05-18T03:09:10Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12918v1","created_at":"2026-05-18T03:09:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12918","created_at":"2026-05-18T03:09:10Z"},{"alias_kind":"pith_short_12","alias_value":"FERP7UN3IEHU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"FERP7UN3IEHUJRI2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"FERP7UN3","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:125c624a26d0f6df00e3c32710e5bc8e996df0a5774e4dc5e2c480b15f2ef606","target":"graph","created_at":"2026-05-18T03:09:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CommonWhy is a new dataset of 15,000 why-questions for evaluating LLMs on entity-based causal commonsense reasoning grounded in Wikidata."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CommonWhy introduces 15,000 why questions that test whether LLMs can combine specific entity facts with causal commonsense inference"}],"snapshot_sha256":"168942156c9252f35eef4703d0a82277946ad9fd4eb8f7b6c4486af0c4859e92"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Armin Toroghi, Faeze Moradi Kalarde, Scott Sanner","cross_cats":[],"headline":"CommonWhy introduces 15,000 why questions that test whether LLMs can combine specific entity facts with causal commonsense inference","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T02:47:21Z","title":"CommonWhy: A Dataset for Evaluating Entity-Based Causal Commonsense Reasoning in Large Language Models"},"references":{"count":70,"internal_anchors":3,"resolved_work":70,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"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","year":2005},{"cited_arxiv_id":"1701.08954","doi":"","is_internal_anchor":true,"ref_index":2,"title":"CommAI: Evaluating the first steps towards a useful general AI","work_id":"e668a18c-b63a-4658-aaaf-8ee976ba8d0e","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"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","year":2013},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"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","year":2013},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"A is B” fail to learn “B is A","work_id":"e5438272-90bc-42ce-b08e-4f225459ecec","year":2024}],"snapshot_sha256":"daeb71380d12607fc77b9a974812d71deefc70c673faba9a67b39a96531e0e95"},"source":{"id":"2605.12918","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:29:27.984212Z","id":"3898ed84-657f-4b26-82d9-5efa14541b33","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"CommonWhy introduces 15,000 why questions that test whether LLMs can combine specific entity facts with causal commonsense inference","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.","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."}},"verdict_id":"3898ed84-657f-4b26-82d9-5efa14541b33"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8e1981da29ef666e1b825f6f939701547e204f001c22b8ccc5eb6166aaae6aef","target":"record","created_at":"2026-05-18T03:09:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9592c8faa0e8b886c12b3b87214f6e419c5f622aa759dae31d6810543695b969","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T02:47:21Z","title_canon_sha256":"3abb3e7e165af69dcb2ed63b40b440f667de36b49ab7f513f7642a9b5477c766"},"schema_version":"1.0","source":{"id":"2605.12918","kind":"arxiv","version":1}},"canonical_sha256":"2922ffd1bb410f44c51ac6d34dc0dea4423380b83f7a65ca7895e1f8f0b93256","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2922ffd1bb410f44c51ac6d34dc0dea4423380b83f7a65ca7895e1f8f0b93256","first_computed_at":"2026-05-18T03:09:10.302646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:10.302646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uwykyFt4qYhdDfmJ24Y1Vvqi0YZwOfDdNxcMLdi94Dsa/orSES2e+61muo0D17s01Vr5IRdwpJ4p1j1AzjE3Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:10.303242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12918","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e1981da29ef666e1b825f6f939701547e204f001c22b8ccc5eb6166aaae6aef","sha256:125c624a26d0f6df00e3c32710e5bc8e996df0a5774e4dc5e2c480b15f2ef606"],"state_sha256":"c951616325090fb5c8dcdbd5f34fb675625dc869d06de06b2b308ff5f8fda208"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p6zal9HUIV1qSGdA+eN4xqNoJiO0Jnz1ufEQwFE1rAG5FeZNScr0BYU3CWxomt8VtFadmeW2hqbogJssDfXoBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T05:59:39.622105Z","bundle_sha256":"18d83f7e1228607dd240e1209cdd2805e69ae63b5ac66b1e65821d1c8076933b"}}