{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TO7S2ELHTBHW4FYY2WRTOASAOK","short_pith_number":"pith:TO7S2ELH","schema_version":"1.0","canonical_sha256":"9bbf2d1167984f6e1718d5a337024072854ec4e228b8b3380322fd6fb7d9eff6","source":{"kind":"arxiv","id":"1911.11641","version":1},"attestation_state":"computed","paper":{"title":"PIQA: Reasoning about Physical Commonsense in Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Large pretrained models reach only 77 percent accuracy on physical commonsense questions that humans answer at 95 percent.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jianfeng Gao, Ronan Le Bras, Rowan Zellers, Yejin Choi, Yonatan Bisk","submitted_at":"2019-11-26T15:31:46Z","abstract_excerpt":"To apply eyeshadow without a brush, should I use a cotton swab or a toothpick? Questions requiring this kind of physical commonsense pose a challenge to today's natural language understanding systems. While recent pretrained models (such as BERT) have made progress on question answering over more abstract domains - such as news articles and encyclopedia entries, where text is plentiful - in more physical domains, text is inherently limited due to reporting bias. Can AI systems learn to reliably answer physical common-sense questions without experiencing the physical world? In this paper, we in"},"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":true},"canonical_record":{"source":{"id":"1911.11641","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-26T15:31:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e3a4aee1cb2d205fde52f4d934479050fda3d115f107a611a5e692b7161df23d","abstract_canon_sha256":"8c17cda83691e282f942aa64ce5ea21bb14aa866bfa39c594f09daff64f57594"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:13.765763Z","signature_b64":"vecb4av4wskbD5c0F2q2gsGFRQMUzhdu50qBjIOXFi71Dl5G1cJwip+U5RyCovY6HWpV2XkaH/lZoVxkRJTBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bbf2d1167984f6e1718d5a337024072854ec4e228b8b3380322fd6fb7d9eff6","last_reissued_at":"2026-05-17T23:38:13.765123Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:13.765123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PIQA: Reasoning about Physical Commonsense in Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Large pretrained models reach only 77 percent accuracy on physical commonsense questions that humans answer at 95 percent.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jianfeng Gao, Ronan Le Bras, Rowan Zellers, Yejin Choi, Yonatan Bisk","submitted_at":"2019-11-26T15:31:46Z","abstract_excerpt":"To apply eyeshadow without a brush, should I use a cotton swab or a toothpick? Questions requiring this kind of physical commonsense pose a challenge to today's natural language understanding systems. While recent pretrained models (such as BERT) have made progress on question answering over more abstract domains - such as news articles and encyclopedia entries, where text is plentiful - in more physical domains, text is inherently limited due to reporting bias. Can AI systems learn to reliably answer physical common-sense questions without experiencing the physical world? In this paper, we in"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"large pretrained models struggle (77%). We provide analysis about the dimensions of knowledge that existing models lack, which offers significant opportunities for future research.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the collected PIQA questions genuinely require physical commonsense reasoning and cannot be solved primarily through linguistic patterns or reporting bias present in the training data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PIQA is a new benchmark showing that current AI models achieve 77% on physical commonsense questions versus humans at 95%.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Large pretrained models reach only 77 percent accuracy on physical commonsense questions that humans answer at 95 percent.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"19baf1132d6926b66e49f791e0b60257c465a72c23a1bfb4f3bc723ed74854f3"},"source":{"id":"1911.11641","kind":"arxiv","version":1},"verdict":{"id":"f2f2f679-75c2-4177-9f56-70f1e42efc77","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T14:49:40.257530Z","strongest_claim":"large pretrained models struggle (77%). We provide analysis about the dimensions of knowledge that existing models lack, which offers significant opportunities for future research.","one_line_summary":"PIQA is a new benchmark showing that current AI models achieve 77% on physical commonsense questions versus humans at 95%.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the collected PIQA questions genuinely require physical commonsense reasoning and cannot be solved primarily through linguistic patterns or reporting bias present in the training data.","pith_extraction_headline":"Large pretrained models reach only 77 percent accuracy on physical commonsense questions that humans answer at 95 percent."},"references":{"count":80,"sample":[{"doi":"","year":null,"title":"CVPR , year =","work_id":"374a8d8b-958e-44b8-8c16-270a161b52ae","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"SocialIQA: Commonsense Reasoning about Social Interactions , booktitle =","work_id":"85cba18d-9710-4a1f-baaf-d9afe0f47ee2","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"WINOGRANDE: An Adversarial Winograd Schema Challenge at Scale , author=. AAAI , year=","work_id":"79b330d8-2547-4062-b1ee-339bd722572f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"ACL , year =","work_id":"054e6f64-f7b0-4ec6-aabe-a7f7c9a335da","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"IROS , year =","work_id":"7604fee5-ff70-49f4-befb-6e4f5799963d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":80,"snapshot_sha256":"c4efa8c48324514518d8c4444bd98ac02bb57bc92802696c7cc4d12fde74bb29","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"185f23d4ef10c48d0939a6322566368657620f70ea6a0f46ecb915e77ccfc765"},"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":"1911.11641","created_at":"2026-05-17T23:38:13.765203+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.11641v1","created_at":"2026-05-17T23:38:13.765203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.11641","created_at":"2026-05-17T23:38:13.765203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":18,"sample":[{"citing_arxiv_id":"2512.20856","citing_title":"NVIDIA Nemotron 3: Efficient and Open Intelligence","ref_index":98,"is_internal_anchor":true},{"citing_arxiv_id":"2402.17764","citing_title":"The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2402.17762","citing_title":"Massive Activations in Large Language Models","ref_index":106,"is_internal_anchor":true},{"citing_arxiv_id":"2309.05463","citing_title":"Textbooks Are All You Need II: phi-1.5 technical report","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2603.28239","citing_title":"A Switch-Centric In-Network Architecture for Accelerating LLM Inference in Shared-Memory Network","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11011","citing_title":"LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2403.04652","citing_title":"Yi: Open Foundation Models by 01.AI","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08894","citing_title":"Fitting Is Not Enough: Smoothness in Extremely Quantized LLMs","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2503.01743","citing_title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2402.06196","citing_title":"Large Language Models: A Survey","ref_index":196,"is_internal_anchor":true},{"citing_arxiv_id":"2204.02311","citing_title":"PaLM: Scaling Language Modeling with Pathways","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06169","citing_title":"In-Place Test-Time Training","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2404.14219","citing_title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2403.08295","citing_title":"Gemma: Open Models Based on Gemini Research and Technology","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2009.03300","citing_title":"Measuring Massive Multitask Language Understanding","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2408.00118","citing_title":"Gemma 2: Improving Open Language Models at a Practical Size","ref_index":76,"is_internal_anchor":true},{"citing_arxiv_id":"2005.14165","citing_title":"Language Models are Few-Shot Learners","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18738","citing_title":"Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Large Language Models","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TO7S2ELHTBHW4FYY2WRTOASAOK","json":"https://pith.science/pith/TO7S2ELHTBHW4FYY2WRTOASAOK.json","graph_json":"https://pith.science/api/pith-number/TO7S2ELHTBHW4FYY2WRTOASAOK/graph.json","events_json":"https://pith.science/api/pith-number/TO7S2ELHTBHW4FYY2WRTOASAOK/events.json","paper":"https://pith.science/paper/TO7S2ELH"},"agent_actions":{"view_html":"https://pith.science/pith/TO7S2ELHTBHW4FYY2WRTOASAOK","download_json":"https://pith.science/pith/TO7S2ELHTBHW4FYY2WRTOASAOK.json","view_paper":"https://pith.science/paper/TO7S2ELH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.11641&json=true","fetch_graph":"https://pith.science/api/pith-number/TO7S2ELHTBHW4FYY2WRTOASAOK/graph.json","fetch_events":"https://pith.science/api/pith-number/TO7S2ELHTBHW4FYY2WRTOASAOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TO7S2ELHTBHW4FYY2WRTOASAOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TO7S2ELHTBHW4FYY2WRTOASAOK/action/storage_attestation","attest_author":"https://pith.science/pith/TO7S2ELHTBHW4FYY2WRTOASAOK/action/author_attestation","sign_citation":"https://pith.science/pith/TO7S2ELHTBHW4FYY2WRTOASAOK/action/citation_signature","submit_replication":"https://pith.science/pith/TO7S2ELHTBHW4FYY2WRTOASAOK/action/replication_record"}},"created_at":"2026-05-17T23:38:13.765203+00:00","updated_at":"2026-05-17T23:38:13.765203+00:00"}