{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TO7S2ELHTBHW4FYY2WRTOASAOK","short_pith_number":"pith:TO7S2ELH","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"},"canonical_sha256":"9bbf2d1167984f6e1718d5a337024072854ec4e228b8b3380322fd6fb7d9eff6","source":{"kind":"arxiv","id":"1911.11641","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.11641","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"1911.11641v1","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.11641","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"TO7S2ELHTBHW","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TO7S2ELHTBHW4FYY","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TO7S2ELH","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TO7S2ELHTBHW4FYY2WRTOASAOK","target":"record","payload":{"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"},"canonical_sha256":"9bbf2d1167984f6e1718d5a337024072854ec4e228b8b3380322fd6fb7d9eff6","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"},"source_kind":"arxiv","source_id":"1911.11641","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":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MbPR0S/KEOhC4Toy1NyzmYHO07JlUWmLqjqKgYFjQBcCo9EYhwaC3FeGIqIKuCsLZAGjTH1Si2ZvA1dCK8nxBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T18:01:42.501874Z"},"content_sha256":"a8731ad447d64a29c88c0edf8c464df06c4ea8f6da4132873025f780a831ae97","schema_version":"1.0","event_id":"sha256:a8731ad447d64a29c88c0edf8c464df06c4ea8f6da4132873025f780a831ae97"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TO7S2ELHTBHW4FYY2WRTOASAOK","target":"graph","payload":{"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"},"verdict_id":"f2f2f679-75c2-4177-9f56-70f1e42efc77"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wagq6HxPgyZ2DaQYX1jpMKnSh1x1poExKjD7eSpuqrNFvYxri+1pjXqZQjEM97T5EcRIGMG1Jyu92SkwfHyMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-18T18:01:42.502927Z"},"content_sha256":"508e1dfc1ed802e0d66f6cd768cc8500940ed73c0f086786cf88031617238c3d","schema_version":"1.0","event_id":"sha256:508e1dfc1ed802e0d66f6cd768cc8500940ed73c0f086786cf88031617238c3d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TO7S2ELHTBHW4FYY2WRTOASAOK/bundle.json","state_url":"https://pith.science/pith/TO7S2ELHTBHW4FYY2WRTOASAOK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TO7S2ELHTBHW4FYY2WRTOASAOK/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":"2026-05-18T18:01:42Z","links":{"resolver":"https://pith.science/pith/TO7S2ELHTBHW4FYY2WRTOASAOK","bundle":"https://pith.science/pith/TO7S2ELHTBHW4FYY2WRTOASAOK/bundle.json","state":"https://pith.science/pith/TO7S2ELHTBHW4FYY2WRTOASAOK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TO7S2ELHTBHW4FYY2WRTOASAOK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TO7S2ELHTBHW4FYY2WRTOASAOK","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":"8c17cda83691e282f942aa64ce5ea21bb14aa866bfa39c594f09daff64f57594","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-26T15:31:46Z","title_canon_sha256":"e3a4aee1cb2d205fde52f4d934479050fda3d115f107a611a5e692b7161df23d"},"schema_version":"1.0","source":{"id":"1911.11641","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.11641","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"1911.11641v1","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.11641","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"TO7S2ELHTBHW","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TO7S2ELHTBHW4FYY","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TO7S2ELH","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:508e1dfc1ed802e0d66f6cd768cc8500940ed73c0f086786cf88031617238c3d","target":"graph","created_at":"2026-05-17T23:38:13Z","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":"large pretrained models struggle (77%). We provide analysis about the dimensions of knowledge that existing models lack, which offers significant opportunities for future research."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PIQA is a new benchmark showing that current AI models achieve 77% on physical commonsense questions versus humans at 95%."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Large pretrained models reach only 77 percent accuracy on physical commonsense questions that humans answer at 95 percent."}],"snapshot_sha256":"19baf1132d6926b66e49f791e0b60257c465a72c23a1bfb4f3bc723ed74854f3"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"185f23d4ef10c48d0939a6322566368657620f70ea6a0f46ecb915e77ccfc765"},"paper":{"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","authors_text":"Jianfeng Gao, Ronan Le Bras, Rowan Zellers, Yejin Choi, Yonatan Bisk","cross_cats":["cs.AI","cs.LG"],"headline":"Large pretrained models reach only 77 percent accuracy on physical commonsense questions that humans answer at 95 percent.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-26T15:31:46Z","title":"PIQA: Reasoning about Physical Commonsense in Natural Language"},"references":{"count":80,"internal_anchors":4,"resolved_work":80,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"CVPR , year =","work_id":"374a8d8b-958e-44b8-8c16-270a161b52ae","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"SocialIQA: Commonsense Reasoning about Social Interactions , booktitle =","work_id":"85cba18d-9710-4a1f-baaf-d9afe0f47ee2","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"WINOGRANDE: An Adversarial Winograd Schema Challenge at Scale , author=. AAAI , year=","work_id":"79b330d8-2547-4062-b1ee-339bd722572f","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"ACL , year =","work_id":"054e6f64-f7b0-4ec6-aabe-a7f7c9a335da","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"IROS , year =","work_id":"7604fee5-ff70-49f4-befb-6e4f5799963d","year":null}],"snapshot_sha256":"c4efa8c48324514518d8c4444bd98ac02bb57bc92802696c7cc4d12fde74bb29"},"source":{"id":"1911.11641","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-17T14:49:40.257530Z","id":"f2f2f679-75c2-4177-9f56-70f1e42efc77","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Large pretrained models reach only 77 percent accuracy on physical commonsense questions that humans answer at 95 percent.","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.","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."}},"verdict_id":"f2f2f679-75c2-4177-9f56-70f1e42efc77"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a8731ad447d64a29c88c0edf8c464df06c4ea8f6da4132873025f780a831ae97","target":"record","created_at":"2026-05-17T23:38:13Z","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":"8c17cda83691e282f942aa64ce5ea21bb14aa866bfa39c594f09daff64f57594","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-26T15:31:46Z","title_canon_sha256":"e3a4aee1cb2d205fde52f4d934479050fda3d115f107a611a5e692b7161df23d"},"schema_version":"1.0","source":{"id":"1911.11641","kind":"arxiv","version":1}},"canonical_sha256":"9bbf2d1167984f6e1718d5a337024072854ec4e228b8b3380322fd6fb7d9eff6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bbf2d1167984f6e1718d5a337024072854ec4e228b8b3380322fd6fb7d9eff6","first_computed_at":"2026-05-17T23:38:13.765123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:13.765123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vecb4av4wskbD5c0F2q2gsGFRQMUzhdu50qBjIOXFi71Dl5G1cJwip+U5RyCovY6HWpV2XkaH/lZoVxkRJTBBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:13.765763Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.11641","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8731ad447d64a29c88c0edf8c464df06c4ea8f6da4132873025f780a831ae97","sha256:508e1dfc1ed802e0d66f6cd768cc8500940ed73c0f086786cf88031617238c3d"],"state_sha256":"27a4daba8888b2ade0851a49cca14b85c80b201467e5d1165540e915e81699ce"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WED8DpGy3ONX84t0rU3ZJf/1Pw41Thl7XVj3D6odxS1tsE/czhEkihoFAZsXaYjlvtr6Z9vC0ddvYc9YLmZmDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-18T18:01:42.505356Z","bundle_sha256":"00ea6ccefd967860b85ec35f9f9ca86058a666727450c29886526089558292ff"}}