{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IFVCT2TKKSK3YM4E7BJN2I5IGG","short_pith_number":"pith:IFVCT2TK","schema_version":"1.0","canonical_sha256":"416a29ea6a5495bc3384f852dd23a8318748a5ac9c8e6dfa0bfb949674f0af72","source":{"kind":"arxiv","id":"2211.17257","version":1},"attestation_state":"computed","paper":{"title":"CREPE: Open-Domain Question Answering with False Presuppositions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hannaneh Hajishirzi, Luke Zettlemoyer, Sewon Min, Xinyan Velocity Yu","submitted_at":"2022-11-30T18:54:49Z","abstract_excerpt":"Information seeking users often pose questions with false presuppositions, especially when asking about unfamiliar topics. Most existing question answering (QA) datasets, in contrast, assume all questions have well defined answers. We introduce CREPE, a QA dataset containing a natural distribution of presupposition failures from online information-seeking forums. We find that 25% of questions contain false presuppositions, and provide annotations for these presuppositions and their corrections. Through extensive baseline experiments, we show that adaptations of existing open-domain QA models c"},"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":"2211.17257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-30T18:54:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"34e6e4e2cea835fa10596f9d841418373765924f0079c3559245e7833700965f","abstract_canon_sha256":"02ffde106e7b65574ca77f32f86866e77e836e1ca0e7f215fcdeec188c495c9b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:16.553080Z","signature_b64":"EhAco3gymJCPU1pUGL5CQjO7m2QmpdFmgmN4HUGxv5X3NNP9RM+FMtx/YU0TtpejVccBYIWrrYpTPUfhSgeNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"416a29ea6a5495bc3384f852dd23a8318748a5ac9c8e6dfa0bfb949674f0af72","last_reissued_at":"2026-07-05T05:21:16.552622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:16.552622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CREPE: Open-Domain Question Answering with False Presuppositions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hannaneh Hajishirzi, Luke Zettlemoyer, Sewon Min, Xinyan Velocity Yu","submitted_at":"2022-11-30T18:54:49Z","abstract_excerpt":"Information seeking users often pose questions with false presuppositions, especially when asking about unfamiliar topics. Most existing question answering (QA) datasets, in contrast, assume all questions have well defined answers. We introduce CREPE, a QA dataset containing a natural distribution of presupposition failures from online information-seeking forums. We find that 25% of questions contain false presuppositions, and provide annotations for these presuppositions and their corrections. Through extensive baseline experiments, we show that adaptations of existing open-domain QA models c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.17257","kind":"arxiv","version":1},"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/2211.17257/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":"2211.17257","created_at":"2026-07-05T05:21:16.552680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.17257v1","created_at":"2026-07-05T05:21:16.552680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.17257","created_at":"2026-07-05T05:21:16.552680+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFVCT2TKKSK3","created_at":"2026-07-05T05:21:16.552680+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFVCT2TKKSK3YM4E","created_at":"2026-07-05T05:21:16.552680+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFVCT2TK","created_at":"2026-07-05T05:21:16.552680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06476","citing_title":"Towards Emotion Consistency Analysis of Large Language Models in Emotional Conversational Contexts","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IFVCT2TKKSK3YM4E7BJN2I5IGG","json":"https://pith.science/pith/IFVCT2TKKSK3YM4E7BJN2I5IGG.json","graph_json":"https://pith.science/api/pith-number/IFVCT2TKKSK3YM4E7BJN2I5IGG/graph.json","events_json":"https://pith.science/api/pith-number/IFVCT2TKKSK3YM4E7BJN2I5IGG/events.json","paper":"https://pith.science/paper/IFVCT2TK"},"agent_actions":{"view_html":"https://pith.science/pith/IFVCT2TKKSK3YM4E7BJN2I5IGG","download_json":"https://pith.science/pith/IFVCT2TKKSK3YM4E7BJN2I5IGG.json","view_paper":"https://pith.science/paper/IFVCT2TK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.17257&json=true","fetch_graph":"https://pith.science/api/pith-number/IFVCT2TKKSK3YM4E7BJN2I5IGG/graph.json","fetch_events":"https://pith.science/api/pith-number/IFVCT2TKKSK3YM4E7BJN2I5IGG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFVCT2TKKSK3YM4E7BJN2I5IGG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFVCT2TKKSK3YM4E7BJN2I5IGG/action/storage_attestation","attest_author":"https://pith.science/pith/IFVCT2TKKSK3YM4E7BJN2I5IGG/action/author_attestation","sign_citation":"https://pith.science/pith/IFVCT2TKKSK3YM4E7BJN2I5IGG/action/citation_signature","submit_replication":"https://pith.science/pith/IFVCT2TKKSK3YM4E7BJN2I5IGG/action/replication_record"}},"created_at":"2026-07-05T05:21:16.552680+00:00","updated_at":"2026-07-05T05:21:16.552680+00:00"}