{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PT3W64FSSRDTGIYIQGXHVSNZHB","short_pith_number":"pith:PT3W64FS","schema_version":"1.0","canonical_sha256":"7cf76f70b2944733230881ae7ac9b9384d2a4fa29e67b00e1cfd920e2b4b3a3a","source":{"kind":"arxiv","id":"2112.08608","version":2},"attestation_state":"computed","paper":{"title":"QuALITY: Question Answering with Long Input Texts, Yes!","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alicia Parrish, Angelica Chen, He He, Jana Thompson, Jason Phang, Johnny Ma, Nikita Nangia, Nitish Joshi, Richard Yuanzhe Pang, Samuel R. Bowman, Vishakh Padmakumar","submitted_at":"2021-12-16T04:14:38Z","abstract_excerpt":"To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average length of about 5,000 tokens, much longer than typical current models can process. Unlike in prior work with passages, our questions are written and validated by contributors who have read the entire passage, rather than relying on summaries or excerpts. In addition, only half of the questions are answerable by annotators working under tight time constraints, indicating that skimming and simple search are not enough to co"},"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":"2112.08608","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T04:14:38Z","cross_cats_sorted":[],"title_canon_sha256":"29ea8fc219e116a1a9d29fc37e61420601fa3adc314dc47f00405afe086fddaf","abstract_canon_sha256":"013633a025d05a1dbc0a0a8482942d70f16662c238c8e2c6b61476a31a8ad8e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:18.700013Z","signature_b64":"0MlzoYzj+O9VNMKtUmaWZAbYSTeqJlgtwIzQk6UfUoK0+4/pKIOWVZ49Kev9JgvCVpsdy+r7wbdjZIKqS0HHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cf76f70b2944733230881ae7ac9b9384d2a4fa29e67b00e1cfd920e2b4b3a3a","last_reissued_at":"2026-07-05T04:22:18.699532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:18.699532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QuALITY: Question Answering with Long Input Texts, Yes!","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alicia Parrish, Angelica Chen, He He, Jana Thompson, Jason Phang, Johnny Ma, Nikita Nangia, Nitish Joshi, Richard Yuanzhe Pang, Samuel R. Bowman, Vishakh Padmakumar","submitted_at":"2021-12-16T04:14:38Z","abstract_excerpt":"To enable building and testing models on long-document comprehension, we introduce QuALITY, a multiple-choice QA dataset with context passages in English that have an average length of about 5,000 tokens, much longer than typical current models can process. Unlike in prior work with passages, our questions are written and validated by contributors who have read the entire passage, rather than relying on summaries or excerpts. In addition, only half of the questions are answerable by annotators working under tight time constraints, indicating that skimming and simple search are not enough to co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08608","kind":"arxiv","version":2},"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/2112.08608/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":"2112.08608","created_at":"2026-07-05T04:22:18.699593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08608v2","created_at":"2026-07-05T04:22:18.699593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08608","created_at":"2026-07-05T04:22:18.699593+00:00"},{"alias_kind":"pith_short_12","alias_value":"PT3W64FSSRDT","created_at":"2026-07-05T04:22:18.699593+00:00"},{"alias_kind":"pith_short_16","alias_value":"PT3W64FSSRDTGIYI","created_at":"2026-07-05T04:22:18.699593+00:00"},{"alias_kind":"pith_short_8","alias_value":"PT3W64FS","created_at":"2026-07-05T04:22:18.699593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18075","citing_title":"A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04315","citing_title":"Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":130,"is_internal_anchor":false},{"citing_arxiv_id":"2503.04338","citing_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2406.10162","citing_title":"Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models","ref_index":245,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":205,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PT3W64FSSRDTGIYIQGXHVSNZHB","json":"https://pith.science/pith/PT3W64FSSRDTGIYIQGXHVSNZHB.json","graph_json":"https://pith.science/api/pith-number/PT3W64FSSRDTGIYIQGXHVSNZHB/graph.json","events_json":"https://pith.science/api/pith-number/PT3W64FSSRDTGIYIQGXHVSNZHB/events.json","paper":"https://pith.science/paper/PT3W64FS"},"agent_actions":{"view_html":"https://pith.science/pith/PT3W64FSSRDTGIYIQGXHVSNZHB","download_json":"https://pith.science/pith/PT3W64FSSRDTGIYIQGXHVSNZHB.json","view_paper":"https://pith.science/paper/PT3W64FS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08608&json=true","fetch_graph":"https://pith.science/api/pith-number/PT3W64FSSRDTGIYIQGXHVSNZHB/graph.json","fetch_events":"https://pith.science/api/pith-number/PT3W64FSSRDTGIYIQGXHVSNZHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PT3W64FSSRDTGIYIQGXHVSNZHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PT3W64FSSRDTGIYIQGXHVSNZHB/action/storage_attestation","attest_author":"https://pith.science/pith/PT3W64FSSRDTGIYIQGXHVSNZHB/action/author_attestation","sign_citation":"https://pith.science/pith/PT3W64FSSRDTGIYIQGXHVSNZHB/action/citation_signature","submit_replication":"https://pith.science/pith/PT3W64FSSRDTGIYIQGXHVSNZHB/action/replication_record"}},"created_at":"2026-07-05T04:22:18.699593+00:00","updated_at":"2026-07-05T04:22:18.699593+00:00"}