{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KNNUNPQLKPINKLHMHYAKLE5EXW","short_pith_number":"pith:KNNUNPQL","schema_version":"1.0","canonical_sha256":"535b46be0b53d0d52cec3e00a593a4bda6745353f6f5bce961070a1d11ce44e7","source":{"kind":"arxiv","id":"2406.00179","version":1},"attestation_state":"computed","paper":{"title":"Long-Span Question-Answering: Automatic Question Generation and QA-System Ranking via Side-by-Side Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aaron T Parisi, Angeliki Lazaridou, Azade Nova, Bernd Bohnet, Hanie Sedghi, Javier Snaider, Kevin Swersky, Michael Collins, Noah Fiedel, Orhan Firat, Pranjal Awasthi, Rosanne Liu","submitted_at":"2024-05-31T20:15:10Z","abstract_excerpt":"We explore the use of long-context capabilities in large language models to create synthetic reading comprehension data from entire books. Previous efforts to construct such datasets relied on crowd-sourcing, but the emergence of transformers with a context size of 1 million or more tokens now enables entirely automatic approaches. Our objective is to test the capabilities of LLMs to analyze, understand, and reason over problems that require a detailed comprehension of long spans of text, such as questions involving character arcs, broader themes, or the consequences of early actions later 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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2406.00179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-31T20:15:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7488df44c4e6a761e67bc24c1ac75ac3ddf34fc9cf30d171819b2a01da8d61cf","abstract_canon_sha256":"4d50011518d1ce7a9eb52ed5f23b477fd2fd9cde0af3edbb1f8e6669fc8bfbe2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:58.163363Z","signature_b64":"Cibu3mKiq4Oq7xjXefzbZ5OLhMZLUxi/f8sTcf97O7bbRfh63uqHX91UaIpGzTodODKxG+5UJPWQQ29HnrLnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"535b46be0b53d0d52cec3e00a593a4bda6745353f6f5bce961070a1d11ce44e7","last_reissued_at":"2026-07-05T08:25:58.162799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:58.162799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long-Span Question-Answering: Automatic Question Generation and QA-System Ranking via Side-by-Side Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aaron T Parisi, Angeliki Lazaridou, Azade Nova, Bernd Bohnet, Hanie Sedghi, Javier Snaider, Kevin Swersky, Michael Collins, Noah Fiedel, Orhan Firat, Pranjal Awasthi, Rosanne Liu","submitted_at":"2024-05-31T20:15:10Z","abstract_excerpt":"We explore the use of long-context capabilities in large language models to create synthetic reading comprehension data from entire books. Previous efforts to construct such datasets relied on crowd-sourcing, but the emergence of transformers with a context size of 1 million or more tokens now enables entirely automatic approaches. Our objective is to test the capabilities of LLMs to analyze, understand, and reason over problems that require a detailed comprehension of long spans of text, such as questions involving character arcs, broader themes, or the consequences of early actions later in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00179","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/2406.00179/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":"2406.00179","created_at":"2026-07-05T08:25:58.162868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00179v1","created_at":"2026-07-05T08:25:58.162868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00179","created_at":"2026-07-05T08:25:58.162868+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNNUNPQLKPIN","created_at":"2026-07-05T08:25:58.162868+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNNUNPQLKPINKLHM","created_at":"2026-07-05T08:25:58.162868+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNNUNPQL","created_at":"2026-07-05T08:25:58.162868+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KNNUNPQLKPINKLHMHYAKLE5EXW","json":"https://pith.science/pith/KNNUNPQLKPINKLHMHYAKLE5EXW.json","graph_json":"https://pith.science/api/pith-number/KNNUNPQLKPINKLHMHYAKLE5EXW/graph.json","events_json":"https://pith.science/api/pith-number/KNNUNPQLKPINKLHMHYAKLE5EXW/events.json","paper":"https://pith.science/paper/KNNUNPQL"},"agent_actions":{"view_html":"https://pith.science/pith/KNNUNPQLKPINKLHMHYAKLE5EXW","download_json":"https://pith.science/pith/KNNUNPQLKPINKLHMHYAKLE5EXW.json","view_paper":"https://pith.science/paper/KNNUNPQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00179&json=true","fetch_graph":"https://pith.science/api/pith-number/KNNUNPQLKPINKLHMHYAKLE5EXW/graph.json","fetch_events":"https://pith.science/api/pith-number/KNNUNPQLKPINKLHMHYAKLE5EXW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNNUNPQLKPINKLHMHYAKLE5EXW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNNUNPQLKPINKLHMHYAKLE5EXW/action/storage_attestation","attest_author":"https://pith.science/pith/KNNUNPQLKPINKLHMHYAKLE5EXW/action/author_attestation","sign_citation":"https://pith.science/pith/KNNUNPQLKPINKLHMHYAKLE5EXW/action/citation_signature","submit_replication":"https://pith.science/pith/KNNUNPQLKPINKLHMHYAKLE5EXW/action/replication_record"}},"created_at":"2026-07-05T08:25:58.162868+00:00","updated_at":"2026-07-05T08:25:58.162868+00:00"}