{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6K2DTJ2H4MY5ALZ6Z7SYUIEYZE","short_pith_number":"pith:6K2DTJ2H","schema_version":"1.0","canonical_sha256":"f2b439a747e331d02f3ecfe58a2098c91be84bcbef71cb8fe24173ad77845411","source":{"kind":"arxiv","id":"2402.17896","version":1},"attestation_state":"computed","paper":{"title":"Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmed Awadallah, Corby Rosset, Ethan C. Chau, Guanghui Qin, Ho-Lam Chung, Jennifer Neville, Nikhil Rao, Zhuo Feng","submitted_at":"2024-02-27T21:27:16Z","abstract_excerpt":"Existing question answering (QA) datasets are no longer challenging to most powerful Large Language Models (LLMs). Traditional QA benchmarks like TriviaQA, NaturalQuestions, ELI5 and HotpotQA mainly study ``known unknowns'' with clear indications of both what information is missing, and how to find it to answer the question. Hence, good performance on these benchmarks provides a false sense of security. A yet unmet need of the NLP community is a bank of non-factoid, multi-perspective questions involving a great deal of unclear information needs, i.e. ``unknown uknowns''. We claim we can find s"},"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":"2402.17896","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-27T21:27:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b842f9acfdce8976b1f84bc7b44a7d4b2d031c4b1258d309f7c0aa4dd4b3685f","abstract_canon_sha256":"2f7403803381271948917ed2d76c0b9a7c6fa7caa98cea9d9783d25df6ab4b91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:09.534140Z","signature_b64":"nNhuIRiwpk4eDcwo9GQ0ms4+G+nvbeaCW2BJlGNCoS99NRGRUV6SnZBAV2Ib2ZgVfkyoBy/x6DvB6i0niP16CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2b439a747e331d02f3ecfe58a2098c91be84bcbef71cb8fe24173ad77845411","last_reissued_at":"2026-07-05T07:50:09.533707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:09.533707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Researchy Questions: A Dataset of Multi-Perspective, Decompositional Questions for LLM Web Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ahmed Awadallah, Corby Rosset, Ethan C. Chau, Guanghui Qin, Ho-Lam Chung, Jennifer Neville, Nikhil Rao, Zhuo Feng","submitted_at":"2024-02-27T21:27:16Z","abstract_excerpt":"Existing question answering (QA) datasets are no longer challenging to most powerful Large Language Models (LLMs). Traditional QA benchmarks like TriviaQA, NaturalQuestions, ELI5 and HotpotQA mainly study ``known unknowns'' with clear indications of both what information is missing, and how to find it to answer the question. Hence, good performance on these benchmarks provides a false sense of security. A yet unmet need of the NLP community is a bank of non-factoid, multi-perspective questions involving a great deal of unclear information needs, i.e. ``unknown uknowns''. We claim we can find s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17896","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/2402.17896/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":"2402.17896","created_at":"2026-07-05T07:50:09.533766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17896v1","created_at":"2026-07-05T07:50:09.533766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17896","created_at":"2026-07-05T07:50:09.533766+00:00"},{"alias_kind":"pith_short_12","alias_value":"6K2DTJ2H4MY5","created_at":"2026-07-05T07:50:09.533766+00:00"},{"alias_kind":"pith_short_16","alias_value":"6K2DTJ2H4MY5ALZ6","created_at":"2026-07-05T07:50:09.533766+00:00"},{"alias_kind":"pith_short_8","alias_value":"6K2DTJ2H","created_at":"2026-07-05T07:50:09.533766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04458","citing_title":"DoGMaTiQ: Automated Generation of Question-and-Answer Nuggets for Report Evaluation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04458","citing_title":"DoGMaTiQ: Automated Generation of Question-and-Answer Nuggets for Report Evaluation","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6K2DTJ2H4MY5ALZ6Z7SYUIEYZE","json":"https://pith.science/pith/6K2DTJ2H4MY5ALZ6Z7SYUIEYZE.json","graph_json":"https://pith.science/api/pith-number/6K2DTJ2H4MY5ALZ6Z7SYUIEYZE/graph.json","events_json":"https://pith.science/api/pith-number/6K2DTJ2H4MY5ALZ6Z7SYUIEYZE/events.json","paper":"https://pith.science/paper/6K2DTJ2H"},"agent_actions":{"view_html":"https://pith.science/pith/6K2DTJ2H4MY5ALZ6Z7SYUIEYZE","download_json":"https://pith.science/pith/6K2DTJ2H4MY5ALZ6Z7SYUIEYZE.json","view_paper":"https://pith.science/paper/6K2DTJ2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17896&json=true","fetch_graph":"https://pith.science/api/pith-number/6K2DTJ2H4MY5ALZ6Z7SYUIEYZE/graph.json","fetch_events":"https://pith.science/api/pith-number/6K2DTJ2H4MY5ALZ6Z7SYUIEYZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6K2DTJ2H4MY5ALZ6Z7SYUIEYZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6K2DTJ2H4MY5ALZ6Z7SYUIEYZE/action/storage_attestation","attest_author":"https://pith.science/pith/6K2DTJ2H4MY5ALZ6Z7SYUIEYZE/action/author_attestation","sign_citation":"https://pith.science/pith/6K2DTJ2H4MY5ALZ6Z7SYUIEYZE/action/citation_signature","submit_replication":"https://pith.science/pith/6K2DTJ2H4MY5ALZ6Z7SYUIEYZE/action/replication_record"}},"created_at":"2026-07-05T07:50:09.533766+00:00","updated_at":"2026-07-05T07:50:09.533766+00:00"}