{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IVKMN6YHGKP2WWDHM25YIQJ3M4","short_pith_number":"pith:IVKMN6YH","schema_version":"1.0","canonical_sha256":"4554c6fb07329fab586766bb84413b670ecf74076fe4b796acdfdf900749c43d","source":{"kind":"arxiv","id":"2402.18479","version":2},"attestation_state":"computed","paper":{"title":"NewsQs: Multi-Source Question Generation for the Inquiring Mind","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alyssa Hwang, Kalpit Dixit, Kathleen McKeown, Markus Dreyer, Miguel Ballesteros, Mohit Bansal, Vittorio Castelli, Yassine Benajiba","submitted_at":"2024-02-28T16:59:35Z","abstract_excerpt":"We present NewsQs (news-cues), a dataset that provides question-answer pairs for multiple news documents. To create NewsQs, we augment a traditional multi-document summarization dataset with questions automatically generated by a T5-Large model fine-tuned on FAQ-style news articles from the News On the Web corpus. We show that fine-tuning a model with control codes produces questions that are judged acceptable more often than the same model without them as measured through human evaluation. We use a QNLI model with high correlation with human annotations to filter our data. We release our fina"},"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":"2402.18479","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T16:59:35Z","cross_cats_sorted":[],"title_canon_sha256":"61610141027fb7fc3aa3202f96d9bb7d61abcfa9a2dfbcc977c31066296c55ca","abstract_canon_sha256":"58e5459a0dbe34d704cedcb2aff33df667a0340237db9ea424d7d5d3ee628997"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:11.634014Z","signature_b64":"VgGGc/FFbx4LLpikc6gNGQ+F2X9fOik8MXKMVu/6tLty6sV/louHXJHtp4JuZefnWsN6Wl4Bt6yX4ropR/SsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4554c6fb07329fab586766bb84413b670ecf74076fe4b796acdfdf900749c43d","last_reissued_at":"2026-07-05T08:32:11.633411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:11.633411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NewsQs: Multi-Source Question Generation for the Inquiring Mind","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alyssa Hwang, Kalpit Dixit, Kathleen McKeown, Markus Dreyer, Miguel Ballesteros, Mohit Bansal, Vittorio Castelli, Yassine Benajiba","submitted_at":"2024-02-28T16:59:35Z","abstract_excerpt":"We present NewsQs (news-cues), a dataset that provides question-answer pairs for multiple news documents. To create NewsQs, we augment a traditional multi-document summarization dataset with questions automatically generated by a T5-Large model fine-tuned on FAQ-style news articles from the News On the Web corpus. We show that fine-tuning a model with control codes produces questions that are judged acceptable more often than the same model without them as measured through human evaluation. We use a QNLI model with high correlation with human annotations to filter our data. We release our fina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18479","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/2402.18479/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":"2402.18479","created_at":"2026-07-05T08:32:11.633475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.18479v2","created_at":"2026-07-05T08:32:11.633475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18479","created_at":"2026-07-05T08:32:11.633475+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVKMN6YHGKP2","created_at":"2026-07-05T08:32:11.633475+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVKMN6YHGKP2WWDH","created_at":"2026-07-05T08:32:11.633475+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVKMN6YH","created_at":"2026-07-05T08:32:11.633475+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/IVKMN6YHGKP2WWDHM25YIQJ3M4","json":"https://pith.science/pith/IVKMN6YHGKP2WWDHM25YIQJ3M4.json","graph_json":"https://pith.science/api/pith-number/IVKMN6YHGKP2WWDHM25YIQJ3M4/graph.json","events_json":"https://pith.science/api/pith-number/IVKMN6YHGKP2WWDHM25YIQJ3M4/events.json","paper":"https://pith.science/paper/IVKMN6YH"},"agent_actions":{"view_html":"https://pith.science/pith/IVKMN6YHGKP2WWDHM25YIQJ3M4","download_json":"https://pith.science/pith/IVKMN6YHGKP2WWDHM25YIQJ3M4.json","view_paper":"https://pith.science/paper/IVKMN6YH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.18479&json=true","fetch_graph":"https://pith.science/api/pith-number/IVKMN6YHGKP2WWDHM25YIQJ3M4/graph.json","fetch_events":"https://pith.science/api/pith-number/IVKMN6YHGKP2WWDHM25YIQJ3M4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVKMN6YHGKP2WWDHM25YIQJ3M4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVKMN6YHGKP2WWDHM25YIQJ3M4/action/storage_attestation","attest_author":"https://pith.science/pith/IVKMN6YHGKP2WWDHM25YIQJ3M4/action/author_attestation","sign_citation":"https://pith.science/pith/IVKMN6YHGKP2WWDHM25YIQJ3M4/action/citation_signature","submit_replication":"https://pith.science/pith/IVKMN6YHGKP2WWDHM25YIQJ3M4/action/replication_record"}},"created_at":"2026-07-05T08:32:11.633475+00:00","updated_at":"2026-07-05T08:32:11.633475+00:00"}