{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IX3Y6JVYSGRNZVIWTHPRVSFQIE","short_pith_number":"pith:IX3Y6JVY","schema_version":"1.0","canonical_sha256":"45f78f26b891a2dcd51699df1ac8b04104b83142041a9f4d1eb76375106d75e6","source":{"kind":"arxiv","id":"1808.09419","version":1},"attestation_state":"computed","paper":{"title":"Identifying Well-formed Natural Language Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dipanjan Das, Manaal Faruqui","submitted_at":"2018-08-28T17:20:51Z","abstract_excerpt":"Understanding search queries is a hard problem as it involves dealing with \"word salad\" text ubiquitously issued by users. However, if a query resembles a well-formed question, a natural language processing pipeline is able to perform more accurate interpretation, thus reducing downstream compounding errors. Hence, identifying whether or not a query is well formed can enhance query understanding. Here, we introduce a new task of identifying a well-formed natural language question. We construct and release a dataset of 25,100 publicly available questions classified into well-formed and non-well"},"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":"1808.09419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T17:20:51Z","cross_cats_sorted":[],"title_canon_sha256":"8a0f3bea7eda3b1900b6dfd47b0221fb175c373ba213f06c2051ebd628f57bb3","abstract_canon_sha256":"cae4e4dd0b23fbc69e9feb2c3a7f1f37e9fce917501bca01f9dd4f06180b8a3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:01.451441Z","signature_b64":"FF+3vm2TrCCRXDT8296WVyViXiy59EMaylgTKMhmjcphXuW/Ehj0GsrsmvSMRm6JFGv8ZDBXjB7nj2/ZLz4WDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45f78f26b891a2dcd51699df1ac8b04104b83142041a9f4d1eb76375106d75e6","last_reissued_at":"2026-05-18T00:07:01.450909Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:01.450909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Identifying Well-formed Natural Language Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dipanjan Das, Manaal Faruqui","submitted_at":"2018-08-28T17:20:51Z","abstract_excerpt":"Understanding search queries is a hard problem as it involves dealing with \"word salad\" text ubiquitously issued by users. However, if a query resembles a well-formed question, a natural language processing pipeline is able to perform more accurate interpretation, thus reducing downstream compounding errors. Hence, identifying whether or not a query is well formed can enhance query understanding. Here, we introduce a new task of identifying a well-formed natural language question. We construct and release a dataset of 25,100 publicly available questions classified into well-formed and non-well"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09419","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":""},"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":"1808.09419","created_at":"2026-05-18T00:07:01.450997+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.09419v1","created_at":"2026-05-18T00:07:01.450997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09419","created_at":"2026-05-18T00:07:01.450997+00:00"},{"alias_kind":"pith_short_12","alias_value":"IX3Y6JVYSGRN","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IX3Y6JVYSGRNZVIW","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IX3Y6JVY","created_at":"2026-05-18T12:32:31.084164+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.17847","citing_title":"Bridging the Data Provenance Gap Across Text, Speech and Video","ref_index":250,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE","json":"https://pith.science/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE.json","graph_json":"https://pith.science/api/pith-number/IX3Y6JVYSGRNZVIWTHPRVSFQIE/graph.json","events_json":"https://pith.science/api/pith-number/IX3Y6JVYSGRNZVIWTHPRVSFQIE/events.json","paper":"https://pith.science/paper/IX3Y6JVY"},"agent_actions":{"view_html":"https://pith.science/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE","download_json":"https://pith.science/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE.json","view_paper":"https://pith.science/paper/IX3Y6JVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.09419&json=true","fetch_graph":"https://pith.science/api/pith-number/IX3Y6JVYSGRNZVIWTHPRVSFQIE/graph.json","fetch_events":"https://pith.science/api/pith-number/IX3Y6JVYSGRNZVIWTHPRVSFQIE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE/action/storage_attestation","attest_author":"https://pith.science/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE/action/author_attestation","sign_citation":"https://pith.science/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE/action/citation_signature","submit_replication":"https://pith.science/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE/action/replication_record"}},"created_at":"2026-05-18T00:07:01.450997+00:00","updated_at":"2026-05-18T00:07:01.450997+00:00"}