{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IX3Y6JVYSGRNZVIWTHPRVSFQIE","short_pith_number":"pith:IX3Y6JVY","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"},"canonical_sha256":"45f78f26b891a2dcd51699df1ac8b04104b83142041a9f4d1eb76375106d75e6","source":{"kind":"arxiv","id":"1808.09419","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09419","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09419v1","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09419","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"pith_short_12","alias_value":"IX3Y6JVYSGRN","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IX3Y6JVYSGRNZVIW","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IX3Y6JVY","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IX3Y6JVYSGRNZVIWTHPRVSFQIE","target":"record","payload":{"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"},"canonical_sha256":"45f78f26b891a2dcd51699df1ac8b04104b83142041a9f4d1eb76375106d75e6","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"},"source_kind":"arxiv","source_id":"1808.09419","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g6BwV/bKFU8wqrjFy0JqNCitQlkiEXStKdLiSS7xHNte2iEOUyzd8zIcHWDxBO8+AmfiO6N1yFV12tkxB+/ABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:54:36.528064Z"},"content_sha256":"3761063eef85758d05339ff71b56195360ad7ba29afbeae8eb0eae0ffe3c7214","schema_version":"1.0","event_id":"sha256:3761063eef85758d05339ff71b56195360ad7ba29afbeae8eb0eae0ffe3c7214"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IX3Y6JVYSGRNZVIWTHPRVSFQIE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XrMKJ2Bh5omXIn/PllSSO+CLokbgJVdMkkziKxGeTWy276sRzXcwUsIWdpBAaz8KboExgwtdK8cOkasSfcuNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:54:36.528531Z"},"content_sha256":"8d4d0c2bed7a3da8f7df040614d393397eeb7e4b52eded6e9c57f4f56c97dd65","schema_version":"1.0","event_id":"sha256:8d4d0c2bed7a3da8f7df040614d393397eeb7e4b52eded6e9c57f4f56c97dd65"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE/bundle.json","state_url":"https://pith.science/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T21:54:36Z","links":{"resolver":"https://pith.science/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE","bundle":"https://pith.science/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE/bundle.json","state":"https://pith.science/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IX3Y6JVYSGRNZVIWTHPRVSFQIE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IX3Y6JVYSGRNZVIWTHPRVSFQIE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cae4e4dd0b23fbc69e9feb2c3a7f1f37e9fce917501bca01f9dd4f06180b8a3f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T17:20:51Z","title_canon_sha256":"8a0f3bea7eda3b1900b6dfd47b0221fb175c373ba213f06c2051ebd628f57bb3"},"schema_version":"1.0","source":{"id":"1808.09419","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09419","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09419v1","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09419","created_at":"2026-05-18T00:07:01Z"},{"alias_kind":"pith_short_12","alias_value":"IX3Y6JVYSGRN","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IX3Y6JVYSGRNZVIW","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IX3Y6JVY","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:8d4d0c2bed7a3da8f7df040614d393397eeb7e4b52eded6e9c57f4f56c97dd65","target":"graph","created_at":"2026-05-18T00:07:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Dipanjan Das, Manaal Faruqui","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T17:20:51Z","title":"Identifying Well-formed Natural Language Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09419","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3761063eef85758d05339ff71b56195360ad7ba29afbeae8eb0eae0ffe3c7214","target":"record","created_at":"2026-05-18T00:07:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cae4e4dd0b23fbc69e9feb2c3a7f1f37e9fce917501bca01f9dd4f06180b8a3f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T17:20:51Z","title_canon_sha256":"8a0f3bea7eda3b1900b6dfd47b0221fb175c373ba213f06c2051ebd628f57bb3"},"schema_version":"1.0","source":{"id":"1808.09419","kind":"arxiv","version":1}},"canonical_sha256":"45f78f26b891a2dcd51699df1ac8b04104b83142041a9f4d1eb76375106d75e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45f78f26b891a2dcd51699df1ac8b04104b83142041a9f4d1eb76375106d75e6","first_computed_at":"2026-05-18T00:07:01.450909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:01.450909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FF+3vm2TrCCRXDT8296WVyViXiy59EMaylgTKMhmjcphXuW/Ehj0GsrsmvSMRm6JFGv8ZDBXjB7nj2/ZLz4WDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:01.451441Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.09419","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3761063eef85758d05339ff71b56195360ad7ba29afbeae8eb0eae0ffe3c7214","sha256:8d4d0c2bed7a3da8f7df040614d393397eeb7e4b52eded6e9c57f4f56c97dd65"],"state_sha256":"1d961846ed360afeb0393481c92ed06bcd7f6efd883be70730dd72fc49166e44"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GsUyVButxhihzKMpQDtsPQ5XuhlT1pWL1k/uTHaqBUHWmBfan3GbtMhXc5SUS0wHt0MoiGXNru8x8TBakZaXAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T21:54:36.531507Z","bundle_sha256":"55b9a303e5d74ca68f68bfbfb26665be6a505125b76de93b928c567abb1d1e86"}}