{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NIVBTGOJBLBRR6NT4XDZC6IFGZ","short_pith_number":"pith:NIVBTGOJ","schema_version":"1.0","canonical_sha256":"6a2a1999c90ac318f9b3e5c7917905366d3017211a0a4e2147ea6356de94ddbf","source":{"kind":"arxiv","id":"1909.00599","version":1},"attestation_state":"computed","paper":{"title":"Subword Language Model for Query Auto-Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gyuwan Kim","submitted_at":"2019-09-02T08:40:41Z","abstract_excerpt":"Current neural query auto-completion (QAC) systems rely on character-level language models, but they slow down when queries are long. We present how to utilize subword language models for the fast and accurate generation of query completion candidates. Representing queries with subwords shorten a decoding length significantly. To deal with issues coming from introducing subword language model, we develop a retrace algorithm and a reranking method by approximate marginalization. As a result, our model achieves up to 2.5 times faster while maintaining a similar quality of generated results compa"},"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":"1909.00599","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-02T08:40:41Z","cross_cats_sorted":[],"title_canon_sha256":"d8677375c38566457ed68501df3f00dbbdbe625c9a64e2dfab4b0e9237e30ded","abstract_canon_sha256":"d16ce55d057d9d9b129758111c8cf693ce79f542d1d93cf81f79acbac7ee8451"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:10.137177Z","signature_b64":"NCHaaqSb8OYMVUTBSqVaWXOgVBzCilE2cHZSp+y0b25EQECPxKgUrVMawyt3SVmnnxDn1C+zbVoPzHSD/g9wCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a2a1999c90ac318f9b3e5c7917905366d3017211a0a4e2147ea6356de94ddbf","last_reissued_at":"2026-07-05T00:02:10.136784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:10.136784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Subword Language Model for Query Auto-Completion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gyuwan Kim","submitted_at":"2019-09-02T08:40:41Z","abstract_excerpt":"Current neural query auto-completion (QAC) systems rely on character-level language models, but they slow down when queries are long. We present how to utilize subword language models for the fast and accurate generation of query completion candidates. Representing queries with subwords shorten a decoding length significantly. To deal with issues coming from introducing subword language model, we develop a retrace algorithm and a reranking method by approximate marginalization. As a result, our model achieves up to 2.5 times faster while maintaining a similar quality of generated results compa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00599","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/1909.00599/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":"1909.00599","created_at":"2026-07-05T00:02:10.136839+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.00599v1","created_at":"2026-07-05T00:02:10.136839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00599","created_at":"2026-07-05T00:02:10.136839+00:00"},{"alias_kind":"pith_short_12","alias_value":"NIVBTGOJBLBR","created_at":"2026-07-05T00:02:10.136839+00:00"},{"alias_kind":"pith_short_16","alias_value":"NIVBTGOJBLBRR6NT","created_at":"2026-07-05T00:02:10.136839+00:00"},{"alias_kind":"pith_short_8","alias_value":"NIVBTGOJ","created_at":"2026-07-05T00:02:10.136839+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/NIVBTGOJBLBRR6NT4XDZC6IFGZ","json":"https://pith.science/pith/NIVBTGOJBLBRR6NT4XDZC6IFGZ.json","graph_json":"https://pith.science/api/pith-number/NIVBTGOJBLBRR6NT4XDZC6IFGZ/graph.json","events_json":"https://pith.science/api/pith-number/NIVBTGOJBLBRR6NT4XDZC6IFGZ/events.json","paper":"https://pith.science/paper/NIVBTGOJ"},"agent_actions":{"view_html":"https://pith.science/pith/NIVBTGOJBLBRR6NT4XDZC6IFGZ","download_json":"https://pith.science/pith/NIVBTGOJBLBRR6NT4XDZC6IFGZ.json","view_paper":"https://pith.science/paper/NIVBTGOJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.00599&json=true","fetch_graph":"https://pith.science/api/pith-number/NIVBTGOJBLBRR6NT4XDZC6IFGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/NIVBTGOJBLBRR6NT4XDZC6IFGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NIVBTGOJBLBRR6NT4XDZC6IFGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NIVBTGOJBLBRR6NT4XDZC6IFGZ/action/storage_attestation","attest_author":"https://pith.science/pith/NIVBTGOJBLBRR6NT4XDZC6IFGZ/action/author_attestation","sign_citation":"https://pith.science/pith/NIVBTGOJBLBRR6NT4XDZC6IFGZ/action/citation_signature","submit_replication":"https://pith.science/pith/NIVBTGOJBLBRR6NT4XDZC6IFGZ/action/replication_record"}},"created_at":"2026-07-05T00:02:10.136839+00:00","updated_at":"2026-07-05T00:02:10.136839+00:00"}