{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QT26B7RWF22FCX4W7DBXDNQ2C5","short_pith_number":"pith:QT26B7RW","schema_version":"1.0","canonical_sha256":"84f5e0fe362eb4515f96f8c371b61a1758459746804f0d6fe9758486c350039c","source":{"kind":"arxiv","id":"1705.00652","version":1},"attestation_state":"computed","paper":{"title":"Efficient Natural Language Response Suggestion for Smart Reply","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Balint Miklos, Brian Strope, Laszlo Lukacs, Matthew Henderson, Rami Al-Rfou, Ray Kurzweil, Ruiqi Guo, Sanjiv Kumar, Yun-hsuan Sung","submitted_at":"2017-05-01T18:24:15Z","abstract_excerpt":"This paper presents a computationally efficient machine-learned method for natural language response suggestion. Feed-forward neural networks using n-gram embedding features encode messages into vectors which are optimized to give message-response pairs a high dot-product value. An optimized search finds response suggestions. The method is evaluated in a large-scale commercial e-mail application, Inbox by Gmail. Compared to a sequence-to-sequence approach, the new system achieves the same quality at a small fraction of the computational requirements and latency."},"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":"1705.00652","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-01T18:24:15Z","cross_cats_sorted":[],"title_canon_sha256":"2a11f2810a77db9b388980337c8de96e0041ee0ec940e7517c716b4658205bae","abstract_canon_sha256":"117a96e9af604b36a0590d52456948f621f2ecaa32363342d5d659cf6652f11a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:10.229967Z","signature_b64":"pnMBZXeZvTlnKK51MzlPae95HXM3nNI3mMuDMmKje7DqZ1Jd2LsbwVmSVcVaO+qD9a5fYw/oVA7maZ55xqhnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84f5e0fe362eb4515f96f8c371b61a1758459746804f0d6fe9758486c350039c","last_reissued_at":"2026-05-18T00:45:10.229407Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:10.229407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Natural Language Response Suggestion for Smart Reply","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Balint Miklos, Brian Strope, Laszlo Lukacs, Matthew Henderson, Rami Al-Rfou, Ray Kurzweil, Ruiqi Guo, Sanjiv Kumar, Yun-hsuan Sung","submitted_at":"2017-05-01T18:24:15Z","abstract_excerpt":"This paper presents a computationally efficient machine-learned method for natural language response suggestion. Feed-forward neural networks using n-gram embedding features encode messages into vectors which are optimized to give message-response pairs a high dot-product value. An optimized search finds response suggestions. The method is evaluated in a large-scale commercial e-mail application, Inbox by Gmail. Compared to a sequence-to-sequence approach, the new system achieves the same quality at a small fraction of the computational requirements and latency."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.00652","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":"1705.00652","created_at":"2026-05-18T00:45:10.229497+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.00652v1","created_at":"2026-05-18T00:45:10.229497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.00652","created_at":"2026-05-18T00:45:10.229497+00:00"},{"alias_kind":"pith_short_12","alias_value":"QT26B7RWF22F","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QT26B7RWF22FCX4W","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QT26B7RW","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2301.12652","citing_title":"REPLUG: Retrieval-Augmented Black-Box Language Models","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2004.04906","citing_title":"Dense Passage Retrieval for Open-Domain Question Answering","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2104.08821","citing_title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03127","citing_title":"Domain-Adapted Retrieval for In-Context Annotation of Pedagogical Dialogue Acts","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20666","citing_title":"ORPHEAS: A Cross-Lingual Greek-English Embedding Model for Retrieval-Augmented Generation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07930","citing_title":"Unified Supervision for Walmart's Sponsored Search Retrieval via Joint Semantic Relevance and Behavioral Engagement Modeling","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06830","citing_title":"ProtSent: Protein Sentence Transformers","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QT26B7RWF22FCX4W7DBXDNQ2C5","json":"https://pith.science/pith/QT26B7RWF22FCX4W7DBXDNQ2C5.json","graph_json":"https://pith.science/api/pith-number/QT26B7RWF22FCX4W7DBXDNQ2C5/graph.json","events_json":"https://pith.science/api/pith-number/QT26B7RWF22FCX4W7DBXDNQ2C5/events.json","paper":"https://pith.science/paper/QT26B7RW"},"agent_actions":{"view_html":"https://pith.science/pith/QT26B7RWF22FCX4W7DBXDNQ2C5","download_json":"https://pith.science/pith/QT26B7RWF22FCX4W7DBXDNQ2C5.json","view_paper":"https://pith.science/paper/QT26B7RW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.00652&json=true","fetch_graph":"https://pith.science/api/pith-number/QT26B7RWF22FCX4W7DBXDNQ2C5/graph.json","fetch_events":"https://pith.science/api/pith-number/QT26B7RWF22FCX4W7DBXDNQ2C5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QT26B7RWF22FCX4W7DBXDNQ2C5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QT26B7RWF22FCX4W7DBXDNQ2C5/action/storage_attestation","attest_author":"https://pith.science/pith/QT26B7RWF22FCX4W7DBXDNQ2C5/action/author_attestation","sign_citation":"https://pith.science/pith/QT26B7RWF22FCX4W7DBXDNQ2C5/action/citation_signature","submit_replication":"https://pith.science/pith/QT26B7RWF22FCX4W7DBXDNQ2C5/action/replication_record"}},"created_at":"2026-05-18T00:45:10.229497+00:00","updated_at":"2026-05-18T00:45:10.229497+00:00"}