{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:P2EICT7TBLIAUZXOMUKUBTJFF7","short_pith_number":"pith:P2EICT7T","schema_version":"1.0","canonical_sha256":"7e88814ff30ad00a66ee651540cd252ff8430d2432c90b9ff6ad896ddfe2aa9f","source":{"kind":"arxiv","id":"1803.11175","version":2},"attestation_state":"computed","paper":{"title":"Universal Sentence Encoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brian Strope, Chris Tar, Daniel Cer, Mario Guajardo-Cespedes, Nan Hua, Nicole Limtiaco, Noah Constant, Ray Kurzweil, Rhomni St. John, Sheng-yi Kong, Steve Yuan, Yinfei Yang, Yun-hsuan Sung","submitted_at":"2018-03-29T17:43:03Z","abstract_excerpt":"We present models for encoding sentences into embedding vectors that specifically target transfer learning to other NLP tasks. The models are efficient and result in accurate performance on diverse transfer tasks. Two variants of the encoding models allow for trade-offs between accuracy and compute resources. For both variants, we investigate and report the relationship between model complexity, resource consumption, the availability of transfer task training data, and task performance. Comparisons are made with baselines that use word level transfer learning via pretrained word embeddings as "},"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":"1803.11175","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-29T17:43:03Z","cross_cats_sorted":[],"title_canon_sha256":"c71d10236d9d952f198a20d6b73c01e4aae20ef9ce98209241e2ba6a5ccb6159","abstract_canon_sha256":"a423fe6103d4850b4703ce25c75ec072de04fa4936b6ecfafa7108dc1f1ceac5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:37.005804Z","signature_b64":"/Mat6DPdVKOReZQuK5txdoU+pClL5dtJr3l6C4aWIlXvP9WN8cbWNP/AIn8J04kO+Uo6ISc+8QPlWWsE43xEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e88814ff30ad00a66ee651540cd252ff8430d2432c90b9ff6ad896ddfe2aa9f","last_reissued_at":"2026-05-18T00:18:37.005238Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:37.005238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Sentence Encoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brian Strope, Chris Tar, Daniel Cer, Mario Guajardo-Cespedes, Nan Hua, Nicole Limtiaco, Noah Constant, Ray Kurzweil, Rhomni St. John, Sheng-yi Kong, Steve Yuan, Yinfei Yang, Yun-hsuan Sung","submitted_at":"2018-03-29T17:43:03Z","abstract_excerpt":"We present models for encoding sentences into embedding vectors that specifically target transfer learning to other NLP tasks. The models are efficient and result in accurate performance on diverse transfer tasks. Two variants of the encoding models allow for trade-offs between accuracy and compute resources. For both variants, we investigate and report the relationship between model complexity, resource consumption, the availability of transfer task training data, and task performance. Comparisons are made with baselines that use word level transfer learning via pretrained word embeddings as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.11175","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":""},"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":"1803.11175","created_at":"2026-05-18T00:18:37.005329+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.11175v2","created_at":"2026-05-18T00:18:37.005329+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.11175","created_at":"2026-05-18T00:18:37.005329+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2EICT7TBLIA","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2EICT7TBLIAUZXO","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2EICT7T","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":11,"sample":[{"citing_arxiv_id":"1906.08340","citing_title":"Learning Compressed Sentence Representations for On-Device Text Processing","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02581","citing_title":"Transfer Learning for Risk Classification of Social Media Posts: Model Evaluation Study","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07366","citing_title":"Leveraging Linguistic Characteristics for Bipolar Disorder Recognition with Gender Differences","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"1907.10710","citing_title":"Generic Intent Representation in Web Search","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2104.05565","citing_title":"Survey on reinforcement learning for language processing","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2304.10726","citing_title":"Usenix'23 Extended Version: Smart Learning to Find Dumb Contracts","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2504.18902","citing_title":"Transformer-Empowered Actor-Critic Reinforcement Learning for Sequence-Aware Service Function Chain Partitioning","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2508.20086","citing_title":"Detecting Malicious Intents in Smart Contracts with Pre-trained Programming Language Models","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2507.01925","citing_title":"A Survey on Vision-Language-Action Models: An Action Tokenization Perspective","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2311.01378","citing_title":"Vision-Language Foundation Models as Effective Robot Imitators","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12813","citing_title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","ref_index":148,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27641","citing_title":"Semantics-Aware Hierarchical Token Communication: Clustering, Bit Mapping, and Power Allocation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10430","citing_title":"Real vs. Semi-Simulated: Rethinking Evaluation for Treatment Effect Estimation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10606","citing_title":"Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10021","citing_title":"Enhancing Healthcare Search Intent Recognition with Query Representation Learning and Session Context","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04295","citing_title":"LLMs Uncertainty Quantification via Adaptive Conformal Semantic Entropy","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00618","citing_title":"Is Textual Similarity Invariant under Machine Translation? Evidence Based on the Political Manifesto Corpus","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07553","citing_title":"TR-EduVSum: A Turkish-Focused Dataset and Consensus Framework for Educational Video Summarization","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2204.01691","citing_title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"1908.10084","citing_title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16770","citing_title":"Exploring Ethical Concerns of Mobile Applications from App Reviews: A Literature Survey","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17257","citing_title":"REZE: Representation Regularization for Domain-adaptive Text Embedding Pre-finetuning","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2EICT7TBLIAUZXOMUKUBTJFF7","json":"https://pith.science/pith/P2EICT7TBLIAUZXOMUKUBTJFF7.json","graph_json":"https://pith.science/api/pith-number/P2EICT7TBLIAUZXOMUKUBTJFF7/graph.json","events_json":"https://pith.science/api/pith-number/P2EICT7TBLIAUZXOMUKUBTJFF7/events.json","paper":"https://pith.science/paper/P2EICT7T"},"agent_actions":{"view_html":"https://pith.science/pith/P2EICT7TBLIAUZXOMUKUBTJFF7","download_json":"https://pith.science/pith/P2EICT7TBLIAUZXOMUKUBTJFF7.json","view_paper":"https://pith.science/paper/P2EICT7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.11175&json=true","fetch_graph":"https://pith.science/api/pith-number/P2EICT7TBLIAUZXOMUKUBTJFF7/graph.json","fetch_events":"https://pith.science/api/pith-number/P2EICT7TBLIAUZXOMUKUBTJFF7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2EICT7TBLIAUZXOMUKUBTJFF7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2EICT7TBLIAUZXOMUKUBTJFF7/action/storage_attestation","attest_author":"https://pith.science/pith/P2EICT7TBLIAUZXOMUKUBTJFF7/action/author_attestation","sign_citation":"https://pith.science/pith/P2EICT7TBLIAUZXOMUKUBTJFF7/action/citation_signature","submit_replication":"https://pith.science/pith/P2EICT7TBLIAUZXOMUKUBTJFF7/action/replication_record"}},"created_at":"2026-05-18T00:18:37.005329+00:00","updated_at":"2026-05-18T00:18:37.005329+00:00"}