{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6AYQL7GPK53UOJG44P4JOAEH4X","short_pith_number":"pith:6AYQL7GP","schema_version":"1.0","canonical_sha256":"f03105fccf57774724dce3f8970087e5f2bb4b017ebb448e1d078a171acb956c","source":{"kind":"arxiv","id":"1908.10084","version":1},"attestation_state":"computed","paper":{"title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Sentence-BERT uses siamese and triplet training on BERT to create fixed sentence embeddings that support fast cosine-similarity comparisons while matching original accuracy.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Nils Reimers","submitted_at":"2019-08-27T08:50:17Z","abstract_excerpt":"BERT (Devlin et al., 2018) and RoBERTa (Liu et al., 2019) has set a new state-of-the-art performance on sentence-pair regression tasks like semantic textual similarity (STS). However, it requires that both sentences are fed into the network, which causes a massive computational overhead: Finding the most similar pair in a collection of 10,000 sentences requires about 50 million inference computations (~65 hours) with BERT. The construction of BERT makes it unsuitable for semantic similarity search as well as for unsupervised tasks like clustering.\n  In this publication, we present Sentence-BER"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"1908.10084","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-27T08:50:17Z","cross_cats_sorted":[],"title_canon_sha256":"53a538c63e761741689bc54af71fddd3f514ca77502874d1ba18aa7479f59a04","abstract_canon_sha256":"aab77e2d42b30ca5519979a32ff7f90487fe7e727b45fefa440feeec411de6ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:53.701857Z","signature_b64":"A+Kbn8CcSlZhxkzYd8nUSH5BECkWj4Nhzg2QwAb6gdCnWnhwDWGG19CgJHE0rf2x1QGg87nzF6mpCPR0Nf0/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f03105fccf57774724dce3f8970087e5f2bb4b017ebb448e1d078a171acb956c","last_reissued_at":"2026-07-04T23:59:53.701495Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:53.701495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Sentence-BERT uses siamese and triplet training on BERT to create fixed sentence embeddings that support fast cosine-similarity comparisons while matching original accuracy.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iryna Gurevych, Nils Reimers","submitted_at":"2019-08-27T08:50:17Z","abstract_excerpt":"BERT (Devlin et al., 2018) and RoBERTa (Liu et al., 2019) has set a new state-of-the-art performance on sentence-pair regression tasks like semantic textual similarity (STS). However, it requires that both sentences are fed into the network, which causes a massive computational overhead: Finding the most similar pair in a collection of 10,000 sentences requires about 50 million inference computations (~65 hours) with BERT. The construction of BERT makes it unsuitable for semantic similarity search as well as for unsupervised tasks like clustering.\n  In this publication, we present Sentence-BER"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we present Sentence-BERT (SBERT), a modification of the pretrained BERT network that use siamese and triplet network structures to derive semantically meaningful sentence embeddings that can be compared using cosine-similarity. This reduces the effort for finding the most similar pair from 65 hours with BERT / RoBERTa to about 5 seconds with SBERT, while maintaining the accuracy from BERT.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That fine-tuning BERT with siamese and triplet networks produces standalone sentence embeddings whose cosine similarities accurately reflect semantic similarity at the level of the original pairwise BERT inference.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Sentence-BERT adapts BERT with siamese and triplet networks to produce sentence embeddings for efficient cosine-similarity comparisons, cutting computation time from hours to seconds on similarity search while matching BERT accuracy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Sentence-BERT uses siamese and triplet training on BERT to create fixed sentence embeddings that support fast cosine-similarity comparisons while matching original accuracy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"eab657b24b93e83c3e3307fb58ddc9c0febd889486866a1e63f45cb764981d20"},"source":{"id":"1908.10084","kind":"arxiv","version":1},"verdict":{"id":"282d487d-d305-4302-9665-5b865e4d22e6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T14:47:49.156617Z","strongest_claim":"we present Sentence-BERT (SBERT), a modification of the pretrained BERT network that use siamese and triplet network structures to derive semantically meaningful sentence embeddings that can be compared using cosine-similarity. This reduces the effort for finding the most similar pair from 65 hours with BERT / RoBERTa to about 5 seconds with SBERT, while maintaining the accuracy from BERT.","one_line_summary":"Sentence-BERT adapts BERT with siamese and triplet networks to produce sentence embeddings for efficient cosine-similarity comparisons, cutting computation time from hours to seconds on similarity search while matching BERT accuracy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That fine-tuning BERT with siamese and triplet networks produces standalone sentence embeddings whose cosine similarities accurately reflect semantic similarity at the level of the original pairwise BERT inference.","pith_extraction_headline":"Sentence-BERT uses siamese and triplet training on BERT to create fixed sentence embeddings that support fast cosine-similarity comparisons while matching original accuracy."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.10084/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":38,"sample":[{"doi":"","year":2015,"title":"Eneko Agirre, Carmen Banea, Claire Cardie, Daniel Cer, Mona Diab, Aitor Gonzalez-Agirre, Weiwei Guo, Inigo Lopez-Gazpio, Montse Maritxalar, Rada Mihalcea, German Rigau, Larraitz Uria, and Janyce Wiebe","work_id":"045e6092-8c74-4f10-a95a-5f99899e9866","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.3115/v1/s14-2010","year":2014,"title":"Eneko Agirre, Carmen Banea, Claire Cardie, Daniel Cer, Mona Diab, Aitor Gonzalez-Agirre, Weiwei Guo, Rada Mihalcea, German Rigau, and Janyce Wiebe. 2014. https://doi.org/10.3115/v1/S14-2010 S em E val","work_id":"9644ab35-855a-4f87-97a6-b7db05cb97f9","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Eneko Agirre, Carmen Banea, Daniel M. Cer, Mona T. Diab, Aitor Gonzalez - Agirre, Rada Mihalcea, German Rigau, and Janyce Wiebe. 2016. http://aclweb.org/anthology/S/S16/S16-1081.pdf SemEval-2016 Task ","work_id":"b53a638c-aa98-4acd-b768-2150a7c9b7ed","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2013,"title":"Eneko Agirre, Daniel Cer, Mona Diab, Aitor Gonzalez-Agirre, and Weiwei Guo. 2013. https://www.aclweb.org/anthology/S13-1004 * SEM 2013 shared task: Semantic Textual Similarity . In Second Joint Confer","work_id":"73f9adc0-1e66-417a-94b8-b2554aa4e341","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2012,"title":"Eneko Agirre, Mona Diab, Daniel Cer, and Aitor Gonzalez-Agirre. 2012. http://dl.acm.org/citation.cfm?id=2387636.2387697 SemEval-2012 Task 6: A Pilot on Semantic Textual Similarity . In Proceedings of ","work_id":"b69745b4-4076-4c10-b7a6-fce20eb44197","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":38,"snapshot_sha256":"04424c6fbd6ae4d1d05787feaf8b6b0e5267a9420979d64eb26d1177dde4a201","internal_anchors":5},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b57db49ec398ecfe15cc90a5ac76220a8c8f98935943645c847ddd6a1e4581db"},"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":"1908.10084","created_at":"2026-07-04T23:59:53.701558+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.10084v1","created_at":"2026-07-04T23:59:53.701558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10084","created_at":"2026-07-04T23:59:53.701558+00:00"},{"alias_kind":"pith_short_12","alias_value":"6AYQL7GPK53U","created_at":"2026-07-04T23:59:53.701558+00:00"},{"alias_kind":"pith_short_16","alias_value":"6AYQL7GPK53UOJG4","created_at":"2026-07-04T23:59:53.701558+00:00"},{"alias_kind":"pith_short_8","alias_value":"6AYQL7GP","created_at":"2026-07-04T23:59:53.701558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":284,"internal_anchor_count":284,"sample":[{"citing_arxiv_id":"2606.07521","citing_title":"Evaluating Hallucinations in Domain-Adapted Large Language Models","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25391","citing_title":"From Sounds to Scenes: A Benchmark for Evaluating Context-Aware Auditory Scene Understanding in Large Audio Language Models","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25379","citing_title":"Story Operators: Decomposing the Original $\\to$ Sequel Transformation in Embedding Space","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27106","citing_title":"Application of LLMs to Threat Assessment of Foreign Peacekeeping Missions","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26641","citing_title":"Invisible Impact of Empathy on Behavioral Change: Isolating the Effect of Empathy in Long-term Physical Activity Coaching Chatbot Interactions","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27036","citing_title":"RelAfford6D: Relational 6D Affordance Graphs for Constraint-Driven Robotic Manipulation","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26753","citing_title":"ConvMemory v3: A Validity Context Layer for Conversational Memory via Target-Conditioned Relation Verification","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23919","citing_title":"Unified Multi-Task Relevance Modeling for E-Commerce: Comparing Task Routing Architectures Across LLMs and Cross-Encoders","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23911","citing_title":"Scaling Dense Retrieval with LLM-Annotated Training Data: Structured Mining and Progressive Curriculum for E-Commerce Sponsored Search","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22778","citing_title":"HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions","ref_index":114,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22370","citing_title":"Towards Error-Free Long Video Generation","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22158","citing_title":"Improving Reasoning in Vision-Language Models via Perception Verified Self-Training","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24910","citing_title":"End-to-End Voice Intent Recognition for Spontaneous Human-Drone Interaction with Naive Users","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21622","citing_title":"Evaluating Document-Tuned Transformer Representations for Person-level Mental Health Assessment","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20846","citing_title":"Adverse Online Social Interactions: A Multi-Level Evolutionary Analysis of Local Patterns, Diffusion, and Community Disruption","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21252","citing_title":"A Neurosymbolic Framework for Interpretable Skeleton-Based Seizure Detection via Concept-Driven Logical Reasoning","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20553","citing_title":"From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18667","citing_title":"Can neurons speak? Semantic narration of vision at single-cell resolution","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01241","citing_title":"Mapping Text to Multiplex Graph: Prompt Compression as L\\'evy Walk-Guided Graph Pruning","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18560","citing_title":"Constraining to Generalize: Subspace Tuning for Few-shot Generalization of Audio-Language Models","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17965","citing_title":"BLAgent: Agentic RAG for File-Level Bug Localization","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2606.17628","citing_title":"OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18098","citing_title":"IsabeLLM: Automated Theorem Proving Applied to Formally Verifying Consensus","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2607.01485","citing_title":"CoPersona: Collaborative Persona Graphs for Robust LLM Personalization","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12793","citing_title":"Semantic Identification of IoT Devices from Behavioral Primitives","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6AYQL7GPK53UOJG44P4JOAEH4X","json":"https://pith.science/pith/6AYQL7GPK53UOJG44P4JOAEH4X.json","graph_json":"https://pith.science/api/pith-number/6AYQL7GPK53UOJG44P4JOAEH4X/graph.json","events_json":"https://pith.science/api/pith-number/6AYQL7GPK53UOJG44P4JOAEH4X/events.json","paper":"https://pith.science/paper/6AYQL7GP"},"agent_actions":{"view_html":"https://pith.science/pith/6AYQL7GPK53UOJG44P4JOAEH4X","download_json":"https://pith.science/pith/6AYQL7GPK53UOJG44P4JOAEH4X.json","view_paper":"https://pith.science/paper/6AYQL7GP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.10084&json=true","fetch_graph":"https://pith.science/api/pith-number/6AYQL7GPK53UOJG44P4JOAEH4X/graph.json","fetch_events":"https://pith.science/api/pith-number/6AYQL7GPK53UOJG44P4JOAEH4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6AYQL7GPK53UOJG44P4JOAEH4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6AYQL7GPK53UOJG44P4JOAEH4X/action/storage_attestation","attest_author":"https://pith.science/pith/6AYQL7GPK53UOJG44P4JOAEH4X/action/author_attestation","sign_citation":"https://pith.science/pith/6AYQL7GPK53UOJG44P4JOAEH4X/action/citation_signature","submit_replication":"https://pith.science/pith/6AYQL7GPK53UOJG44P4JOAEH4X/action/replication_record"}},"created_at":"2026-07-04T23:59:53.701558+00:00","updated_at":"2026-07-04T23:59:53.701558+00:00"}