{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:6AYQL7GPK53UOJG44P4JOAEH4X","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":"aab77e2d42b30ca5519979a32ff7f90487fe7e727b45fefa440feeec411de6ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-27T08:50:17Z","title_canon_sha256":"53a538c63e761741689bc54af71fddd3f514ca77502874d1ba18aa7479f59a04"},"schema_version":"1.0","source":{"id":"1908.10084","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.10084","created_at":"2026-07-04T23:59:53Z"},{"alias_kind":"arxiv_version","alias_value":"1908.10084v1","created_at":"2026-07-04T23:59:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10084","created_at":"2026-07-04T23:59:53Z"},{"alias_kind":"pith_short_12","alias_value":"6AYQL7GPK53U","created_at":"2026-07-04T23:59:53Z"},{"alias_kind":"pith_short_16","alias_value":"6AYQL7GPK53UOJG4","created_at":"2026-07-04T23:59:53Z"},{"alias_kind":"pith_short_8","alias_value":"6AYQL7GP","created_at":"2026-07-04T23:59:53Z"}],"graph_snapshots":[{"event_id":"sha256:6dafa43224d994090721f30334324cd728d35255b4bf901e5f6a38e04694e371","target":"graph","created_at":"2026-07-04T23:59:53Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","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."}],"snapshot_sha256":"eab657b24b93e83c3e3307fb58ddc9c0febd889486866a1e63f45cb764981d20"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b57db49ec398ecfe15cc90a5ac76220a8c8f98935943645c847ddd6a1e4581db"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.10084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Iryna Gurevych, Nils Reimers","cross_cats":[],"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.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-27T08:50:17Z","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks"},"references":{"count":38,"internal_anchors":5,"resolved_work":38,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"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","year":2015},{"cited_arxiv_id":"","doi":"10.3115/v1/s14-2010","is_internal_anchor":false,"ref_index":2,"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","year":2014},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"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","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"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","year":2013},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"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","year":2012}],"snapshot_sha256":"04424c6fbd6ae4d1d05787feaf8b6b0e5267a9420979d64eb26d1177dde4a201"},"source":{"id":"1908.10084","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-10T14:47:49.156617Z","id":"282d487d-d305-4302-9665-5b865e4d22e6","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"282d487d-d305-4302-9665-5b865e4d22e6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b3b771d5366b115629a5a07022e3c88cff172b367bb9749c94107da645ab6e11","target":"record","created_at":"2026-07-04T23:59:53Z","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":"aab77e2d42b30ca5519979a32ff7f90487fe7e727b45fefa440feeec411de6ed","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-27T08:50:17Z","title_canon_sha256":"53a538c63e761741689bc54af71fddd3f514ca77502874d1ba18aa7479f59a04"},"schema_version":"1.0","source":{"id":"1908.10084","kind":"arxiv","version":1}},"canonical_sha256":"f03105fccf57774724dce3f8970087e5f2bb4b017ebb448e1d078a171acb956c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f03105fccf57774724dce3f8970087e5f2bb4b017ebb448e1d078a171acb956c","first_computed_at":"2026-07-04T23:59:53.701495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:59:53.701495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A+Kbn8CcSlZhxkzYd8nUSH5BECkWj4Nhzg2QwAb6gdCnWnhwDWGG19CgJHE0rf2x1QGg87nzF6mpCPR0Nf0/Cw==","signature_status":"signed_v1","signed_at":"2026-07-04T23:59:53.701857Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.10084","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3b771d5366b115629a5a07022e3c88cff172b367bb9749c94107da645ab6e11","sha256:6dafa43224d994090721f30334324cd728d35255b4bf901e5f6a38e04694e371"],"state_sha256":"15daa65bd0b6800c4c6f3f5deb03703dfc8c9f0aa0c3b786b5391caa6d63ebba"}