{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VZCXKKXNHEMEJUCPVGJBU4TD4E","short_pith_number":"pith:VZCXKKXN","schema_version":"1.0","canonical_sha256":"ae45752aed391844d04fa9921a7263e1331de23b9914f96fbf8fe5d1a9280632","source":{"kind":"arxiv","id":"2101.10642","version":1},"attestation_state":"computed","paper":{"title":"Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hyunjin Choi, Judong Kim, Seongho Joe, Youngjune Gwon","submitted_at":"2021-01-26T09:14:06Z","abstract_excerpt":"Contextualized representations from a pre-trained language model are central to achieve a high performance on downstream NLP task. The pre-trained BERT and A Lite BERT (ALBERT) models can be fine-tuned to give state-ofthe-art results in sentence-pair regressions such as semantic textual similarity (STS) and natural language inference (NLI). Although BERT-based models yield the [CLS] token vector as a reasonable sentence embedding, the search for an optimal sentence embedding scheme remains an active research area in computational linguistics. This paper explores on sentence embedding models fo"},"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":"2101.10642","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-01-26T09:14:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"66ebfb68bea2fab6993c7e0b4fa787a5292809961ccb75eacae735287bde0c23","abstract_canon_sha256":"6594b020d315b101042bbcc8f31b407c5aa2448e5e28a57b33fb840539d640b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:00.747343Z","signature_b64":"TcfNkBbGP7NQ0haBlsiy2BpH8JcISM8YTu+tYu1m59/k0hbx9CXGLGn/637c5QWr4cvyPX4k2Fmwlc5JVSqBDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae45752aed391844d04fa9921a7263e1331de23b9914f96fbf8fe5d1a9280632","last_reissued_at":"2026-07-05T02:10:00.746959Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:00.746959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hyunjin Choi, Judong Kim, Seongho Joe, Youngjune Gwon","submitted_at":"2021-01-26T09:14:06Z","abstract_excerpt":"Contextualized representations from a pre-trained language model are central to achieve a high performance on downstream NLP task. The pre-trained BERT and A Lite BERT (ALBERT) models can be fine-tuned to give state-ofthe-art results in sentence-pair regressions such as semantic textual similarity (STS) and natural language inference (NLI). Although BERT-based models yield the [CLS] token vector as a reasonable sentence embedding, the search for an optimal sentence embedding scheme remains an active research area in computational linguistics. This paper explores on sentence embedding models fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.10642","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/2101.10642/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":"2101.10642","created_at":"2026-07-05T02:10:00.747014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.10642v1","created_at":"2026-07-05T02:10:00.747014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.10642","created_at":"2026-07-05T02:10:00.747014+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZCXKKXNHEME","created_at":"2026-07-05T02:10:00.747014+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZCXKKXNHEMEJUCP","created_at":"2026-07-05T02:10:00.747014+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZCXKKXN","created_at":"2026-07-05T02:10:00.747014+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/VZCXKKXNHEMEJUCPVGJBU4TD4E","json":"https://pith.science/pith/VZCXKKXNHEMEJUCPVGJBU4TD4E.json","graph_json":"https://pith.science/api/pith-number/VZCXKKXNHEMEJUCPVGJBU4TD4E/graph.json","events_json":"https://pith.science/api/pith-number/VZCXKKXNHEMEJUCPVGJBU4TD4E/events.json","paper":"https://pith.science/paper/VZCXKKXN"},"agent_actions":{"view_html":"https://pith.science/pith/VZCXKKXNHEMEJUCPVGJBU4TD4E","download_json":"https://pith.science/pith/VZCXKKXNHEMEJUCPVGJBU4TD4E.json","view_paper":"https://pith.science/paper/VZCXKKXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.10642&json=true","fetch_graph":"https://pith.science/api/pith-number/VZCXKKXNHEMEJUCPVGJBU4TD4E/graph.json","fetch_events":"https://pith.science/api/pith-number/VZCXKKXNHEMEJUCPVGJBU4TD4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZCXKKXNHEMEJUCPVGJBU4TD4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZCXKKXNHEMEJUCPVGJBU4TD4E/action/storage_attestation","attest_author":"https://pith.science/pith/VZCXKKXNHEMEJUCPVGJBU4TD4E/action/author_attestation","sign_citation":"https://pith.science/pith/VZCXKKXNHEMEJUCPVGJBU4TD4E/action/citation_signature","submit_replication":"https://pith.science/pith/VZCXKKXNHEMEJUCPVGJBU4TD4E/action/replication_record"}},"created_at":"2026-07-05T02:10:00.747014+00:00","updated_at":"2026-07-05T02:10:00.747014+00:00"}