{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VGIRN4OB35K7B7BMCVORQUAUV7","short_pith_number":"pith:VGIRN4OB","schema_version":"1.0","canonical_sha256":"a99116f1c1df55f0fc2c155d185014afc27e7bf580ac4e17b529db38afd4b154","source":{"kind":"arxiv","id":"1806.06259","version":1},"attestation_state":"computed","paper":{"title":"Evaluation of sentence embeddings in downstream and linguistic probing tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian S. Perone, Roberto Silveira, Thomas S. Paula","submitted_at":"2018-06-16T16:07:49Z","abstract_excerpt":"Despite the fast developmental pace of new sentence embedding methods, it is still challenging to find comprehensive evaluations of these different techniques. In the past years, we saw significant improvements in the field of sentence embeddings and especially towards the development of universal sentence encoders that could provide inductive transfer to a wide variety of downstream tasks. In this work, we perform a comprehensive evaluation of recent methods using a wide variety of downstream and linguistic feature probing tasks. We show that a simple approach using bag-of-words with a recent"},"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":"1806.06259","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-06-16T16:07:49Z","cross_cats_sorted":[],"title_canon_sha256":"fb7fcec906f87a574524769c566bd09f393760f1b16cfc04d36622b4e841f700","abstract_canon_sha256":"1715f48689f295791b58c814b3aed8eab642e4de059a186daf0f952857081ffd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:03.111262Z","signature_b64":"kOt1M9HRObqD/7cF8n+zq3v1cByi7zy+xzja83TLunZvyARxG30NujH1vIoyK+nYroBfC0c5bmYAIRxEmhLfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a99116f1c1df55f0fc2c155d185014afc27e7bf580ac4e17b529db38afd4b154","last_reissued_at":"2026-05-18T00:13:03.110607Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:03.110607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of sentence embeddings in downstream and linguistic probing tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian S. Perone, Roberto Silveira, Thomas S. Paula","submitted_at":"2018-06-16T16:07:49Z","abstract_excerpt":"Despite the fast developmental pace of new sentence embedding methods, it is still challenging to find comprehensive evaluations of these different techniques. In the past years, we saw significant improvements in the field of sentence embeddings and especially towards the development of universal sentence encoders that could provide inductive transfer to a wide variety of downstream tasks. In this work, we perform a comprehensive evaluation of recent methods using a wide variety of downstream and linguistic feature probing tasks. We show that a simple approach using bag-of-words with a recent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06259","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":"1806.06259","created_at":"2026-05-18T00:13:03.110708+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.06259v1","created_at":"2026-05-18T00:13:03.110708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06259","created_at":"2026-05-18T00:13:03.110708+00:00"},{"alias_kind":"pith_short_12","alias_value":"VGIRN4OB35K7","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VGIRN4OB35K7B7BM","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VGIRN4OB","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.07033","citing_title":"Neural Language Model Based Training Data Augmentation for Weakly Supervised Early Rumor Detection","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11158","citing_title":"Cross-Lingual Transfer for Distantly Supervised and Low-resources Indonesian NER","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VGIRN4OB35K7B7BMCVORQUAUV7","json":"https://pith.science/pith/VGIRN4OB35K7B7BMCVORQUAUV7.json","graph_json":"https://pith.science/api/pith-number/VGIRN4OB35K7B7BMCVORQUAUV7/graph.json","events_json":"https://pith.science/api/pith-number/VGIRN4OB35K7B7BMCVORQUAUV7/events.json","paper":"https://pith.science/paper/VGIRN4OB"},"agent_actions":{"view_html":"https://pith.science/pith/VGIRN4OB35K7B7BMCVORQUAUV7","download_json":"https://pith.science/pith/VGIRN4OB35K7B7BMCVORQUAUV7.json","view_paper":"https://pith.science/paper/VGIRN4OB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.06259&json=true","fetch_graph":"https://pith.science/api/pith-number/VGIRN4OB35K7B7BMCVORQUAUV7/graph.json","fetch_events":"https://pith.science/api/pith-number/VGIRN4OB35K7B7BMCVORQUAUV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VGIRN4OB35K7B7BMCVORQUAUV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VGIRN4OB35K7B7BMCVORQUAUV7/action/storage_attestation","attest_author":"https://pith.science/pith/VGIRN4OB35K7B7BMCVORQUAUV7/action/author_attestation","sign_citation":"https://pith.science/pith/VGIRN4OB35K7B7BMCVORQUAUV7/action/citation_signature","submit_replication":"https://pith.science/pith/VGIRN4OB35K7B7BMCVORQUAUV7/action/replication_record"}},"created_at":"2026-05-18T00:13:03.110708+00:00","updated_at":"2026-05-18T00:13:03.110708+00:00"}