{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:AYEB3SLVQFCPGQYOR65ACAQRWD","short_pith_number":"pith:AYEB3SLV","schema_version":"1.0","canonical_sha256":"06081dc9758144f3430e8fba010211b0f1edf490c02822d0dcb62af4ac2e6d66","source":{"kind":"arxiv","id":"1705.02364","version":5},"attestation_state":"computed","paper":{"title":"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexis Conneau, Antoine Bordes, Douwe Kiela, Holger Schwenk, Loic Barrault","submitted_at":"2017-05-05T18:54:39Z","abstract_excerpt":"Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks of text, such as sentences, have however not been so successful. Several attempts at learning unsupervised representations of sentences have not reached satisfactory enough performance to be widely adopted. In this paper, we show how universal sentence representations trained using the supervised data of the Stanford Natural Language Inference datasets can consistently outperform unsupervised methods like SkipThought ve"},"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":"1705.02364","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-05T18:54:39Z","cross_cats_sorted":[],"title_canon_sha256":"47dabcc8d69137d5b590bb2b676f6603ddd66425bcc233129f6fe2ecac0fe953","abstract_canon_sha256":"0c76eaeb5eae2b7a21175503d85414986c28b3bf076f11ee6e1d1e983758d660"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:18.937664Z","signature_b64":"r4DqPtYtNrBAl0SUU7BRNLe0S3++kGwzaHDOVH/ehbjBXKO8XduGkBOFitd0vX4LyR5S5eBUBJHlBmsj0Q1UCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06081dc9758144f3430e8fba010211b0f1edf490c02822d0dcb62af4ac2e6d66","last_reissued_at":"2026-05-18T00:11:18.936986Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:18.936986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Supervised Learning of Universal Sentence Representations from Natural Language Inference Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexis Conneau, Antoine Bordes, Douwe Kiela, Holger Schwenk, Loic Barrault","submitted_at":"2017-05-05T18:54:39Z","abstract_excerpt":"Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks of text, such as sentences, have however not been so successful. Several attempts at learning unsupervised representations of sentences have not reached satisfactory enough performance to be widely adopted. In this paper, we show how universal sentence representations trained using the supervised data of the Stanford Natural Language Inference datasets can consistently outperform unsupervised methods like SkipThought ve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.02364","kind":"arxiv","version":5},"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":"1705.02364","created_at":"2026-05-18T00:11:18.937088+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.02364v5","created_at":"2026-05-18T00:11:18.937088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.02364","created_at":"2026-05-18T00:11:18.937088+00:00"},{"alias_kind":"pith_short_12","alias_value":"AYEB3SLVQFCP","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"AYEB3SLVQFCPGQYO","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"AYEB3SLV","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2405.13071","citing_title":"A Novel Method for News Article Event-Based Embedding","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"1910.10683","citing_title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14547","citing_title":"Predicting Post-Traumatic Epilepsy from Clinical Records using Large Language Model Embeddings","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AYEB3SLVQFCPGQYOR65ACAQRWD","json":"https://pith.science/pith/AYEB3SLVQFCPGQYOR65ACAQRWD.json","graph_json":"https://pith.science/api/pith-number/AYEB3SLVQFCPGQYOR65ACAQRWD/graph.json","events_json":"https://pith.science/api/pith-number/AYEB3SLVQFCPGQYOR65ACAQRWD/events.json","paper":"https://pith.science/paper/AYEB3SLV"},"agent_actions":{"view_html":"https://pith.science/pith/AYEB3SLVQFCPGQYOR65ACAQRWD","download_json":"https://pith.science/pith/AYEB3SLVQFCPGQYOR65ACAQRWD.json","view_paper":"https://pith.science/paper/AYEB3SLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.02364&json=true","fetch_graph":"https://pith.science/api/pith-number/AYEB3SLVQFCPGQYOR65ACAQRWD/graph.json","fetch_events":"https://pith.science/api/pith-number/AYEB3SLVQFCPGQYOR65ACAQRWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AYEB3SLVQFCPGQYOR65ACAQRWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AYEB3SLVQFCPGQYOR65ACAQRWD/action/storage_attestation","attest_author":"https://pith.science/pith/AYEB3SLVQFCPGQYOR65ACAQRWD/action/author_attestation","sign_citation":"https://pith.science/pith/AYEB3SLVQFCPGQYOR65ACAQRWD/action/citation_signature","submit_replication":"https://pith.science/pith/AYEB3SLVQFCPGQYOR65ACAQRWD/action/replication_record"}},"created_at":"2026-05-18T00:11:18.937088+00:00","updated_at":"2026-05-18T00:11:18.937088+00:00"}