{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WJ6HZFPNIUFXYVN2PQZJPAFMZD","short_pith_number":"pith:WJ6HZFPN","schema_version":"1.0","canonical_sha256":"b27c7c95ed450b7c55ba7c329780acc8e61a96ce2b17ffb94be3528291d9cbbb","source":{"kind":"arxiv","id":"1803.02893","version":1},"attestation_state":"computed","paper":{"title":"An efficient framework for learning sentence representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Honglak Lee, Lajanugen Logeswaran","submitted_at":"2018-03-07T22:02:10Z","abstract_excerpt":"In this work we propose a simple and efficient framework for learning sentence representations from unlabelled data. Drawing inspiration from the distributional hypothesis and recent work on learning sentence representations, we reformulate the problem of predicting the context in which a sentence appears as a classification problem. Given a sentence and its context, a classifier distinguishes context sentences from other contrastive sentences based on their vector representations. This allows us to efficiently learn different types of encoding functions, and we show that the model learns high"},"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":"1803.02893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-03-07T22:02:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"722dfadb437b200fe774fa973330bcde67e4f9ef53bba7ed55327a27807cff2e","abstract_canon_sha256":"38370a7b38a0010d95944c77bb5c65eb5bc143184186e5ce290365f6673b853d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:45.109495Z","signature_b64":"0DgVAez/jKS6J/9mEP4BnniVwxpnZL9St3IR69UTntEk1UaKyBHVbdaFN3cMGOpuJqsy3mPKRhJpUvKNT2JnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b27c7c95ed450b7c55ba7c329780acc8e61a96ce2b17ffb94be3528291d9cbbb","last_reissued_at":"2026-05-18T00:21:45.108860Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:45.108860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An efficient framework for learning sentence representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Honglak Lee, Lajanugen Logeswaran","submitted_at":"2018-03-07T22:02:10Z","abstract_excerpt":"In this work we propose a simple and efficient framework for learning sentence representations from unlabelled data. Drawing inspiration from the distributional hypothesis and recent work on learning sentence representations, we reformulate the problem of predicting the context in which a sentence appears as a classification problem. Given a sentence and its context, a classifier distinguishes context sentences from other contrastive sentences based on their vector representations. This allows us to efficiently learn different types of encoding functions, and we show that the model learns high"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.02893","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":"1803.02893","created_at":"2026-05-18T00:21:45.108943+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.02893v1","created_at":"2026-05-18T00:21:45.108943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.02893","created_at":"2026-05-18T00:21:45.108943+00:00"},{"alias_kind":"pith_short_12","alias_value":"WJ6HZFPNIUFX","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"WJ6HZFPNIUFXYVN2","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"WJ6HZFPN","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.11085","citing_title":"Enhancing PIO Element Detection in Medical Text Using Contextualized Embedding","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11043","citing_title":"EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11291","citing_title":"Optimal Representations for Generalized Contrastive Learning with Imbalanced Datasets","ref_index":96,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01372","citing_title":"Embedding-based In-Context Prompt Training for Enhancing LLMs as Text Encoders","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11043","citing_title":"EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WJ6HZFPNIUFXYVN2PQZJPAFMZD","json":"https://pith.science/pith/WJ6HZFPNIUFXYVN2PQZJPAFMZD.json","graph_json":"https://pith.science/api/pith-number/WJ6HZFPNIUFXYVN2PQZJPAFMZD/graph.json","events_json":"https://pith.science/api/pith-number/WJ6HZFPNIUFXYVN2PQZJPAFMZD/events.json","paper":"https://pith.science/paper/WJ6HZFPN"},"agent_actions":{"view_html":"https://pith.science/pith/WJ6HZFPNIUFXYVN2PQZJPAFMZD","download_json":"https://pith.science/pith/WJ6HZFPNIUFXYVN2PQZJPAFMZD.json","view_paper":"https://pith.science/paper/WJ6HZFPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.02893&json=true","fetch_graph":"https://pith.science/api/pith-number/WJ6HZFPNIUFXYVN2PQZJPAFMZD/graph.json","fetch_events":"https://pith.science/api/pith-number/WJ6HZFPNIUFXYVN2PQZJPAFMZD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WJ6HZFPNIUFXYVN2PQZJPAFMZD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WJ6HZFPNIUFXYVN2PQZJPAFMZD/action/storage_attestation","attest_author":"https://pith.science/pith/WJ6HZFPNIUFXYVN2PQZJPAFMZD/action/author_attestation","sign_citation":"https://pith.science/pith/WJ6HZFPNIUFXYVN2PQZJPAFMZD/action/citation_signature","submit_replication":"https://pith.science/pith/WJ6HZFPNIUFXYVN2PQZJPAFMZD/action/replication_record"}},"created_at":"2026-05-18T00:21:45.108943+00:00","updated_at":"2026-05-18T00:21:45.108943+00:00"}