{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:KF7F54W6RLWSC2PLYVRDGXT7VL","short_pith_number":"pith:KF7F54W6","schema_version":"1.0","canonical_sha256":"517e5ef2de8aed2169ebc562335e7faaf268f3f615f0dc1d5c44ff24e52b6758","source":{"kind":"arxiv","id":"1511.01432","version":1},"attestation_state":"computed","paper":{"title":"Semi-supervised Sequence Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Andrew M. Dai, Quoc V. Le","submitted_at":"2015-11-04T18:48:36Z","abstract_excerpt":"We present two approaches that use unlabeled data to improve sequence learning with recurrent networks. The first approach is to predict what comes next in a sequence, which is a conventional language model in natural language processing. The second approach is to use a sequence autoencoder, which reads the input sequence into a vector and predicts the input sequence again. These two algorithms can be used as a \"pretraining\" step for a later supervised sequence learning algorithm. In other words, the parameters obtained from the unsupervised step can be used as a starting point for other super"},"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":"1511.01432","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-04T18:48:36Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6f99d228662896679525750f05cb8ce1a91be97b8f9e7ded22462e76751e827c","abstract_canon_sha256":"e4fd26e295b1b71390ac98780172b0f8d4d4bec2618661b526b8fb501a606363"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:27:47.100695Z","signature_b64":"kLJ9jHH26APJflkkMg1kr+vloEQcsj67DHLtVcijLy0gBBPpUb0yJ/4ffD3ccAg0Fc5vtVUptzBJ2JTVNrnpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"517e5ef2de8aed2169ebc562335e7faaf268f3f615f0dc1d5c44ff24e52b6758","last_reissued_at":"2026-05-18T01:27:47.100048Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:27:47.100048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-supervised Sequence Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Andrew M. Dai, Quoc V. Le","submitted_at":"2015-11-04T18:48:36Z","abstract_excerpt":"We present two approaches that use unlabeled data to improve sequence learning with recurrent networks. The first approach is to predict what comes next in a sequence, which is a conventional language model in natural language processing. The second approach is to use a sequence autoencoder, which reads the input sequence into a vector and predicts the input sequence again. These two algorithms can be used as a \"pretraining\" step for a later supervised sequence learning algorithm. In other words, the parameters obtained from the unsupervised step can be used as a starting point for other super"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.01432","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":"1511.01432","created_at":"2026-05-18T01:27:47.100148+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.01432v1","created_at":"2026-05-18T01:27:47.100148+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.01432","created_at":"2026-05-18T01:27:47.100148+00:00"},{"alias_kind":"pith_short_12","alias_value":"KF7F54W6RLWS","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_16","alias_value":"KF7F54W6RLWSC2PL","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_8","alias_value":"KF7F54W6","created_at":"2026-05-18T12:29:27.538025+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2102.01293","citing_title":"Scaling Laws for Transfer","ref_index":169,"is_internal_anchor":true},{"citing_arxiv_id":"1908.09203","citing_title":"Release Strategies and the Social Impacts of Language Models","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2112.00861","citing_title":"A General Language Assistant as a Laboratory for Alignment","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2207.05221","citing_title":"Language Models (Mostly) Know What They Know","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KF7F54W6RLWSC2PLYVRDGXT7VL","json":"https://pith.science/pith/KF7F54W6RLWSC2PLYVRDGXT7VL.json","graph_json":"https://pith.science/api/pith-number/KF7F54W6RLWSC2PLYVRDGXT7VL/graph.json","events_json":"https://pith.science/api/pith-number/KF7F54W6RLWSC2PLYVRDGXT7VL/events.json","paper":"https://pith.science/paper/KF7F54W6"},"agent_actions":{"view_html":"https://pith.science/pith/KF7F54W6RLWSC2PLYVRDGXT7VL","download_json":"https://pith.science/pith/KF7F54W6RLWSC2PLYVRDGXT7VL.json","view_paper":"https://pith.science/paper/KF7F54W6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.01432&json=true","fetch_graph":"https://pith.science/api/pith-number/KF7F54W6RLWSC2PLYVRDGXT7VL/graph.json","fetch_events":"https://pith.science/api/pith-number/KF7F54W6RLWSC2PLYVRDGXT7VL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KF7F54W6RLWSC2PLYVRDGXT7VL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KF7F54W6RLWSC2PLYVRDGXT7VL/action/storage_attestation","attest_author":"https://pith.science/pith/KF7F54W6RLWSC2PLYVRDGXT7VL/action/author_attestation","sign_citation":"https://pith.science/pith/KF7F54W6RLWSC2PLYVRDGXT7VL/action/citation_signature","submit_replication":"https://pith.science/pith/KF7F54W6RLWSC2PLYVRDGXT7VL/action/replication_record"}},"created_at":"2026-05-18T01:27:47.100148+00:00","updated_at":"2026-05-18T01:27:47.100148+00:00"}