{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:KF7F54W6RLWSC2PLYVRDGXT7VL","short_pith_number":"pith:KF7F54W6","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"},"canonical_sha256":"517e5ef2de8aed2169ebc562335e7faaf268f3f615f0dc1d5c44ff24e52b6758","source":{"kind":"arxiv","id":"1511.01432","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.01432","created_at":"2026-05-18T01:27:47Z"},{"alias_kind":"arxiv_version","alias_value":"1511.01432v1","created_at":"2026-05-18T01:27:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.01432","created_at":"2026-05-18T01:27:47Z"},{"alias_kind":"pith_short_12","alias_value":"KF7F54W6RLWS","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"KF7F54W6RLWSC2PL","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"KF7F54W6","created_at":"2026-05-18T12:29:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:KF7F54W6RLWSC2PLYVRDGXT7VL","target":"record","payload":{"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"},"canonical_sha256":"517e5ef2de8aed2169ebc562335e7faaf268f3f615f0dc1d5c44ff24e52b6758","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"},"source_kind":"arxiv","source_id":"1511.01432","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:27:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kYE4nKUQPvlD0AUji88K3ZSYE9KqH0AqA54rfies+uvPbglsmveCt4tU/SSjya4206OLmmrd0H1lCXmpYOyCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-19T23:14:17.858400Z"},"content_sha256":"6f76e679657ebe962fe209387a301b9bc207124b5c4b3ce646bf7f08967105c2","schema_version":"1.0","event_id":"sha256:6f76e679657ebe962fe209387a301b9bc207124b5c4b3ce646bf7f08967105c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:KF7F54W6RLWSC2PLYVRDGXT7VL","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:27:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pJdCdeEwSvXZrpn0vdnhQaHDnaAfMrYT3kqtHUnPvyE6TBA67RyiB3IwZczzFjUO/NQlslyahBCulU0KsxPJBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-19T23:14:17.858760Z"},"content_sha256":"ede8db34b44832e7b99390ad2371d2c96a9dc610302158a53d7d23c678fc6e94","schema_version":"1.0","event_id":"sha256:ede8db34b44832e7b99390ad2371d2c96a9dc610302158a53d7d23c678fc6e94"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KF7F54W6RLWSC2PLYVRDGXT7VL/bundle.json","state_url":"https://pith.science/pith/KF7F54W6RLWSC2PLYVRDGXT7VL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KF7F54W6RLWSC2PLYVRDGXT7VL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-19T23:14:17Z","links":{"resolver":"https://pith.science/pith/KF7F54W6RLWSC2PLYVRDGXT7VL","bundle":"https://pith.science/pith/KF7F54W6RLWSC2PLYVRDGXT7VL/bundle.json","state":"https://pith.science/pith/KF7F54W6RLWSC2PLYVRDGXT7VL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KF7F54W6RLWSC2PLYVRDGXT7VL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:KF7F54W6RLWSC2PLYVRDGXT7VL","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e4fd26e295b1b71390ac98780172b0f8d4d4bec2618661b526b8fb501a606363","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-04T18:48:36Z","title_canon_sha256":"6f99d228662896679525750f05cb8ce1a91be97b8f9e7ded22462e76751e827c"},"schema_version":"1.0","source":{"id":"1511.01432","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.01432","created_at":"2026-05-18T01:27:47Z"},{"alias_kind":"arxiv_version","alias_value":"1511.01432v1","created_at":"2026-05-18T01:27:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.01432","created_at":"2026-05-18T01:27:47Z"},{"alias_kind":"pith_short_12","alias_value":"KF7F54W6RLWS","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"KF7F54W6RLWSC2PL","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"KF7F54W6","created_at":"2026-05-18T12:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:ede8db34b44832e7b99390ad2371d2c96a9dc610302158a53d7d23c678fc6e94","target":"graph","created_at":"2026-05-18T01:27:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Andrew M. Dai, Quoc V. Le","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-04T18:48:36Z","title":"Semi-supervised Sequence Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.01432","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6f76e679657ebe962fe209387a301b9bc207124b5c4b3ce646bf7f08967105c2","target":"record","created_at":"2026-05-18T01:27:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e4fd26e295b1b71390ac98780172b0f8d4d4bec2618661b526b8fb501a606363","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-04T18:48:36Z","title_canon_sha256":"6f99d228662896679525750f05cb8ce1a91be97b8f9e7ded22462e76751e827c"},"schema_version":"1.0","source":{"id":"1511.01432","kind":"arxiv","version":1}},"canonical_sha256":"517e5ef2de8aed2169ebc562335e7faaf268f3f615f0dc1d5c44ff24e52b6758","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"517e5ef2de8aed2169ebc562335e7faaf268f3f615f0dc1d5c44ff24e52b6758","first_computed_at":"2026-05-18T01:27:47.100048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:27:47.100048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kLJ9jHH26APJflkkMg1kr+vloEQcsj67DHLtVcijLy0gBBPpUb0yJ/4ffD3ccAg0Fc5vtVUptzBJ2JTVNrnpCw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:27:47.100695Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.01432","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f76e679657ebe962fe209387a301b9bc207124b5c4b3ce646bf7f08967105c2","sha256:ede8db34b44832e7b99390ad2371d2c96a9dc610302158a53d7d23c678fc6e94"],"state_sha256":"6aaca39eff615cc59830037396342c2267dfdfbcb2250580a421d485e6d4e3f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+5V12dfknIOihCatF/sohdHs//Lg2qdyql1YQLAP672CtSU1JsC2C6pfigWyguWHHqxUrRZRP+BF6BnJSpXcAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-19T23:14:17.860735Z","bundle_sha256":"920cdd5aaaaf3cde965c3873a6dd8f2a483713c321909d039e912b08821af235"}}