{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HFVAUVMSWYT44OMDPXC7UXN2SH","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":"58675995fc212e3be16bba476c07d713958186dbaa27a452c44f4c2843312298","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-05T18:40:37Z","title_canon_sha256":"6607e57b7761e190d93d87d30497eab52aad12947a8aa18147cb3e422f21ee13"},"schema_version":"1.0","source":{"id":"1906.02242","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.02242","created_at":"2026-05-17T23:44:01Z"},{"alias_kind":"arxiv_version","alias_value":"1906.02242v1","created_at":"2026-05-17T23:44:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02242","created_at":"2026-05-17T23:44:01Z"},{"alias_kind":"pith_short_12","alias_value":"HFVAUVMSWYT4","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HFVAUVMSWYT44OMD","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HFVAUVMS","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:5d94e4f0300d87a175f2939ce1336c4100430e11be4789123682218c2ec76a30","target":"graph","created_at":"2026-05-17T23:44:01Z","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 introduce VAMPIRE, a lightweight pretraining framework for effective text classification when data and computing resources are limited. We pretrain a unigram document model as a variational autoencoder on in-domain, unlabeled data and use its internal states as features in a downstream classifier. Empirically, we show the relative strength of VAMPIRE against computationally expensive contextual embeddings and other popular semi-supervised baselines under low resource settings. We also find that fine-tuning to in-domain data is crucial to achieving decent performance from contextual embeddin","authors_text":"Dallas Card, Noah A. Smith, Suchin Gururangan, Tam Dang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-05T18:40:37Z","title":"Variational Pretraining for Semi-supervised Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02242","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":"sha256:02d4f9707471c475b1376812977e8fe8a9270ec60adc08e346bad0aa97324968","target":"record","created_at":"2026-05-17T23:44:01Z","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":"58675995fc212e3be16bba476c07d713958186dbaa27a452c44f4c2843312298","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-05T18:40:37Z","title_canon_sha256":"6607e57b7761e190d93d87d30497eab52aad12947a8aa18147cb3e422f21ee13"},"schema_version":"1.0","source":{"id":"1906.02242","kind":"arxiv","version":1}},"canonical_sha256":"396a0a5592b627ce39837dc5fa5dba91ce78d64de77d69067f999fd0c1f92c13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"396a0a5592b627ce39837dc5fa5dba91ce78d64de77d69067f999fd0c1f92c13","first_computed_at":"2026-05-17T23:44:01.829273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:01.829273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZosGQCNlJy7ufQzMjnYI6gReopTf48uCxSQEHRt9rIitLWAKM1TZsRWmIqVrU1Ey7eSvJwTht/HYYUxrgTNvBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:01.830040Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.02242","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02d4f9707471c475b1376812977e8fe8a9270ec60adc08e346bad0aa97324968","sha256:5d94e4f0300d87a175f2939ce1336c4100430e11be4789123682218c2ec76a30"],"state_sha256":"6650073b72f42bdffff816812478637e3eb7c6818595d2985b2eed3e4add9246"}