{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HFVAUVMSWYT44OMDPXC7UXN2SH","short_pith_number":"pith:HFVAUVMS","canonical_record":{"source":{"id":"1906.02242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-05T18:40:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6607e57b7761e190d93d87d30497eab52aad12947a8aa18147cb3e422f21ee13","abstract_canon_sha256":"58675995fc212e3be16bba476c07d713958186dbaa27a452c44f4c2843312298"},"schema_version":"1.0"},"canonical_sha256":"396a0a5592b627ce39837dc5fa5dba91ce78d64de77d69067f999fd0c1f92c13","source":{"kind":"arxiv","id":"1906.02242","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HFVAUVMSWYT44OMDPXC7UXN2SH","target":"record","payload":{"canonical_record":{"source":{"id":"1906.02242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-05T18:40:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6607e57b7761e190d93d87d30497eab52aad12947a8aa18147cb3e422f21ee13","abstract_canon_sha256":"58675995fc212e3be16bba476c07d713958186dbaa27a452c44f4c2843312298"},"schema_version":"1.0"},"canonical_sha256":"396a0a5592b627ce39837dc5fa5dba91ce78d64de77d69067f999fd0c1f92c13","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:01.830040Z","signature_b64":"ZosGQCNlJy7ufQzMjnYI6gReopTf48uCxSQEHRt9rIitLWAKM1TZsRWmIqVrU1Ey7eSvJwTht/HYYUxrgTNvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"396a0a5592b627ce39837dc5fa5dba91ce78d64de77d69067f999fd0c1f92c13","last_reissued_at":"2026-05-17T23:44:01.829273Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:01.829273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.02242","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":"2026-05-17T23:44:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fXS+zHD3tnkmyezE2JtwJCZWkROZ3PQf/+PpzMkrf/U5SEjS/CMntvDqF3fY9WXLRIFGVhH0PEPFWUhX/TWWCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T06:19:42.117157Z"},"content_sha256":"02d4f9707471c475b1376812977e8fe8a9270ec60adc08e346bad0aa97324968","schema_version":"1.0","event_id":"sha256:02d4f9707471c475b1376812977e8fe8a9270ec60adc08e346bad0aa97324968"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HFVAUVMSWYT44OMDPXC7UXN2SH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational Pretraining for Semi-supervised Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dallas Card, Noah A. Smith, Suchin Gururangan, Tam Dang","submitted_at":"2019-06-05T18:40:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02242","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":"2026-05-17T23:44:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vZA2TzieHSRjkYB9lMNipEhXaflKC5PGQ+ivdLRnWfFU6Ug0VFVknBDbe9U3KZCaURG4ynRMUCjVLQ1MGzovDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T06:19:42.117527Z"},"content_sha256":"5d94e4f0300d87a175f2939ce1336c4100430e11be4789123682218c2ec76a30","schema_version":"1.0","event_id":"sha256:5d94e4f0300d87a175f2939ce1336c4100430e11be4789123682218c2ec76a30"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HFVAUVMSWYT44OMDPXC7UXN2SH/bundle.json","state_url":"https://pith.science/pith/HFVAUVMSWYT44OMDPXC7UXN2SH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HFVAUVMSWYT44OMDPXC7UXN2SH/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":"2026-05-20T06:19:42Z","links":{"resolver":"https://pith.science/pith/HFVAUVMSWYT44OMDPXC7UXN2SH","bundle":"https://pith.science/pith/HFVAUVMSWYT44OMDPXC7UXN2SH/bundle.json","state":"https://pith.science/pith/HFVAUVMSWYT44OMDPXC7UXN2SH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HFVAUVMSWYT44OMDPXC7UXN2SH/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R18AuGSxW7Rs69sWPV2zE/uT7af0ml8P8isbA/mfpJ6L7BcXSqQAZtADE19rI+v66ZtFilDggUTkoB3JxMxeCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T06:19:42.119608Z","bundle_sha256":"ca2153bf91f8cff877cea8623efe816a82d202f37e490d5a8d3ac1b6c93e8b68"}}