{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YECCA6KWI2XCIGYDNH263UXALY","short_pith_number":"pith:YECCA6KW","canonical_record":{"source":{"id":"1908.08788","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-08-22T17:23:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b2f862b079e47d22ef3d6101c3e5141fc41e293e2e95675e2bf8959af9ed5e51","abstract_canon_sha256":"38005aaf1d057af378de963e9da8ac92b185cd3148735a34dbee9219a2b5801e"},"schema_version":"1.0"},"canonical_sha256":"c10420795646ae241b0369f5edd2e05e1d2ddf1d3fd5418cb8a853df41b791b6","source":{"kind":"arxiv","id":"1908.08788","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08788","created_at":"2026-07-05T00:20:54Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08788v2","created_at":"2026-07-05T00:20:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08788","created_at":"2026-07-05T00:20:54Z"},{"alias_kind":"pith_short_12","alias_value":"YECCA6KWI2XC","created_at":"2026-07-05T00:20:54Z"},{"alias_kind":"pith_short_16","alias_value":"YECCA6KWI2XCIGYD","created_at":"2026-07-05T00:20:54Z"},{"alias_kind":"pith_short_8","alias_value":"YECCA6KW","created_at":"2026-07-05T00:20:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YECCA6KWI2XCIGYDNH263UXALY","target":"record","payload":{"canonical_record":{"source":{"id":"1908.08788","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-08-22T17:23:29Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b2f862b079e47d22ef3d6101c3e5141fc41e293e2e95675e2bf8959af9ed5e51","abstract_canon_sha256":"38005aaf1d057af378de963e9da8ac92b185cd3148735a34dbee9219a2b5801e"},"schema_version":"1.0"},"canonical_sha256":"c10420795646ae241b0369f5edd2e05e1d2ddf1d3fd5418cb8a853df41b791b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:54.396574Z","signature_b64":"4//CiAYn2LwRdGaovlyOv55YuFr3/omBeee4fVwCEhZI17bR7gDivOA11OGEz1EcyeMN3OR1L9eTGdCZJbOMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c10420795646ae241b0369f5edd2e05e1d2ddf1d3fd5418cb8a853df41b791b6","last_reissued_at":"2026-07-05T00:20:54.396156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:54.396156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.08788","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:20:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4M/8Sdf55rb4D0GBEud7thKZfCXdFogUhvO1x4R2bLf6BPmxK5ztpLez0Lfoj4szXeowtaOykn4GSqkwZIRGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T12:30:04.554908Z"},"content_sha256":"21f60f32f1fbb6be2778b2b5de3fec240eceac0ebbd3ffd462ab00e924121a2c","schema_version":"1.0","event_id":"sha256:21f60f32f1fbb6be2778b2b5de3fec240eceac0ebbd3ffd462ab00e924121a2c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YECCA6KWI2XCIGYDNH263UXALY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Low Resource NLP Meets Unsupervised Language Model: Meta-pretraining Then Meta-learning for Few-shot Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Huajun Chen, Jiaoyan Chen, Ningyu Zhang, Shumin Deng, Zhanlin Sun","submitted_at":"2019-08-22T17:23:29Z","abstract_excerpt":"Text classification tends to be difficult when data are deficient or when it is required to adapt to unseen classes. In such challenging scenarios, recent studies have often used meta-learning to simulate the few-shot task, thus negating implicit common linguistic features across tasks. This paper addresses such problems using meta-learning and unsupervised language models. Our approach is based on the insight that having a good generalization from a few examples relies on both a generic model initialization and an effective strategy for adapting this model to newly arising tasks. We show that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08788","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.08788/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:20:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C7UfrmvnYJNlxNaWhZ4SFqD2fPYudrwRu2LfG3y/xwK0Ymw2rMGA9WK/l9mkMWjBYrBWiz+p0FnDxn0kc573Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T12:30:04.555395Z"},"content_sha256":"739686534bb289243106c50df4687850d0d1517fe75b64ce3bb111584bd5b7bd","schema_version":"1.0","event_id":"sha256:739686534bb289243106c50df4687850d0d1517fe75b64ce3bb111584bd5b7bd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YECCA6KWI2XCIGYDNH263UXALY/bundle.json","state_url":"https://pith.science/pith/YECCA6KWI2XCIGYDNH263UXALY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YECCA6KWI2XCIGYDNH263UXALY/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":"2026-08-16T12:30:04Z","links":{"resolver":"https://pith.science/pith/YECCA6KWI2XCIGYDNH263UXALY","bundle":"https://pith.science/pith/YECCA6KWI2XCIGYDNH263UXALY/bundle.json","state":"https://pith.science/pith/YECCA6KWI2XCIGYDNH263UXALY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YECCA6KWI2XCIGYDNH263UXALY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YECCA6KWI2XCIGYDNH263UXALY","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":"38005aaf1d057af378de963e9da8ac92b185cd3148735a34dbee9219a2b5801e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-08-22T17:23:29Z","title_canon_sha256":"b2f862b079e47d22ef3d6101c3e5141fc41e293e2e95675e2bf8959af9ed5e51"},"schema_version":"1.0","source":{"id":"1908.08788","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08788","created_at":"2026-07-05T00:20:54Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08788v2","created_at":"2026-07-05T00:20:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08788","created_at":"2026-07-05T00:20:54Z"},{"alias_kind":"pith_short_12","alias_value":"YECCA6KWI2XC","created_at":"2026-07-05T00:20:54Z"},{"alias_kind":"pith_short_16","alias_value":"YECCA6KWI2XCIGYD","created_at":"2026-07-05T00:20:54Z"},{"alias_kind":"pith_short_8","alias_value":"YECCA6KW","created_at":"2026-07-05T00:20:54Z"}],"graph_snapshots":[{"event_id":"sha256:739686534bb289243106c50df4687850d0d1517fe75b64ce3bb111584bd5b7bd","target":"graph","created_at":"2026-07-05T00:20:54Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.08788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text classification tends to be difficult when data are deficient or when it is required to adapt to unseen classes. In such challenging scenarios, recent studies have often used meta-learning to simulate the few-shot task, thus negating implicit common linguistic features across tasks. This paper addresses such problems using meta-learning and unsupervised language models. Our approach is based on the insight that having a good generalization from a few examples relies on both a generic model initialization and an effective strategy for adapting this model to newly arising tasks. We show that","authors_text":"Huajun Chen, Jiaoyan Chen, Ningyu Zhang, Shumin Deng, Zhanlin Sun","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-08-22T17:23:29Z","title":"When Low Resource NLP Meets Unsupervised Language Model: Meta-pretraining Then Meta-learning for Few-shot Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08788","kind":"arxiv","version":2},"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":"sha256:21f60f32f1fbb6be2778b2b5de3fec240eceac0ebbd3ffd462ab00e924121a2c","target":"record","created_at":"2026-07-05T00:20:54Z","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":"38005aaf1d057af378de963e9da8ac92b185cd3148735a34dbee9219a2b5801e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-08-22T17:23:29Z","title_canon_sha256":"b2f862b079e47d22ef3d6101c3e5141fc41e293e2e95675e2bf8959af9ed5e51"},"schema_version":"1.0","source":{"id":"1908.08788","kind":"arxiv","version":2}},"canonical_sha256":"c10420795646ae241b0369f5edd2e05e1d2ddf1d3fd5418cb8a853df41b791b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c10420795646ae241b0369f5edd2e05e1d2ddf1d3fd5418cb8a853df41b791b6","first_computed_at":"2026-07-05T00:20:54.396156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:20:54.396156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4//CiAYn2LwRdGaovlyOv55YuFr3/omBeee4fVwCEhZI17bR7gDivOA11OGEz1EcyeMN3OR1L9eTGdCZJbOMBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:20:54.396574Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.08788","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21f60f32f1fbb6be2778b2b5de3fec240eceac0ebbd3ffd462ab00e924121a2c","sha256:739686534bb289243106c50df4687850d0d1517fe75b64ce3bb111584bd5b7bd"],"state_sha256":"f33a9dcc3e390e9b028bc8a7532f8584585e733ff4ec37f27039fd29a3a7994c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0muptzJyqUJq0HBMQsXh+u4zMfgCt8k9V660ZYHYX1v9MIloHLvz010hMu3vVoxRnN+R29Kmp0JUFY+JMG84Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T12:30:04.558927Z","bundle_sha256":"53b11a0c888db5ae0510f4a72cd7fc2565fb6b99139664c5c09148a14d7aaa93"}}