{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BAD6YCLINZKUUJGOWRLFXECPSQ","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":"38239d6e66a290d95ec1d4fdad106ad7d285b8d39a0ecb82bf2a39c7ff0ced3f","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T04:30:09Z","title_canon_sha256":"d1a4509b1ef95c51b48c4a16a2f7699b767a5a2febc61e7d24617ae078485ae1"},"schema_version":"1.0","source":{"id":"2305.10703","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.10703","created_at":"2026-07-05T06:11:25Z"},{"alias_kind":"arxiv_version","alias_value":"2305.10703v1","created_at":"2026-07-05T06:11:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10703","created_at":"2026-07-05T06:11:25Z"},{"alias_kind":"pith_short_12","alias_value":"BAD6YCLINZKU","created_at":"2026-07-05T06:11:25Z"},{"alias_kind":"pith_short_16","alias_value":"BAD6YCLINZKUUJGO","created_at":"2026-07-05T06:11:25Z"},{"alias_kind":"pith_short_8","alias_value":"BAD6YCLI","created_at":"2026-07-05T06:11:25Z"}],"graph_snapshots":[{"event_id":"sha256:fe38aba4500345ab10f7f0585f793852af7636847d91e20ca830f358a80ce428","target":"graph","created_at":"2026-07-05T06:11:25Z","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/2305.10703/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the development of large language models (LLMs), zero-shot learning has attracted much attention for various NLP tasks. Different from prior works that generate training data with billion-scale natural language generation (NLG) models, we propose a retrieval-enhanced framework to create training data from a general-domain unlabeled corpus. To realize this, we first conduct contrastive pretraining to learn an unsupervised dense retriever for extracting the most relevant documents using class-descriptive verbalizers. We then further propose two simple strategies, namely Verbalizer Augmentat","authors_text":"Chao Zhang, Jiaming Shen, Rongzhi Zhang, Yuchen Zhuang, Yue Yu, Yu Meng","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T04:30:09Z","title":"ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10703","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":"sha256:7d05e5e591d59db2fc68ee5ae93d984f499ea4ae1da31e1879bf5b96bc9919fc","target":"record","created_at":"2026-07-05T06:11:25Z","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":"38239d6e66a290d95ec1d4fdad106ad7d285b8d39a0ecb82bf2a39c7ff0ced3f","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-18T04:30:09Z","title_canon_sha256":"d1a4509b1ef95c51b48c4a16a2f7699b767a5a2febc61e7d24617ae078485ae1"},"schema_version":"1.0","source":{"id":"2305.10703","kind":"arxiv","version":1}},"canonical_sha256":"0807ec09686e554a24ceb4565b904f9436424848ffca148de419fd6e510940d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0807ec09686e554a24ceb4565b904f9436424848ffca148de419fd6e510940d1","first_computed_at":"2026-07-05T06:11:25.716687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:25.716687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zLUHAmz29/bFn3ULPfPx0hb8i50OGGmGTf396KksMvecHNFTxPwOrSehdKIaQmjRO4oCzyomp5M+7BL61pKYDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:25.717097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.10703","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d05e5e591d59db2fc68ee5ae93d984f499ea4ae1da31e1879bf5b96bc9919fc","sha256:fe38aba4500345ab10f7f0585f793852af7636847d91e20ca830f358a80ce428"],"state_sha256":"9b53e99b561512798455262dcdf3fda5143dfebc8b5e97f6482afb27f0dfd1ea"}