{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WTEDVKJIX42RLLYNRJWLP3EY5P","short_pith_number":"pith:WTEDVKJI","schema_version":"1.0","canonical_sha256":"b4c83aa928bf3515af0d8a6cb7ec98ebeb0005a64fed442151c6353129d19409","source":{"kind":"arxiv","id":"2210.12329","version":1},"attestation_state":"computed","paper":{"title":"ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiacheng Ye, Jiahui Gao, Jiangtao Feng, Lingpeng Kong, Tao Yu, Zhiyong Wu","submitted_at":"2022-10-22T02:07:10Z","abstract_excerpt":"Recently, dataset-generation-based zero-shot learning has shown promising results by training a task-specific model with a dataset synthesized from large pre-trained language models (PLMs). The final task-specific model often achieves compatible or even better performance than PLMs under the zero-shot setting, with orders of magnitude fewer parameters. However, synthetic datasets have their drawbacks. They have long been suffering from low-quality issues (e.g., low informativeness and redundancy). This explains why the massive synthetic data does not lead to better performance -- a scenario we"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.12329","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-22T02:07:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"456b160fbd42e0eccdbb560fbe844e30c45ecd19beb0fb812639826029d187b3","abstract_canon_sha256":"d4d6e05a6ddcd64f76e89c632601df11867d7a6401984f4874b9ce66b08fce12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:26.772165Z","signature_b64":"fSZ93KNkCObPjUDCSr9IYGlUqqqXTsZJroIb1UqjTNH7Gzwihn1NL8/QX9/ViuaFf0cJ+SD+2PFnyeDUc5TYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4c83aa928bf3515af0d8a6cb7ec98ebeb0005a64fed442151c6353129d19409","last_reissued_at":"2026-07-05T05:09:26.771703Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:26.771703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiacheng Ye, Jiahui Gao, Jiangtao Feng, Lingpeng Kong, Tao Yu, Zhiyong Wu","submitted_at":"2022-10-22T02:07:10Z","abstract_excerpt":"Recently, dataset-generation-based zero-shot learning has shown promising results by training a task-specific model with a dataset synthesized from large pre-trained language models (PLMs). The final task-specific model often achieves compatible or even better performance than PLMs under the zero-shot setting, with orders of magnitude fewer parameters. However, synthetic datasets have their drawbacks. They have long been suffering from low-quality issues (e.g., low informativeness and redundancy). This explains why the massive synthetic data does not lead to better performance -- a scenario we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12329","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.12329/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.12329","created_at":"2026-07-05T05:09:26.771762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.12329v1","created_at":"2026-07-05T05:09:26.771762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12329","created_at":"2026-07-05T05:09:26.771762+00:00"},{"alias_kind":"pith_short_12","alias_value":"WTEDVKJIX42R","created_at":"2026-07-05T05:09:26.771762+00:00"},{"alias_kind":"pith_short_16","alias_value":"WTEDVKJIX42RLLYN","created_at":"2026-07-05T05:09:26.771762+00:00"},{"alias_kind":"pith_short_8","alias_value":"WTEDVKJI","created_at":"2026-07-05T05:09:26.771762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.06226","citing_title":"No Data? No Problem: Synthesizing Security Graphs for Better Intrusion Detection","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14169","citing_title":"BOOKMARKS: Efficient Active Storyline Memory for Role-playing","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WTEDVKJIX42RLLYNRJWLP3EY5P","json":"https://pith.science/pith/WTEDVKJIX42RLLYNRJWLP3EY5P.json","graph_json":"https://pith.science/api/pith-number/WTEDVKJIX42RLLYNRJWLP3EY5P/graph.json","events_json":"https://pith.science/api/pith-number/WTEDVKJIX42RLLYNRJWLP3EY5P/events.json","paper":"https://pith.science/paper/WTEDVKJI"},"agent_actions":{"view_html":"https://pith.science/pith/WTEDVKJIX42RLLYNRJWLP3EY5P","download_json":"https://pith.science/pith/WTEDVKJIX42RLLYNRJWLP3EY5P.json","view_paper":"https://pith.science/paper/WTEDVKJI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.12329&json=true","fetch_graph":"https://pith.science/api/pith-number/WTEDVKJIX42RLLYNRJWLP3EY5P/graph.json","fetch_events":"https://pith.science/api/pith-number/WTEDVKJIX42RLLYNRJWLP3EY5P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WTEDVKJIX42RLLYNRJWLP3EY5P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WTEDVKJIX42RLLYNRJWLP3EY5P/action/storage_attestation","attest_author":"https://pith.science/pith/WTEDVKJIX42RLLYNRJWLP3EY5P/action/author_attestation","sign_citation":"https://pith.science/pith/WTEDVKJIX42RLLYNRJWLP3EY5P/action/citation_signature","submit_replication":"https://pith.science/pith/WTEDVKJIX42RLLYNRJWLP3EY5P/action/replication_record"}},"created_at":"2026-07-05T05:09:26.771762+00:00","updated_at":"2026-07-05T05:09:26.771762+00:00"}