{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KCJJIFK3Y4STGKBWY7GPTYRERQ","short_pith_number":"pith:KCJJIFK3","schema_version":"1.0","canonical_sha256":"509294155bc725332836c7ccf9e2248c2a91cf9d568a1012f707f1a95d35cab0","source":{"kind":"arxiv","id":"2406.12527","version":1},"attestation_state":"computed","paper":{"title":"FuseGen: PLM Fusion for Data-generation based Zero-shot Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianqing Zhang, Jingjing Liu, Peng Li, Tianyuan Zou, Yang Liu, Ya-Qin Zhang","submitted_at":"2024-06-18T11:55:05Z","abstract_excerpt":"Data generation-based zero-shot learning, although effective in training Small Task-specific Models (STMs) via synthetic datasets generated by Pre-trained Language Models (PLMs), is often limited by the low quality of such synthetic datasets. Previous solutions have primarily focused on single PLM settings, where synthetic datasets are typically restricted to specific sub-spaces and often deviate from real-world distributions, leading to severe distribution bias. To mitigate such bias, we propose FuseGen, a novel data generation-based zero-shot learning framework that introduces a new criteria"},"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":"2406.12527","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T11:55:05Z","cross_cats_sorted":[],"title_canon_sha256":"a7dcd147af2f147ca157cfca87ef338f11784fce4d2993be8586a4b9430e22e1","abstract_canon_sha256":"eb305622d38a6b564c9710ac5f35191b57a4c947010f50d3aeb7b2e007ad96e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:47.775072Z","signature_b64":"lUvO3TRmLBiY6+6pV0F4ND5rc9rE06+jc9Jqhrldg5Q8Gf696XSPjtiS8FSMAQSRLgB6GiaLUrUngeWcVU/hCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"509294155bc725332836c7ccf9e2248c2a91cf9d568a1012f707f1a95d35cab0","last_reissued_at":"2026-07-05T08:33:47.774640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:47.774640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FuseGen: PLM Fusion for Data-generation based Zero-shot Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianqing Zhang, Jingjing Liu, Peng Li, Tianyuan Zou, Yang Liu, Ya-Qin Zhang","submitted_at":"2024-06-18T11:55:05Z","abstract_excerpt":"Data generation-based zero-shot learning, although effective in training Small Task-specific Models (STMs) via synthetic datasets generated by Pre-trained Language Models (PLMs), is often limited by the low quality of such synthetic datasets. Previous solutions have primarily focused on single PLM settings, where synthetic datasets are typically restricted to specific sub-spaces and often deviate from real-world distributions, leading to severe distribution bias. To mitigate such bias, we propose FuseGen, a novel data generation-based zero-shot learning framework that introduces a new criteria"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12527","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/2406.12527/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":"2406.12527","created_at":"2026-07-05T08:33:47.774697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12527v1","created_at":"2026-07-05T08:33:47.774697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12527","created_at":"2026-07-05T08:33:47.774697+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCJJIFK3Y4ST","created_at":"2026-07-05T08:33:47.774697+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCJJIFK3Y4STGKBW","created_at":"2026-07-05T08:33:47.774697+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCJJIFK3","created_at":"2026-07-05T08:33:47.774697+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.17421","citing_title":"Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks","ref_index":74,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KCJJIFK3Y4STGKBWY7GPTYRERQ","json":"https://pith.science/pith/KCJJIFK3Y4STGKBWY7GPTYRERQ.json","graph_json":"https://pith.science/api/pith-number/KCJJIFK3Y4STGKBWY7GPTYRERQ/graph.json","events_json":"https://pith.science/api/pith-number/KCJJIFK3Y4STGKBWY7GPTYRERQ/events.json","paper":"https://pith.science/paper/KCJJIFK3"},"agent_actions":{"view_html":"https://pith.science/pith/KCJJIFK3Y4STGKBWY7GPTYRERQ","download_json":"https://pith.science/pith/KCJJIFK3Y4STGKBWY7GPTYRERQ.json","view_paper":"https://pith.science/paper/KCJJIFK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12527&json=true","fetch_graph":"https://pith.science/api/pith-number/KCJJIFK3Y4STGKBWY7GPTYRERQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KCJJIFK3Y4STGKBWY7GPTYRERQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCJJIFK3Y4STGKBWY7GPTYRERQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCJJIFK3Y4STGKBWY7GPTYRERQ/action/storage_attestation","attest_author":"https://pith.science/pith/KCJJIFK3Y4STGKBWY7GPTYRERQ/action/author_attestation","sign_citation":"https://pith.science/pith/KCJJIFK3Y4STGKBWY7GPTYRERQ/action/citation_signature","submit_replication":"https://pith.science/pith/KCJJIFK3Y4STGKBWY7GPTYRERQ/action/replication_record"}},"created_at":"2026-07-05T08:33:47.774697+00:00","updated_at":"2026-07-05T08:33:47.774697+00:00"}