{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DWFECS6HXVPWMCTDWOWXQTNKBH","short_pith_number":"pith:DWFECS6H","schema_version":"1.0","canonical_sha256":"1d8a414bc7bd5f660a63b3ad784daa09fd85208217dae61ab1f80eb0d6d9a581","source":{"kind":"arxiv","id":"2309.09582","version":2},"attestation_state":"computed","paper":{"title":"Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alan Akbik, Felix Hamborg, Jonas Golde, Julian Risch, Patrick Haller","submitted_at":"2023-09-18T08:45:47Z","abstract_excerpt":"Most NLP tasks are modeled as supervised learning and thus require labeled training data to train effective models. However, manually producing such data at sufficient quality and quantity is known to be costly and time-intensive. Current research addresses this bottleneck by exploring a novel paradigm called zero-shot learning via dataset generation. Here, a powerful LLM is prompted with a task description to generate labeled data that can be used to train a downstream NLP model. For instance, an LLM might be prompted to \"generate 500 movie reviews with positive overall sentiment, and another"},"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":"2309.09582","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-18T08:45:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"97ecaadee7f73b5d6692c0ca8554f3f67abac72c89c4ffa182d719f32bfd8220","abstract_canon_sha256":"0889ce738a6bc8e3a612453626feb07cfdd44034d8c6adacdc34b59a9c83ff2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:57.182009Z","signature_b64":"RBQJJNX6QAQ14HO6vqgyMKiTUzOXUsezDrY7dvLxBtcAOqsHga35r2SQ2WIPC/wiWBbfympDFNpyVQdkdhglDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d8a414bc7bd5f660a63b3ad784daa09fd85208217dae61ab1f80eb0d6d9a581","last_reissued_at":"2026-07-05T07:40:57.181506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:57.181506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fabricator: An Open Source Toolkit for Generating Labeled Training Data with Teacher LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alan Akbik, Felix Hamborg, Jonas Golde, Julian Risch, Patrick Haller","submitted_at":"2023-09-18T08:45:47Z","abstract_excerpt":"Most NLP tasks are modeled as supervised learning and thus require labeled training data to train effective models. However, manually producing such data at sufficient quality and quantity is known to be costly and time-intensive. Current research addresses this bottleneck by exploring a novel paradigm called zero-shot learning via dataset generation. Here, a powerful LLM is prompted with a task description to generate labeled data that can be used to train a downstream NLP model. For instance, an LLM might be prompted to \"generate 500 movie reviews with positive overall sentiment, and another"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09582","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/2309.09582/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":"2309.09582","created_at":"2026-07-05T07:40:57.181562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09582v2","created_at":"2026-07-05T07:40:57.181562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09582","created_at":"2026-07-05T07:40:57.181562+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWFECS6HXVPW","created_at":"2026-07-05T07:40:57.181562+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWFECS6HXVPWMCTD","created_at":"2026-07-05T07:40:57.181562+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWFECS6H","created_at":"2026-07-05T07:40:57.181562+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DWFECS6HXVPWMCTDWOWXQTNKBH","json":"https://pith.science/pith/DWFECS6HXVPWMCTDWOWXQTNKBH.json","graph_json":"https://pith.science/api/pith-number/DWFECS6HXVPWMCTDWOWXQTNKBH/graph.json","events_json":"https://pith.science/api/pith-number/DWFECS6HXVPWMCTDWOWXQTNKBH/events.json","paper":"https://pith.science/paper/DWFECS6H"},"agent_actions":{"view_html":"https://pith.science/pith/DWFECS6HXVPWMCTDWOWXQTNKBH","download_json":"https://pith.science/pith/DWFECS6HXVPWMCTDWOWXQTNKBH.json","view_paper":"https://pith.science/paper/DWFECS6H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09582&json=true","fetch_graph":"https://pith.science/api/pith-number/DWFECS6HXVPWMCTDWOWXQTNKBH/graph.json","fetch_events":"https://pith.science/api/pith-number/DWFECS6HXVPWMCTDWOWXQTNKBH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWFECS6HXVPWMCTDWOWXQTNKBH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWFECS6HXVPWMCTDWOWXQTNKBH/action/storage_attestation","attest_author":"https://pith.science/pith/DWFECS6HXVPWMCTDWOWXQTNKBH/action/author_attestation","sign_citation":"https://pith.science/pith/DWFECS6HXVPWMCTDWOWXQTNKBH/action/citation_signature","submit_replication":"https://pith.science/pith/DWFECS6HXVPWMCTDWOWXQTNKBH/action/replication_record"}},"created_at":"2026-07-05T07:40:57.181562+00:00","updated_at":"2026-07-05T07:40:57.181562+00:00"}