{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ROBRK3QFWUBXWGKAB75SUEY5HK","short_pith_number":"pith:ROBRK3QF","schema_version":"1.0","canonical_sha256":"8b83156e05b5037b19400ffb2a131d3a8f59979b18b206f99be63c96bdecaf51","source":{"kind":"arxiv","id":"2310.17876","version":3},"attestation_state":"computed","paper":{"title":"TarGEN: Targeted Data Generation with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chitta Baral, Himanshu Gupta, Kevin Scaria, Mihir Parmar, Saurabh Arjun Sawant, Shreyas Verma, Swaroop Mishra, Ujjwala Anantheswaran","submitted_at":"2023-10-27T03:32:17Z","abstract_excerpt":"The rapid advancement of large language models (LLMs) has sparked interest in data synthesis techniques, aiming to generate diverse and high-quality synthetic datasets. However, these synthetic datasets often suffer from a lack of diversity and added noise. In this paper, we present TarGEN, a multi-step prompting strategy for generating high-quality synthetic datasets utilizing a LLM. An advantage of TarGEN is its seedless nature; it does not require specific task instances, broadening its applicability beyond task replication. We augment TarGEN with a method known as self-correction empowerin"},"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":"2310.17876","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T03:32:17Z","cross_cats_sorted":[],"title_canon_sha256":"7ebe6f48aa071bdce4284b6d2b4622309b28b634eba99be2db53442f60636eed","abstract_canon_sha256":"3b8d8559a0dc468d89ea7e55cf40b4cd187f787f95a8878af1113babe769c520"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:17.895238Z","signature_b64":"ursAdP3+yGvMR2PIpvKIQDji8E2TtueC3eRqVkcV/F4awYms6D3mH/ef6fwqPJAGC2QLLDP4lYi6sOgYJQojAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b83156e05b5037b19400ffb2a131d3a8f59979b18b206f99be63c96bdecaf51","last_reissued_at":"2026-07-05T08:53:17.894746Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:17.894746Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TarGEN: Targeted Data Generation with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chitta Baral, Himanshu Gupta, Kevin Scaria, Mihir Parmar, Saurabh Arjun Sawant, Shreyas Verma, Swaroop Mishra, Ujjwala Anantheswaran","submitted_at":"2023-10-27T03:32:17Z","abstract_excerpt":"The rapid advancement of large language models (LLMs) has sparked interest in data synthesis techniques, aiming to generate diverse and high-quality synthetic datasets. However, these synthetic datasets often suffer from a lack of diversity and added noise. In this paper, we present TarGEN, a multi-step prompting strategy for generating high-quality synthetic datasets utilizing a LLM. An advantage of TarGEN is its seedless nature; it does not require specific task instances, broadening its applicability beyond task replication. We augment TarGEN with a method known as self-correction empowerin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17876","kind":"arxiv","version":3},"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/2310.17876/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":"2310.17876","created_at":"2026-07-05T08:53:17.894805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.17876v3","created_at":"2026-07-05T08:53:17.894805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17876","created_at":"2026-07-05T08:53:17.894805+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROBRK3QFWUBX","created_at":"2026-07-05T08:53:17.894805+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROBRK3QFWUBXWGKA","created_at":"2026-07-05T08:53:17.894805+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROBRK3QF","created_at":"2026-07-05T08:53:17.894805+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27671","citing_title":"Evolving and Detecting Multi-Turn Deception using Geometric Signatures","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08472","citing_title":"Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROBRK3QFWUBXWGKAB75SUEY5HK","json":"https://pith.science/pith/ROBRK3QFWUBXWGKAB75SUEY5HK.json","graph_json":"https://pith.science/api/pith-number/ROBRK3QFWUBXWGKAB75SUEY5HK/graph.json","events_json":"https://pith.science/api/pith-number/ROBRK3QFWUBXWGKAB75SUEY5HK/events.json","paper":"https://pith.science/paper/ROBRK3QF"},"agent_actions":{"view_html":"https://pith.science/pith/ROBRK3QFWUBXWGKAB75SUEY5HK","download_json":"https://pith.science/pith/ROBRK3QFWUBXWGKAB75SUEY5HK.json","view_paper":"https://pith.science/paper/ROBRK3QF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.17876&json=true","fetch_graph":"https://pith.science/api/pith-number/ROBRK3QFWUBXWGKAB75SUEY5HK/graph.json","fetch_events":"https://pith.science/api/pith-number/ROBRK3QFWUBXWGKAB75SUEY5HK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROBRK3QFWUBXWGKAB75SUEY5HK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROBRK3QFWUBXWGKAB75SUEY5HK/action/storage_attestation","attest_author":"https://pith.science/pith/ROBRK3QFWUBXWGKAB75SUEY5HK/action/author_attestation","sign_citation":"https://pith.science/pith/ROBRK3QFWUBXWGKAB75SUEY5HK/action/citation_signature","submit_replication":"https://pith.science/pith/ROBRK3QFWUBXWGKAB75SUEY5HK/action/replication_record"}},"created_at":"2026-07-05T08:53:17.894805+00:00","updated_at":"2026-07-05T08:53:17.894805+00:00"}