{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MO2KZYA5UZ6FWEE32ZI4PGZQKG","short_pith_number":"pith:MO2KZYA5","schema_version":"1.0","canonical_sha256":"63b4ace01da67c5b109bd651c79b3051bff57d09219ed923e814d3b919a6f55a","source":{"kind":"arxiv","id":"2403.12173","version":1},"attestation_state":"computed","paper":{"title":"TnT-LLM: Text Mining at Scale with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chirag Shah, Dhruv Joshi, Georg Buscher, Jennifer Neville, Longqi Yang, Mengting Wan, Nagu Rangan, Reid Andersen, Ryen W White, Scott Counts, Siddharth Suri, Sujay Kumar Jauhar, Tara Safavi, Yujin Kim","submitted_at":"2024-03-18T18:45:28Z","abstract_excerpt":"Transforming unstructured text into structured and meaningful forms, organized by useful category labels, is a fundamental step in text mining for downstream analysis and application. However, most existing methods for producing label taxonomies and building text-based label classifiers still rely heavily on domain expertise and manual curation, making the process expensive and time-consuming. This is particularly challenging when the label space is under-specified and large-scale data annotations are unavailable. In this paper, we address these challenges with Large Language Models (LLMs), wh"},"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":"2403.12173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T18:45:28Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"2439037bdf5f40a4fd539f8b0d84fae8d0a417a9d248d9e5fe7d87524ac01942","abstract_canon_sha256":"58af4894e638776dda687f063186bbffd73c9fa8569a7cab6cffdc817fad5afc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:56.627966Z","signature_b64":"8iocgiVP7xUErN1R2XGFGpE0ZV3IeVbGvxDzjJojU7+tbIqG4pMut45AdYkcDbfzd2yy8bxdE8sXaaEBz9RPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63b4ace01da67c5b109bd651c79b3051bff57d09219ed923e814d3b919a6f55a","last_reissued_at":"2026-07-05T07:57:56.627341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:56.627341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TnT-LLM: Text Mining at Scale with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chirag Shah, Dhruv Joshi, Georg Buscher, Jennifer Neville, Longqi Yang, Mengting Wan, Nagu Rangan, Reid Andersen, Ryen W White, Scott Counts, Siddharth Suri, Sujay Kumar Jauhar, Tara Safavi, Yujin Kim","submitted_at":"2024-03-18T18:45:28Z","abstract_excerpt":"Transforming unstructured text into structured and meaningful forms, organized by useful category labels, is a fundamental step in text mining for downstream analysis and application. However, most existing methods for producing label taxonomies and building text-based label classifiers still rely heavily on domain expertise and manual curation, making the process expensive and time-consuming. This is particularly challenging when the label space is under-specified and large-scale data annotations are unavailable. In this paper, we address these challenges with Large Language Models (LLMs), wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.12173","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/2403.12173/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":"2403.12173","created_at":"2026-07-05T07:57:56.627408+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.12173v1","created_at":"2026-07-05T07:57:56.627408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.12173","created_at":"2026-07-05T07:57:56.627408+00:00"},{"alias_kind":"pith_short_12","alias_value":"MO2KZYA5UZ6F","created_at":"2026-07-05T07:57:56.627408+00:00"},{"alias_kind":"pith_short_16","alias_value":"MO2KZYA5UZ6FWEE3","created_at":"2026-07-05T07:57:56.627408+00:00"},{"alias_kind":"pith_short_8","alias_value":"MO2KZYA5","created_at":"2026-07-05T07:57:56.627408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07293","citing_title":"Thermodynamic Prediction Enabled by Automatic Dataset Building and Machine Learning","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MO2KZYA5UZ6FWEE32ZI4PGZQKG","json":"https://pith.science/pith/MO2KZYA5UZ6FWEE32ZI4PGZQKG.json","graph_json":"https://pith.science/api/pith-number/MO2KZYA5UZ6FWEE32ZI4PGZQKG/graph.json","events_json":"https://pith.science/api/pith-number/MO2KZYA5UZ6FWEE32ZI4PGZQKG/events.json","paper":"https://pith.science/paper/MO2KZYA5"},"agent_actions":{"view_html":"https://pith.science/pith/MO2KZYA5UZ6FWEE32ZI4PGZQKG","download_json":"https://pith.science/pith/MO2KZYA5UZ6FWEE32ZI4PGZQKG.json","view_paper":"https://pith.science/paper/MO2KZYA5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.12173&json=true","fetch_graph":"https://pith.science/api/pith-number/MO2KZYA5UZ6FWEE32ZI4PGZQKG/graph.json","fetch_events":"https://pith.science/api/pith-number/MO2KZYA5UZ6FWEE32ZI4PGZQKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MO2KZYA5UZ6FWEE32ZI4PGZQKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MO2KZYA5UZ6FWEE32ZI4PGZQKG/action/storage_attestation","attest_author":"https://pith.science/pith/MO2KZYA5UZ6FWEE32ZI4PGZQKG/action/author_attestation","sign_citation":"https://pith.science/pith/MO2KZYA5UZ6FWEE32ZI4PGZQKG/action/citation_signature","submit_replication":"https://pith.science/pith/MO2KZYA5UZ6FWEE32ZI4PGZQKG/action/replication_record"}},"created_at":"2026-07-05T07:57:56.627408+00:00","updated_at":"2026-07-05T07:57:56.627408+00:00"}