{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LWBJD3ZCDS5CWNKGJGCH4IO4JW","short_pith_number":"pith:LWBJD3ZC","schema_version":"1.0","canonical_sha256":"5d8291ef221cba2b354649847e21dc4d884e82f13d416adf7a3f9fa2ab8067b8","source":{"kind":"arxiv","id":"2402.07470","version":2},"attestation_state":"computed","paper":{"title":"Pushing The Limit of LLM Capacity for Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Chenyu Ren, Jing Qin, Mengyao Wang, Prayag Tiwari, Qiuchi Li, Yazhou Zhang","submitted_at":"2024-02-12T08:14:03Z","abstract_excerpt":"The value of text classification's future research has encountered challenges and uncertainties, due to the extraordinary efficacy demonstrated by large language models (LLMs) across numerous downstream NLP tasks. In this era of open-ended language modeling, where task boundaries are gradually fading, an urgent question emerges: have we made significant advances in text classification under the full benefit of LLMs? To answer this question, we propose RGPT, an adaptive boosting framework tailored to produce a specialized text classification LLM by recurrently ensembling a pool of strong base l"},"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":"2402.07470","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T08:14:03Z","cross_cats_sorted":[],"title_canon_sha256":"b37854a9c11bcc7537824de2a00d31c167fd9afdf1426fc8bb2150631fcfca6f","abstract_canon_sha256":"bcbb2b1015caffacb4fdd320eb5a0da0041e9aaa4093e045dbb6997881eb69bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:52.439793Z","signature_b64":"JCqJReelzQsG35lZVgJ9Qyt6jjwKQ0gvB5snv5/uYECJJ+nmz85XGbGvXXntiZO5qAADLfPgmh2RMXJDm+S1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d8291ef221cba2b354649847e21dc4d884e82f13d416adf7a3f9fa2ab8067b8","last_reissued_at":"2026-07-05T07:45:52.439359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:52.439359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pushing The Limit of LLM Capacity for Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Chenyu Ren, Jing Qin, Mengyao Wang, Prayag Tiwari, Qiuchi Li, Yazhou Zhang","submitted_at":"2024-02-12T08:14:03Z","abstract_excerpt":"The value of text classification's future research has encountered challenges and uncertainties, due to the extraordinary efficacy demonstrated by large language models (LLMs) across numerous downstream NLP tasks. In this era of open-ended language modeling, where task boundaries are gradually fading, an urgent question emerges: have we made significant advances in text classification under the full benefit of LLMs? To answer this question, we propose RGPT, an adaptive boosting framework tailored to produce a specialized text classification LLM by recurrently ensembling a pool of strong base l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07470","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/2402.07470/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":"2402.07470","created_at":"2026-07-05T07:45:52.439417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07470v2","created_at":"2026-07-05T07:45:52.439417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07470","created_at":"2026-07-05T07:45:52.439417+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWBJD3ZCDS5C","created_at":"2026-07-05T07:45:52.439417+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWBJD3ZCDS5CWNKG","created_at":"2026-07-05T07:45:52.439417+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWBJD3ZC","created_at":"2026-07-05T07:45:52.439417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.05929","citing_title":"Towards Reliable Generative AI-Driven Scaffolding: Reducing Hallucinations and Enhancing Quality in Self-Regulated Learning Support","ref_index":101,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWBJD3ZCDS5CWNKGJGCH4IO4JW","json":"https://pith.science/pith/LWBJD3ZCDS5CWNKGJGCH4IO4JW.json","graph_json":"https://pith.science/api/pith-number/LWBJD3ZCDS5CWNKGJGCH4IO4JW/graph.json","events_json":"https://pith.science/api/pith-number/LWBJD3ZCDS5CWNKGJGCH4IO4JW/events.json","paper":"https://pith.science/paper/LWBJD3ZC"},"agent_actions":{"view_html":"https://pith.science/pith/LWBJD3ZCDS5CWNKGJGCH4IO4JW","download_json":"https://pith.science/pith/LWBJD3ZCDS5CWNKGJGCH4IO4JW.json","view_paper":"https://pith.science/paper/LWBJD3ZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07470&json=true","fetch_graph":"https://pith.science/api/pith-number/LWBJD3ZCDS5CWNKGJGCH4IO4JW/graph.json","fetch_events":"https://pith.science/api/pith-number/LWBJD3ZCDS5CWNKGJGCH4IO4JW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWBJD3ZCDS5CWNKGJGCH4IO4JW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWBJD3ZCDS5CWNKGJGCH4IO4JW/action/storage_attestation","attest_author":"https://pith.science/pith/LWBJD3ZCDS5CWNKGJGCH4IO4JW/action/author_attestation","sign_citation":"https://pith.science/pith/LWBJD3ZCDS5CWNKGJGCH4IO4JW/action/citation_signature","submit_replication":"https://pith.science/pith/LWBJD3ZCDS5CWNKGJGCH4IO4JW/action/replication_record"}},"created_at":"2026-07-05T07:45:52.439417+00:00","updated_at":"2026-07-05T07:45:52.439417+00:00"}