{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4G564OEMR7WTB6SENQ4PV3C4ZT","short_pith_number":"pith:4G564OEM","schema_version":"1.0","canonical_sha256":"e1bbee388c8fed30fa446c38faec5cccfa1a674c72f6b1e2f26f0473d0c6d078","source":{"kind":"arxiv","id":"2411.06175","version":3},"attestation_state":"computed","paper":{"title":"Clustering Algorithms and RAG Enhancing Semi-Supervised Text Classification with Large LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bohong Lin, Jiahao Zeng, Shan Zhong, Yongxin Yu","submitted_at":"2024-11-09T13:17:39Z","abstract_excerpt":"This paper proposes a Clustering, Labeling, then Augmenting framework that significantly enhances performance in Semi-Supervised Text Classification (SSTC) tasks, effectively addressing the challenge of vast datasets with limited labeled examples. Unlike traditional SSTC approaches that rely on a predefined small set of labeled data to generate pseudo-labels for the unlabeled data, this framework innovatively employs clustering to select representative \"landmarks\" for labeling. These landmarks subsequently act as intermediaries in an ensemble of augmentation techniques, including Retrieval-Aug"},"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":"2411.06175","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-09T13:17:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"69963563ecde1b0410411df19bb622d00969ffb4301c07c002e4eb678770a893","abstract_canon_sha256":"d2c72802b31fb536def237b7e57387d40cd0610bb4a77cd5c1a384436d7fa927"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:05.586101Z","signature_b64":"AjUYot08smZYcZ1yrsYTe4ZWFSHlMbht+JEptTM+vfQ5QhyxdoLAQjieFieU2HNDSv1ATg6ZwK27cLqnHGoxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1bbee388c8fed30fa446c38faec5cccfa1a674c72f6b1e2f26f0473d0c6d078","last_reissued_at":"2026-07-05T09:54:05.585595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:05.585595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clustering Algorithms and RAG Enhancing Semi-Supervised Text Classification with Large LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bohong Lin, Jiahao Zeng, Shan Zhong, Yongxin Yu","submitted_at":"2024-11-09T13:17:39Z","abstract_excerpt":"This paper proposes a Clustering, Labeling, then Augmenting framework that significantly enhances performance in Semi-Supervised Text Classification (SSTC) tasks, effectively addressing the challenge of vast datasets with limited labeled examples. Unlike traditional SSTC approaches that rely on a predefined small set of labeled data to generate pseudo-labels for the unlabeled data, this framework innovatively employs clustering to select representative \"landmarks\" for labeling. These landmarks subsequently act as intermediaries in an ensemble of augmentation techniques, including Retrieval-Aug"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.06175","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/2411.06175/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":"2411.06175","created_at":"2026-07-05T09:54:05.585656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.06175v3","created_at":"2026-07-05T09:54:05.585656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.06175","created_at":"2026-07-05T09:54:05.585656+00:00"},{"alias_kind":"pith_short_12","alias_value":"4G564OEMR7WT","created_at":"2026-07-05T09:54:05.585656+00:00"},{"alias_kind":"pith_short_16","alias_value":"4G564OEMR7WTB6SE","created_at":"2026-07-05T09:54:05.585656+00:00"},{"alias_kind":"pith_short_8","alias_value":"4G564OEM","created_at":"2026-07-05T09:54:05.585656+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/4G564OEMR7WTB6SENQ4PV3C4ZT","json":"https://pith.science/pith/4G564OEMR7WTB6SENQ4PV3C4ZT.json","graph_json":"https://pith.science/api/pith-number/4G564OEMR7WTB6SENQ4PV3C4ZT/graph.json","events_json":"https://pith.science/api/pith-number/4G564OEMR7WTB6SENQ4PV3C4ZT/events.json","paper":"https://pith.science/paper/4G564OEM"},"agent_actions":{"view_html":"https://pith.science/pith/4G564OEMR7WTB6SENQ4PV3C4ZT","download_json":"https://pith.science/pith/4G564OEMR7WTB6SENQ4PV3C4ZT.json","view_paper":"https://pith.science/paper/4G564OEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.06175&json=true","fetch_graph":"https://pith.science/api/pith-number/4G564OEMR7WTB6SENQ4PV3C4ZT/graph.json","fetch_events":"https://pith.science/api/pith-number/4G564OEMR7WTB6SENQ4PV3C4ZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4G564OEMR7WTB6SENQ4PV3C4ZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4G564OEMR7WTB6SENQ4PV3C4ZT/action/storage_attestation","attest_author":"https://pith.science/pith/4G564OEMR7WTB6SENQ4PV3C4ZT/action/author_attestation","sign_citation":"https://pith.science/pith/4G564OEMR7WTB6SENQ4PV3C4ZT/action/citation_signature","submit_replication":"https://pith.science/pith/4G564OEMR7WTB6SENQ4PV3C4ZT/action/replication_record"}},"created_at":"2026-07-05T09:54:05.585656+00:00","updated_at":"2026-07-05T09:54:05.585656+00:00"}