{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V3ENEV6LGWAA7TQCPXODDCHBWN","short_pith_number":"pith:V3ENEV6L","schema_version":"1.0","canonical_sha256":"aec8d257cb35800fce027ddc3188e1b34cf95cb356037243d06e5a57be30d0a7","source":{"kind":"arxiv","id":"2410.18130","version":1},"attestation_state":"computed","paper":{"title":"Graph Contrastive Learning via Cluster-refined Negative Sampling for Semi-supervised Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Jianbin Li, Jiayi Du, Keqin Li, Tao Meng, Wei Ai, Yuntao Shou, Ze Wang","submitted_at":"2024-10-18T16:03:49Z","abstract_excerpt":"Graph contrastive learning (GCL) has been widely applied to text classification tasks due to its ability to generate self-supervised signals from unlabeled data, thus facilitating model training. However, existing GCL-based text classification methods often suffer from negative sampling bias, where similar nodes are incorrectly paired as negative pairs. This can lead to over-clustering, where instances of the same class are divided into different clusters. To address the over-clustering issue, we propose an innovative GCL-based method of graph contrastive learning via cluster-refined negative "},"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":"2410.18130","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-18T16:03:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"79348b7e3267e68ef16fb9c96d675e56b2212d3a62c4ea03e29423e327d3467c","abstract_canon_sha256":"8b5c05e25c38be3d3375f09741b36b6dcd42642e70eb53a33b1edeffb34d79d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:04.007119Z","signature_b64":"kruqDMy4VyIK70FPGqd6zp28ng69tLw63zQWStlgVNok+uRxK1LsdF5x8Wp2bUD8elFk0DzEzTozYDXAB/NbBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aec8d257cb35800fce027ddc3188e1b34cf95cb356037243d06e5a57be30d0a7","last_reissued_at":"2026-07-05T09:25:04.006569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:04.006569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Contrastive Learning via Cluster-refined Negative Sampling for Semi-supervised Text Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Jianbin Li, Jiayi Du, Keqin Li, Tao Meng, Wei Ai, Yuntao Shou, Ze Wang","submitted_at":"2024-10-18T16:03:49Z","abstract_excerpt":"Graph contrastive learning (GCL) has been widely applied to text classification tasks due to its ability to generate self-supervised signals from unlabeled data, thus facilitating model training. However, existing GCL-based text classification methods often suffer from negative sampling bias, where similar nodes are incorrectly paired as negative pairs. This can lead to over-clustering, where instances of the same class are divided into different clusters. To address the over-clustering issue, we propose an innovative GCL-based method of graph contrastive learning via cluster-refined negative "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18130","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/2410.18130/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":"2410.18130","created_at":"2026-07-05T09:25:04.006641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18130v1","created_at":"2026-07-05T09:25:04.006641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18130","created_at":"2026-07-05T09:25:04.006641+00:00"},{"alias_kind":"pith_short_12","alias_value":"V3ENEV6LGWAA","created_at":"2026-07-05T09:25:04.006641+00:00"},{"alias_kind":"pith_short_16","alias_value":"V3ENEV6LGWAA7TQC","created_at":"2026-07-05T09:25:04.006641+00:00"},{"alias_kind":"pith_short_8","alias_value":"V3ENEV6L","created_at":"2026-07-05T09:25:04.006641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11450","citing_title":"GroupFace: Imbalanced Age Estimation Based on Multi-hop Attention Graph Convolutional Network and Group-aware Margin Optimization","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V3ENEV6LGWAA7TQCPXODDCHBWN","json":"https://pith.science/pith/V3ENEV6LGWAA7TQCPXODDCHBWN.json","graph_json":"https://pith.science/api/pith-number/V3ENEV6LGWAA7TQCPXODDCHBWN/graph.json","events_json":"https://pith.science/api/pith-number/V3ENEV6LGWAA7TQCPXODDCHBWN/events.json","paper":"https://pith.science/paper/V3ENEV6L"},"agent_actions":{"view_html":"https://pith.science/pith/V3ENEV6LGWAA7TQCPXODDCHBWN","download_json":"https://pith.science/pith/V3ENEV6LGWAA7TQCPXODDCHBWN.json","view_paper":"https://pith.science/paper/V3ENEV6L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18130&json=true","fetch_graph":"https://pith.science/api/pith-number/V3ENEV6LGWAA7TQCPXODDCHBWN/graph.json","fetch_events":"https://pith.science/api/pith-number/V3ENEV6LGWAA7TQCPXODDCHBWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V3ENEV6LGWAA7TQCPXODDCHBWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V3ENEV6LGWAA7TQCPXODDCHBWN/action/storage_attestation","attest_author":"https://pith.science/pith/V3ENEV6LGWAA7TQCPXODDCHBWN/action/author_attestation","sign_citation":"https://pith.science/pith/V3ENEV6LGWAA7TQCPXODDCHBWN/action/citation_signature","submit_replication":"https://pith.science/pith/V3ENEV6LGWAA7TQCPXODDCHBWN/action/replication_record"}},"created_at":"2026-07-05T09:25:04.006641+00:00","updated_at":"2026-07-05T09:25:04.006641+00:00"}