{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YFNKV2TJHY4Z6ZNSXVRHQJMZUR","short_pith_number":"pith:YFNKV2TJ","schema_version":"1.0","canonical_sha256":"c15aaaea693e399f65b2bd62782599a46d9906c17091a2d539bbf439492fd923","source":{"kind":"arxiv","id":"2505.15103","version":2},"attestation_state":"computed","paper":{"title":"Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Boxun Xu, Hejia Geng, Peng Li, Zihu Wang","submitted_at":"2025-05-21T04:54:18Z","abstract_excerpt":"Graph contrastive learning (GCL) has demonstrated great promise for learning generalizable graph representations from unlabeled data. However, conventional GCL approaches face two critical limitations: (1) the restricted expressive capacity of multilayer perceptron (MLP) based encoders, and (2) suboptimal negative samples that either from random augmentations-failing to provide effective 'hard negatives'-or generated hard negatives without addressing the semantic distinctions crucial for discriminating graph data. To this end, we propose Khan-GCL, a novel framework that integrates the Kolmogor"},"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":"2505.15103","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-21T04:54:18Z","cross_cats_sorted":[],"title_canon_sha256":"ade8dccb89b2548c787dbfc2563aa8b7427e273970586fe23a40b906e4e0dc12","abstract_canon_sha256":"0108c6d11110a3e531c5b1fd75f9777f14ade69d91f6766903dae1ddf2a722f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:36.854749Z","signature_b64":"pJf332frCxhG5obnx4Ai18O9n3iBWUox3u8d5svE7eeaEyfMY6+JPHYbCZTkdS6I9X4hLbiytFBJDnqLBEF6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c15aaaea693e399f65b2bd62782599a46d9906c17091a2d539bbf439492fd923","last_reissued_at":"2026-07-05T11:50:36.854254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:36.854254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Khan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Boxun Xu, Hejia Geng, Peng Li, Zihu Wang","submitted_at":"2025-05-21T04:54:18Z","abstract_excerpt":"Graph contrastive learning (GCL) has demonstrated great promise for learning generalizable graph representations from unlabeled data. However, conventional GCL approaches face two critical limitations: (1) the restricted expressive capacity of multilayer perceptron (MLP) based encoders, and (2) suboptimal negative samples that either from random augmentations-failing to provide effective 'hard negatives'-or generated hard negatives without addressing the semantic distinctions crucial for discriminating graph data. To this end, we propose Khan-GCL, a novel framework that integrates the Kolmogor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15103","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/2505.15103/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":"2505.15103","created_at":"2026-07-05T11:50:36.854321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.15103v2","created_at":"2026-07-05T11:50:36.854321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15103","created_at":"2026-07-05T11:50:36.854321+00:00"},{"alias_kind":"pith_short_12","alias_value":"YFNKV2TJHY4Z","created_at":"2026-07-05T11:50:36.854321+00:00"},{"alias_kind":"pith_short_16","alias_value":"YFNKV2TJHY4Z6ZNS","created_at":"2026-07-05T11:50:36.854321+00:00"},{"alias_kind":"pith_short_8","alias_value":"YFNKV2TJ","created_at":"2026-07-05T11:50:36.854321+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/YFNKV2TJHY4Z6ZNSXVRHQJMZUR","json":"https://pith.science/pith/YFNKV2TJHY4Z6ZNSXVRHQJMZUR.json","graph_json":"https://pith.science/api/pith-number/YFNKV2TJHY4Z6ZNSXVRHQJMZUR/graph.json","events_json":"https://pith.science/api/pith-number/YFNKV2TJHY4Z6ZNSXVRHQJMZUR/events.json","paper":"https://pith.science/paper/YFNKV2TJ"},"agent_actions":{"view_html":"https://pith.science/pith/YFNKV2TJHY4Z6ZNSXVRHQJMZUR","download_json":"https://pith.science/pith/YFNKV2TJHY4Z6ZNSXVRHQJMZUR.json","view_paper":"https://pith.science/paper/YFNKV2TJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.15103&json=true","fetch_graph":"https://pith.science/api/pith-number/YFNKV2TJHY4Z6ZNSXVRHQJMZUR/graph.json","fetch_events":"https://pith.science/api/pith-number/YFNKV2TJHY4Z6ZNSXVRHQJMZUR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YFNKV2TJHY4Z6ZNSXVRHQJMZUR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YFNKV2TJHY4Z6ZNSXVRHQJMZUR/action/storage_attestation","attest_author":"https://pith.science/pith/YFNKV2TJHY4Z6ZNSXVRHQJMZUR/action/author_attestation","sign_citation":"https://pith.science/pith/YFNKV2TJHY4Z6ZNSXVRHQJMZUR/action/citation_signature","submit_replication":"https://pith.science/pith/YFNKV2TJHY4Z6ZNSXVRHQJMZUR/action/replication_record"}},"created_at":"2026-07-05T11:50:36.854321+00:00","updated_at":"2026-07-05T11:50:36.854321+00:00"}