{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZT6AGLEYTYEWGNPW35G46KXD7W","short_pith_number":"pith:ZT6AGLEY","schema_version":"1.0","canonical_sha256":"ccfc032c989e096335f6df4dcf2ae3fd9db889fc4330b3ce69b76b4852206c37","source":{"kind":"arxiv","id":"2506.05214","version":1},"attestation_state":"computed","paper":{"title":"Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hongbo Bo, Jingyu Hu, Jun Hong, Weiru Liu, Xiaowei Liu","submitted_at":"2025-06-05T16:28:12Z","abstract_excerpt":"Graph Neural Networks (GNNs) often suffer from degree bias in node classification tasks, where prediction performance varies across nodes with different degrees. Several approaches, which adopt Graph Contrastive Learning (GCL), have been proposed to mitigate this bias. However, the limited number of positive pairs and the equal weighting of all positives and negatives in GCL still lead to low-degree nodes acquiring insufficient and noisy information. This paper proposes the Hardness Adaptive Reweighted (HAR) contrastive loss to mitigate degree bias. It adds more positive pairs by leveraging no"},"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":"2506.05214","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-05T16:28:12Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"b7f63e18b49ad5c01b7118b79ec98816e9dfdacac5d73325812e9614c15babbf","abstract_canon_sha256":"88324281ad0c0cf0656e034ff79331dde0bdb5b8627f3c1493401d29c18bafcc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:44.237517Z","signature_b64":"2C8qmPHOvRDwR92N+kd35xGxBFaCoORqANZj3m7J62KRJVM5KsQQUM5QPh1SjmW6aHV33ySmRNRjvG3l94GIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccfc032c989e096335f6df4dcf2ae3fd9db889fc4330b3ce69b76b4852206c37","last_reissued_at":"2026-07-05T11:16:44.236990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:44.236990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hongbo Bo, Jingyu Hu, Jun Hong, Weiru Liu, Xiaowei Liu","submitted_at":"2025-06-05T16:28:12Z","abstract_excerpt":"Graph Neural Networks (GNNs) often suffer from degree bias in node classification tasks, where prediction performance varies across nodes with different degrees. Several approaches, which adopt Graph Contrastive Learning (GCL), have been proposed to mitigate this bias. However, the limited number of positive pairs and the equal weighting of all positives and negatives in GCL still lead to low-degree nodes acquiring insufficient and noisy information. This paper proposes the Hardness Adaptive Reweighted (HAR) contrastive loss to mitigate degree bias. It adds more positive pairs by leveraging no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05214","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/2506.05214/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":"2506.05214","created_at":"2026-07-05T11:16:44.237059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05214v1","created_at":"2026-07-05T11:16:44.237059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05214","created_at":"2026-07-05T11:16:44.237059+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZT6AGLEYTYEW","created_at":"2026-07-05T11:16:44.237059+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZT6AGLEYTYEWGNPW","created_at":"2026-07-05T11:16:44.237059+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZT6AGLEY","created_at":"2026-07-05T11:16:44.237059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23744","citing_title":"Contrast to Detect: Dynamic Graph Contrastive Regularization for Unsupervised Anomaly Detection in Multivariate Time Series","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZT6AGLEYTYEWGNPW35G46KXD7W","json":"https://pith.science/pith/ZT6AGLEYTYEWGNPW35G46KXD7W.json","graph_json":"https://pith.science/api/pith-number/ZT6AGLEYTYEWGNPW35G46KXD7W/graph.json","events_json":"https://pith.science/api/pith-number/ZT6AGLEYTYEWGNPW35G46KXD7W/events.json","paper":"https://pith.science/paper/ZT6AGLEY"},"agent_actions":{"view_html":"https://pith.science/pith/ZT6AGLEYTYEWGNPW35G46KXD7W","download_json":"https://pith.science/pith/ZT6AGLEYTYEWGNPW35G46KXD7W.json","view_paper":"https://pith.science/paper/ZT6AGLEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05214&json=true","fetch_graph":"https://pith.science/api/pith-number/ZT6AGLEYTYEWGNPW35G46KXD7W/graph.json","fetch_events":"https://pith.science/api/pith-number/ZT6AGLEYTYEWGNPW35G46KXD7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZT6AGLEYTYEWGNPW35G46KXD7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZT6AGLEYTYEWGNPW35G46KXD7W/action/storage_attestation","attest_author":"https://pith.science/pith/ZT6AGLEYTYEWGNPW35G46KXD7W/action/author_attestation","sign_citation":"https://pith.science/pith/ZT6AGLEYTYEWGNPW35G46KXD7W/action/citation_signature","submit_replication":"https://pith.science/pith/ZT6AGLEYTYEWGNPW35G46KXD7W/action/replication_record"}},"created_at":"2026-07-05T11:16:44.237059+00:00","updated_at":"2026-07-05T11:16:44.237059+00:00"}