{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:72PVXYT2BEAJ5A4GPPLYPNXBHC","short_pith_number":"pith:72PVXYT2","schema_version":"1.0","canonical_sha256":"fe9f5be27a09009e83867bd787b6e13899c64029651fac68d3fb5705ffe370af","source":{"kind":"arxiv","id":"2211.10890","version":4},"attestation_state":"computed","paper":{"title":"Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graph","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Haonan Wang, Jieyu Zhang, Kenji Kawaguchi, Qi Zhu, Wei Huang, Xiaokui Xiao","submitted_at":"2022-11-20T07:18:56Z","abstract_excerpt":"Existing graph contrastive learning (GCL) techniques typically require two forward passes for a single instance to construct the contrastive loss, which is effective for capturing the low-frequency signals of node features. Such a dual-pass design has shown empirical success on homophilic graphs, but its effectiveness on heterophilic graphs, where directly connected nodes typically have different labels, is unknown. In addition, existing GCL approaches fail to provide strong performance guarantees. Coupled with the unpredictability of GCL approaches on heterophilic graphs, their applicability "},"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":"2211.10890","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T07:18:56Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"b6c074200170835ca242998de20cc9364a2ed197456c8725bd973713ed11cfa8","abstract_canon_sha256":"10560afd691fea57a1260bd3afe8704e9ebb4cd873d417f63e885bfd1a1daa97"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:07.942310Z","signature_b64":"l72hHsg0vpXJGrF6ICkSn49r70kdFPOjm1vIIWyjfBj/WdU+XY/kmTTJ2kpVcpcn316Rg+psricagT9IWsu5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe9f5be27a09009e83867bd787b6e13899c64029651fac68d3fb5705ffe370af","last_reissued_at":"2026-07-05T07:14:07.941841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:07.941841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graph","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Haonan Wang, Jieyu Zhang, Kenji Kawaguchi, Qi Zhu, Wei Huang, Xiaokui Xiao","submitted_at":"2022-11-20T07:18:56Z","abstract_excerpt":"Existing graph contrastive learning (GCL) techniques typically require two forward passes for a single instance to construct the contrastive loss, which is effective for capturing the low-frequency signals of node features. Such a dual-pass design has shown empirical success on homophilic graphs, but its effectiveness on heterophilic graphs, where directly connected nodes typically have different labels, is unknown. In addition, existing GCL approaches fail to provide strong performance guarantees. Coupled with the unpredictability of GCL approaches on heterophilic graphs, their applicability "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.10890","kind":"arxiv","version":4},"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/2211.10890/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":"2211.10890","created_at":"2026-07-05T07:14:07.941898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.10890v4","created_at":"2026-07-05T07:14:07.941898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.10890","created_at":"2026-07-05T07:14:07.941898+00:00"},{"alias_kind":"pith_short_12","alias_value":"72PVXYT2BEAJ","created_at":"2026-07-05T07:14:07.941898+00:00"},{"alias_kind":"pith_short_16","alias_value":"72PVXYT2BEAJ5A4G","created_at":"2026-07-05T07:14:07.941898+00:00"},{"alias_kind":"pith_short_8","alias_value":"72PVXYT2","created_at":"2026-07-05T07:14:07.941898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11075","citing_title":"Edge Contrastive Learning: An Augmentation-Free Graph Contrastive Learning Model","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/72PVXYT2BEAJ5A4GPPLYPNXBHC","json":"https://pith.science/pith/72PVXYT2BEAJ5A4GPPLYPNXBHC.json","graph_json":"https://pith.science/api/pith-number/72PVXYT2BEAJ5A4GPPLYPNXBHC/graph.json","events_json":"https://pith.science/api/pith-number/72PVXYT2BEAJ5A4GPPLYPNXBHC/events.json","paper":"https://pith.science/paper/72PVXYT2"},"agent_actions":{"view_html":"https://pith.science/pith/72PVXYT2BEAJ5A4GPPLYPNXBHC","download_json":"https://pith.science/pith/72PVXYT2BEAJ5A4GPPLYPNXBHC.json","view_paper":"https://pith.science/paper/72PVXYT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.10890&json=true","fetch_graph":"https://pith.science/api/pith-number/72PVXYT2BEAJ5A4GPPLYPNXBHC/graph.json","fetch_events":"https://pith.science/api/pith-number/72PVXYT2BEAJ5A4GPPLYPNXBHC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72PVXYT2BEAJ5A4GPPLYPNXBHC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72PVXYT2BEAJ5A4GPPLYPNXBHC/action/storage_attestation","attest_author":"https://pith.science/pith/72PVXYT2BEAJ5A4GPPLYPNXBHC/action/author_attestation","sign_citation":"https://pith.science/pith/72PVXYT2BEAJ5A4GPPLYPNXBHC/action/citation_signature","submit_replication":"https://pith.science/pith/72PVXYT2BEAJ5A4GPPLYPNXBHC/action/replication_record"}},"created_at":"2026-07-05T07:14:07.941898+00:00","updated_at":"2026-07-05T07:14:07.941898+00:00"}