{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WFCUJDUQFF6O7ZVDXU64GIEREM","short_pith_number":"pith:WFCUJDUQ","schema_version":"1.0","canonical_sha256":"b145448e90297cefe6a3bd3dc320912317bbccc3f1cac9b5341700c420a5e36f","source":{"kind":"arxiv","id":"2307.16026","version":1},"attestation_state":"computed","paper":{"title":"MUSE: Multi-View Contrastive Learning for Heterophilic Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Mengyi Yuan, Minjie Chen, Xiang Li","submitted_at":"2023-07-29T16:54:34Z","abstract_excerpt":"In recent years, self-supervised learning has emerged as a promising approach in addressing the issues of label dependency and poor generalization performance in traditional GNNs. However, existing self-supervised methods have limited effectiveness on heterophilic graphs, due to the homophily assumption that results in similar node representations for connected nodes. In this work, we propose a multi-view contrastive learning model for heterophilic graphs, namely, MUSE. Specifically, we construct two views to capture the information of the ego node and its neighborhood by GNNs enhanced with co"},"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":"2307.16026","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-29T16:54:34Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"78023f70f2515225dd9e5c3d607dbd8e16698a844b4ace26ffa96ac4760306ca","abstract_canon_sha256":"2eff72d99614f3ccdcb58d01febfb5c307a730e19878a59881721eae08dd111a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:57.909760Z","signature_b64":"4bujF8rcrJb1oig1BeT5egNZjiez+bUvgv53nPgAPsV/hQhwbJZKoac+55hyHzXfwWILRO6m4ZHO6pV79pcxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b145448e90297cefe6a3bd3dc320912317bbccc3f1cac9b5341700c420a5e36f","last_reissued_at":"2026-07-05T06:35:57.909375Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:57.909375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MUSE: Multi-View Contrastive Learning for Heterophilic Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Mengyi Yuan, Minjie Chen, Xiang Li","submitted_at":"2023-07-29T16:54:34Z","abstract_excerpt":"In recent years, self-supervised learning has emerged as a promising approach in addressing the issues of label dependency and poor generalization performance in traditional GNNs. However, existing self-supervised methods have limited effectiveness on heterophilic graphs, due to the homophily assumption that results in similar node representations for connected nodes. In this work, we propose a multi-view contrastive learning model for heterophilic graphs, namely, MUSE. Specifically, we construct two views to capture the information of the ego node and its neighborhood by GNNs enhanced with co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.16026","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/2307.16026/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":"2307.16026","created_at":"2026-07-05T06:35:57.909428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.16026v1","created_at":"2026-07-05T06:35:57.909428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.16026","created_at":"2026-07-05T06:35:57.909428+00:00"},{"alias_kind":"pith_short_12","alias_value":"WFCUJDUQFF6O","created_at":"2026-07-05T06:35:57.909428+00:00"},{"alias_kind":"pith_short_16","alias_value":"WFCUJDUQFF6O7ZVD","created_at":"2026-07-05T06:35:57.909428+00:00"},{"alias_kind":"pith_short_8","alias_value":"WFCUJDUQ","created_at":"2026-07-05T06:35:57.909428+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/WFCUJDUQFF6O7ZVDXU64GIEREM","json":"https://pith.science/pith/WFCUJDUQFF6O7ZVDXU64GIEREM.json","graph_json":"https://pith.science/api/pith-number/WFCUJDUQFF6O7ZVDXU64GIEREM/graph.json","events_json":"https://pith.science/api/pith-number/WFCUJDUQFF6O7ZVDXU64GIEREM/events.json","paper":"https://pith.science/paper/WFCUJDUQ"},"agent_actions":{"view_html":"https://pith.science/pith/WFCUJDUQFF6O7ZVDXU64GIEREM","download_json":"https://pith.science/pith/WFCUJDUQFF6O7ZVDXU64GIEREM.json","view_paper":"https://pith.science/paper/WFCUJDUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.16026&json=true","fetch_graph":"https://pith.science/api/pith-number/WFCUJDUQFF6O7ZVDXU64GIEREM/graph.json","fetch_events":"https://pith.science/api/pith-number/WFCUJDUQFF6O7ZVDXU64GIEREM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WFCUJDUQFF6O7ZVDXU64GIEREM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WFCUJDUQFF6O7ZVDXU64GIEREM/action/storage_attestation","attest_author":"https://pith.science/pith/WFCUJDUQFF6O7ZVDXU64GIEREM/action/author_attestation","sign_citation":"https://pith.science/pith/WFCUJDUQFF6O7ZVDXU64GIEREM/action/citation_signature","submit_replication":"https://pith.science/pith/WFCUJDUQFF6O7ZVDXU64GIEREM/action/replication_record"}},"created_at":"2026-07-05T06:35:57.909428+00:00","updated_at":"2026-07-05T06:35:57.909428+00:00"}