{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J4FOVRYNY3X7VV53XB3KC7CK4U","short_pith_number":"pith:J4FOVRYN","schema_version":"1.0","canonical_sha256":"4f0aeac70dc6effad7bbb876a17c4ae5036f034d3dd19025780d05a41c7795fc","source":{"kind":"arxiv","id":"2304.12228","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Contrastive Learning Enhanced Heterogeneous Graph Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuan Shi, Hui Han, Nian Liu, Xiao Wang","submitted_at":"2023-04-24T16:17:21Z","abstract_excerpt":"Heterogeneous graph neural networks (HGNNs) as an emerging technique have shown superior capacity of dealing with heterogeneous information network (HIN). However, most HGNNs follow a semi-supervised learning manner, which notably limits their wide use in reality since labels are usually scarce in real applications. Recently, contrastive learning, a self-supervised method, becomes one of the most exciting learning paradigms and shows great potential when there are no labels. In this paper, we study the problem of self-supervised HGNNs and propose a novel co-contrastive learning mechanism for H"},"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":"2304.12228","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-24T16:17:21Z","cross_cats_sorted":[],"title_canon_sha256":"7c6bd85b98d70a0bdd0fc662706706cc3bdf97b126432037c79e97c6d18e65b4","abstract_canon_sha256":"f8ae0445cd255ae0a60a671c503fc306e946c61346f345b1810f9e7fa494ad5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:09.539982Z","signature_b64":"p5+vnbSm+D54Y2Uk2Imqki25wYkEwEiBruMmyj7qZfcJSCVbkN5J+/UB/qVU+e7OWxWhOh+CLeJt4AkiddxPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f0aeac70dc6effad7bbb876a17c4ae5036f034d3dd19025780d05a41c7795fc","last_reissued_at":"2026-07-05T07:52:09.539481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:09.539481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Contrastive Learning Enhanced Heterogeneous Graph Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuan Shi, Hui Han, Nian Liu, Xiao Wang","submitted_at":"2023-04-24T16:17:21Z","abstract_excerpt":"Heterogeneous graph neural networks (HGNNs) as an emerging technique have shown superior capacity of dealing with heterogeneous information network (HIN). However, most HGNNs follow a semi-supervised learning manner, which notably limits their wide use in reality since labels are usually scarce in real applications. Recently, contrastive learning, a self-supervised method, becomes one of the most exciting learning paradigms and shows great potential when there are no labels. In this paper, we study the problem of self-supervised HGNNs and propose a novel co-contrastive learning mechanism for H"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12228","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/2304.12228/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":"2304.12228","created_at":"2026-07-05T07:52:09.539549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.12228v2","created_at":"2026-07-05T07:52:09.539549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12228","created_at":"2026-07-05T07:52:09.539549+00:00"},{"alias_kind":"pith_short_12","alias_value":"J4FOVRYNY3X7","created_at":"2026-07-05T07:52:09.539549+00:00"},{"alias_kind":"pith_short_16","alias_value":"J4FOVRYNY3X7VV53","created_at":"2026-07-05T07:52:09.539549+00:00"},{"alias_kind":"pith_short_8","alias_value":"J4FOVRYN","created_at":"2026-07-05T07:52:09.539549+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/J4FOVRYNY3X7VV53XB3KC7CK4U","json":"https://pith.science/pith/J4FOVRYNY3X7VV53XB3KC7CK4U.json","graph_json":"https://pith.science/api/pith-number/J4FOVRYNY3X7VV53XB3KC7CK4U/graph.json","events_json":"https://pith.science/api/pith-number/J4FOVRYNY3X7VV53XB3KC7CK4U/events.json","paper":"https://pith.science/paper/J4FOVRYN"},"agent_actions":{"view_html":"https://pith.science/pith/J4FOVRYNY3X7VV53XB3KC7CK4U","download_json":"https://pith.science/pith/J4FOVRYNY3X7VV53XB3KC7CK4U.json","view_paper":"https://pith.science/paper/J4FOVRYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.12228&json=true","fetch_graph":"https://pith.science/api/pith-number/J4FOVRYNY3X7VV53XB3KC7CK4U/graph.json","fetch_events":"https://pith.science/api/pith-number/J4FOVRYNY3X7VV53XB3KC7CK4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J4FOVRYNY3X7VV53XB3KC7CK4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J4FOVRYNY3X7VV53XB3KC7CK4U/action/storage_attestation","attest_author":"https://pith.science/pith/J4FOVRYNY3X7VV53XB3KC7CK4U/action/author_attestation","sign_citation":"https://pith.science/pith/J4FOVRYNY3X7VV53XB3KC7CK4U/action/citation_signature","submit_replication":"https://pith.science/pith/J4FOVRYNY3X7VV53XB3KC7CK4U/action/replication_record"}},"created_at":"2026-07-05T07:52:09.539549+00:00","updated_at":"2026-07-05T07:52:09.539549+00:00"}