{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IAYDZSPFMESVKKM4PWTNZLZZCJ","short_pith_number":"pith:IAYDZSPF","schema_version":"1.0","canonical_sha256":"40303cc9e5612555299c7da6dcaf391256147c45e8381974ddcc1059567679ab","source":{"kind":"arxiv","id":"2112.14936","version":1},"attestation_state":"computed","paper":{"title":"Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Chang Zhou, Jianguo Jiang, Jie Tang, Ming Ding, Qiang Liu, Qingsong Lv, Siming He, Wenzheng Feng, Yuxiang Chen, Yuxiao Dong","submitted_at":"2021-12-30T06:29:21Z","abstract_excerpt":"Heterogeneous graph neural networks (HGNNs) have been blossoming in recent years, but the unique data processing and evaluation setups used by each work obstruct a full understanding of their advancements. In this work, we present a systematical reproduction of 12 recent HGNNs by using their official codes, datasets, settings, and hyperparameters, revealing surprising findings about the progress of HGNNs. We find that the simple homogeneous GNNs, e.g., GCN and GAT, are largely underestimated due to improper settings. GAT with proper inputs can generally match or outperform all existing HGNNs a"},"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":"2112.14936","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-30T06:29:21Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"10729cb9b1eaccb66d506dce7fbafaca161f0f3698b0edd87b5ea77c08f72aec","abstract_canon_sha256":"59d88bf04dbe7792ba48e088a73e319ae853588b9125f3dd56cf143d088c6fd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:34.987469Z","signature_b64":"SvT5ipQwzDTXr5g7dMs+JC0KMK33R+9hl75deK+wrxE9MQpxQq/ftgpfgdG5lCwXU9Cn+CgbSllZZya/yx+SBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40303cc9e5612555299c7da6dcaf391256147c45e8381974ddcc1059567679ab","last_reissued_at":"2026-07-05T03:44:34.986628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:34.986628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Chang Zhou, Jianguo Jiang, Jie Tang, Ming Ding, Qiang Liu, Qingsong Lv, Siming He, Wenzheng Feng, Yuxiang Chen, Yuxiao Dong","submitted_at":"2021-12-30T06:29:21Z","abstract_excerpt":"Heterogeneous graph neural networks (HGNNs) have been blossoming in recent years, but the unique data processing and evaluation setups used by each work obstruct a full understanding of their advancements. In this work, we present a systematical reproduction of 12 recent HGNNs by using their official codes, datasets, settings, and hyperparameters, revealing surprising findings about the progress of HGNNs. We find that the simple homogeneous GNNs, e.g., GCN and GAT, are largely underestimated due to improper settings. GAT with proper inputs can generally match or outperform all existing HGNNs a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.14936","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/2112.14936/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":"2112.14936","created_at":"2026-07-05T03:44:34.986945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.14936v1","created_at":"2026-07-05T03:44:34.986945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.14936","created_at":"2026-07-05T03:44:34.986945+00:00"},{"alias_kind":"pith_short_12","alias_value":"IAYDZSPFMESV","created_at":"2026-07-05T03:44:34.986945+00:00"},{"alias_kind":"pith_short_16","alias_value":"IAYDZSPFMESVKKM4","created_at":"2026-07-05T03:44:34.986945+00:00"},{"alias_kind":"pith_short_8","alias_value":"IAYDZSPF","created_at":"2026-07-05T03:44:34.986945+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/IAYDZSPFMESVKKM4PWTNZLZZCJ","json":"https://pith.science/pith/IAYDZSPFMESVKKM4PWTNZLZZCJ.json","graph_json":"https://pith.science/api/pith-number/IAYDZSPFMESVKKM4PWTNZLZZCJ/graph.json","events_json":"https://pith.science/api/pith-number/IAYDZSPFMESVKKM4PWTNZLZZCJ/events.json","paper":"https://pith.science/paper/IAYDZSPF"},"agent_actions":{"view_html":"https://pith.science/pith/IAYDZSPFMESVKKM4PWTNZLZZCJ","download_json":"https://pith.science/pith/IAYDZSPFMESVKKM4PWTNZLZZCJ.json","view_paper":"https://pith.science/paper/IAYDZSPF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.14936&json=true","fetch_graph":"https://pith.science/api/pith-number/IAYDZSPFMESVKKM4PWTNZLZZCJ/graph.json","fetch_events":"https://pith.science/api/pith-number/IAYDZSPFMESVKKM4PWTNZLZZCJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IAYDZSPFMESVKKM4PWTNZLZZCJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IAYDZSPFMESVKKM4PWTNZLZZCJ/action/storage_attestation","attest_author":"https://pith.science/pith/IAYDZSPFMESVKKM4PWTNZLZZCJ/action/author_attestation","sign_citation":"https://pith.science/pith/IAYDZSPFMESVKKM4PWTNZLZZCJ/action/citation_signature","submit_replication":"https://pith.science/pith/IAYDZSPFMESVKKM4PWTNZLZZCJ/action/replication_record"}},"created_at":"2026-07-05T03:44:34.986945+00:00","updated_at":"2026-07-05T03:44:34.986945+00:00"}