{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5N4W4MS26TJD3PWDZI4B3YDGVC","short_pith_number":"pith:5N4W4MS2","schema_version":"1.0","canonical_sha256":"eb796e325af4d23dbec3ca381de066a88081facdfd8788bb1c874579d4b17927","source":{"kind":"arxiv","id":"2304.02806","version":2},"attestation_state":"computed","paper":{"title":"Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gaowen Liu, Haotao Wang, Jayanth Srinivasa, Ramana Rao Kompella, Yan Han, Yuning You, Zhangyang Wang, Ziyu Jiang","submitted_at":"2023-04-06T01:09:36Z","abstract_excerpt":"Graph neural networks (GNNs) have found extensive applications in learning from graph data. However, real-world graphs often possess diverse structures and comprise nodes and edges of varying types. To bolster the generalization capacity of GNNs, it has become customary to augment training graph structures through techniques like graph augmentations and large-scale pre-training on a wider array of graphs. Balancing this diversity while avoiding increased computational costs and the notorious trainability issues of GNNs is crucial. This study introduces the concept of Mixture-of-Experts (MoE) t"},"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":"2304.02806","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-06T01:09:36Z","cross_cats_sorted":[],"title_canon_sha256":"0e3a700a01f6a9f14accb196d291d5e374ed034f6616a70c39c7d9f32315c2c2","abstract_canon_sha256":"2a8014aef5e6399e436ae95b90f1b81c9aae19ce8a0d9df3328182b449d2f653"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:40.588453Z","signature_b64":"5ccmGZvcC2oL2d+5FRPUwECS8XtKRiNTVUawkfbsgJgooPLhbRfgAU8j6KyD231X8y206dLWNwwOYGMeeYICCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb796e325af4d23dbec3ca381de066a88081facdfd8788bb1c874579d4b17927","last_reissued_at":"2026-07-05T07:01:40.587895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:40.587895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gaowen Liu, Haotao Wang, Jayanth Srinivasa, Ramana Rao Kompella, Yan Han, Yuning You, Zhangyang Wang, Ziyu Jiang","submitted_at":"2023-04-06T01:09:36Z","abstract_excerpt":"Graph neural networks (GNNs) have found extensive applications in learning from graph data. However, real-world graphs often possess diverse structures and comprise nodes and edges of varying types. To bolster the generalization capacity of GNNs, it has become customary to augment training graph structures through techniques like graph augmentations and large-scale pre-training on a wider array of graphs. Balancing this diversity while avoiding increased computational costs and the notorious trainability issues of GNNs is crucial. This study introduces the concept of Mixture-of-Experts (MoE) t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02806","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/2304.02806/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":"2304.02806","created_at":"2026-07-05T07:01:40.587952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.02806v2","created_at":"2026-07-05T07:01:40.587952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02806","created_at":"2026-07-05T07:01:40.587952+00:00"},{"alias_kind":"pith_short_12","alias_value":"5N4W4MS26TJD","created_at":"2026-07-05T07:01:40.587952+00:00"},{"alias_kind":"pith_short_16","alias_value":"5N4W4MS26TJD3PWD","created_at":"2026-07-05T07:01:40.587952+00:00"},{"alias_kind":"pith_short_8","alias_value":"5N4W4MS2","created_at":"2026-07-05T07:01:40.587952+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21612","citing_title":"AdaptGOT: A Pre-trained Model for Adaptive Contextual POI Representation Learning","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5N4W4MS26TJD3PWDZI4B3YDGVC","json":"https://pith.science/pith/5N4W4MS26TJD3PWDZI4B3YDGVC.json","graph_json":"https://pith.science/api/pith-number/5N4W4MS26TJD3PWDZI4B3YDGVC/graph.json","events_json":"https://pith.science/api/pith-number/5N4W4MS26TJD3PWDZI4B3YDGVC/events.json","paper":"https://pith.science/paper/5N4W4MS2"},"agent_actions":{"view_html":"https://pith.science/pith/5N4W4MS26TJD3PWDZI4B3YDGVC","download_json":"https://pith.science/pith/5N4W4MS26TJD3PWDZI4B3YDGVC.json","view_paper":"https://pith.science/paper/5N4W4MS2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.02806&json=true","fetch_graph":"https://pith.science/api/pith-number/5N4W4MS26TJD3PWDZI4B3YDGVC/graph.json","fetch_events":"https://pith.science/api/pith-number/5N4W4MS26TJD3PWDZI4B3YDGVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5N4W4MS26TJD3PWDZI4B3YDGVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5N4W4MS26TJD3PWDZI4B3YDGVC/action/storage_attestation","attest_author":"https://pith.science/pith/5N4W4MS26TJD3PWDZI4B3YDGVC/action/author_attestation","sign_citation":"https://pith.science/pith/5N4W4MS26TJD3PWDZI4B3YDGVC/action/citation_signature","submit_replication":"https://pith.science/pith/5N4W4MS26TJD3PWDZI4B3YDGVC/action/replication_record"}},"created_at":"2026-07-05T07:01:40.587952+00:00","updated_at":"2026-07-05T07:01:40.587952+00:00"}