{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:36K4PWKHHW6HCJQTFTOIT3RUGN","short_pith_number":"pith:36K4PWKH","schema_version":"1.0","canonical_sha256":"df95c7d9473dbc7126132cdc89ee34336285818dbc31a72fb5cee90daba1111a","source":{"kind":"arxiv","id":"2310.18735","version":1},"attestation_state":"computed","paper":{"title":"Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junxiang Wang, Liang Zhao, Zheng Zhang","submitted_at":"2023-10-28T15:35:34Z","abstract_excerpt":"Graph Neural Networks (GNNs) have achieved great success in representing data with dependencies by recursively propagating and aggregating messages along the edges. However, edges in real-world graphs often have varying degrees of difficulty, and some edges may even be noisy to the downstream tasks. Therefore, existing GNNs may lead to suboptimal learned representations because they usually treat every edge in the graph equally. On the other hand, Curriculum Learning (CL), which mimics the human learning principle of learning data samples in a meaningful order, has been shown to be effective i"},"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":"2310.18735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-28T15:35:34Z","cross_cats_sorted":[],"title_canon_sha256":"865c3268604099339e4b48a41b946b435f0826d530c5009a6f8a47ebb3f9f8fe","abstract_canon_sha256":"fd803f4dd7478e7a57b1d8b57ddb998adfb43a5a4ea170ae5a1d0a54720d28b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:40.273711Z","signature_b64":"z6cXlstazdO29guAQ0baGeXMo42CqLM80edgaRTRBjmHD4G8FA50xx/bVFLqed5GWZw0DRSE28UTlyPmwBCEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df95c7d9473dbc7126132cdc89ee34336285818dbc31a72fb5cee90daba1111a","last_reissued_at":"2026-07-05T07:06:40.273216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:40.273216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junxiang Wang, Liang Zhao, Zheng Zhang","submitted_at":"2023-10-28T15:35:34Z","abstract_excerpt":"Graph Neural Networks (GNNs) have achieved great success in representing data with dependencies by recursively propagating and aggregating messages along the edges. However, edges in real-world graphs often have varying degrees of difficulty, and some edges may even be noisy to the downstream tasks. Therefore, existing GNNs may lead to suboptimal learned representations because they usually treat every edge in the graph equally. On the other hand, Curriculum Learning (CL), which mimics the human learning principle of learning data samples in a meaningful order, has been shown to be effective i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18735","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/2310.18735/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":"2310.18735","created_at":"2026-07-05T07:06:40.273272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18735v1","created_at":"2026-07-05T07:06:40.273272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18735","created_at":"2026-07-05T07:06:40.273272+00:00"},{"alias_kind":"pith_short_12","alias_value":"36K4PWKHHW6H","created_at":"2026-07-05T07:06:40.273272+00:00"},{"alias_kind":"pith_short_16","alias_value":"36K4PWKHHW6HCJQT","created_at":"2026-07-05T07:06:40.273272+00:00"},{"alias_kind":"pith_short_8","alias_value":"36K4PWKH","created_at":"2026-07-05T07:06:40.273272+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.14197","citing_title":"Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/36K4PWKHHW6HCJQTFTOIT3RUGN","json":"https://pith.science/pith/36K4PWKHHW6HCJQTFTOIT3RUGN.json","graph_json":"https://pith.science/api/pith-number/36K4PWKHHW6HCJQTFTOIT3RUGN/graph.json","events_json":"https://pith.science/api/pith-number/36K4PWKHHW6HCJQTFTOIT3RUGN/events.json","paper":"https://pith.science/paper/36K4PWKH"},"agent_actions":{"view_html":"https://pith.science/pith/36K4PWKHHW6HCJQTFTOIT3RUGN","download_json":"https://pith.science/pith/36K4PWKHHW6HCJQTFTOIT3RUGN.json","view_paper":"https://pith.science/paper/36K4PWKH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18735&json=true","fetch_graph":"https://pith.science/api/pith-number/36K4PWKHHW6HCJQTFTOIT3RUGN/graph.json","fetch_events":"https://pith.science/api/pith-number/36K4PWKHHW6HCJQTFTOIT3RUGN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36K4PWKHHW6HCJQTFTOIT3RUGN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36K4PWKHHW6HCJQTFTOIT3RUGN/action/storage_attestation","attest_author":"https://pith.science/pith/36K4PWKHHW6HCJQTFTOIT3RUGN/action/author_attestation","sign_citation":"https://pith.science/pith/36K4PWKHHW6HCJQTFTOIT3RUGN/action/citation_signature","submit_replication":"https://pith.science/pith/36K4PWKHHW6HCJQTFTOIT3RUGN/action/replication_record"}},"created_at":"2026-07-05T07:06:40.273272+00:00","updated_at":"2026-07-05T07:06:40.273272+00:00"}