{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XJ7DKOMFJUQKPQS2WHMLEE2JLF","short_pith_number":"pith:XJ7DKOMF","schema_version":"1.0","canonical_sha256":"ba7e3539854d20a7c25ab1d8b21349597d17c9ad262458dd32343e894f5c911c","source":{"kind":"arxiv","id":"2306.05628","version":1},"attestation_state":"computed","paper":{"title":"Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haitao Lin, Lirong Wu, Stan Z. Li, Yufei Huang","submitted_at":"2023-06-09T02:23:37Z","abstract_excerpt":"To bridge the gaps between topology-aware Graph Neural Networks (GNNs) and inference-efficient Multi-Layer Perceptron (MLPs), GLNN proposes to distill knowledge from a well-trained teacher GNN into a student MLP. Despite their great progress, comparatively little work has been done to explore the reliability of different knowledge points (nodes) in GNNs, especially their roles played during distillation. In this paper, we first quantify the knowledge reliability in GNN by measuring the invariance of their information entropy to noise perturbations, from which we observe that different knowledg"},"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":"2306.05628","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-09T02:23:37Z","cross_cats_sorted":[],"title_canon_sha256":"7539a7bcde40099f1a58964ba0eb3fcd70b361d2d86d66bd0899ff7e5e0abd2b","abstract_canon_sha256":"c0a84fb497e12805111ae198c76fc57b92ca4034a3808a3c3001cd4086ff06b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:08.364049Z","signature_b64":"QJZLSb4O1mw1eM13omixRhV95xNFlRBpWi7X+gpfxtYWMGHwW+Kw02CYVYvAIjL/E5wX/3ZBFdyCjMRRLpgABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba7e3539854d20a7c25ab1d8b21349597d17c9ad262458dd32343e894f5c911c","last_reissued_at":"2026-07-05T06:19:08.363687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:08.363687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying the Knowledge in GNNs for Reliable Distillation into MLPs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Haitao Lin, Lirong Wu, Stan Z. Li, Yufei Huang","submitted_at":"2023-06-09T02:23:37Z","abstract_excerpt":"To bridge the gaps between topology-aware Graph Neural Networks (GNNs) and inference-efficient Multi-Layer Perceptron (MLPs), GLNN proposes to distill knowledge from a well-trained teacher GNN into a student MLP. Despite their great progress, comparatively little work has been done to explore the reliability of different knowledge points (nodes) in GNNs, especially their roles played during distillation. In this paper, we first quantify the knowledge reliability in GNN by measuring the invariance of their information entropy to noise perturbations, from which we observe that different knowledg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05628","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/2306.05628/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":"2306.05628","created_at":"2026-07-05T06:19:08.363746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05628v1","created_at":"2026-07-05T06:19:08.363746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05628","created_at":"2026-07-05T06:19:08.363746+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJ7DKOMFJUQK","created_at":"2026-07-05T06:19:08.363746+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJ7DKOMFJUQKPQS2","created_at":"2026-07-05T06:19:08.363746+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJ7DKOMF","created_at":"2026-07-05T06:19:08.363746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19031","citing_title":"ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJ7DKOMFJUQKPQS2WHMLEE2JLF","json":"https://pith.science/pith/XJ7DKOMFJUQKPQS2WHMLEE2JLF.json","graph_json":"https://pith.science/api/pith-number/XJ7DKOMFJUQKPQS2WHMLEE2JLF/graph.json","events_json":"https://pith.science/api/pith-number/XJ7DKOMFJUQKPQS2WHMLEE2JLF/events.json","paper":"https://pith.science/paper/XJ7DKOMF"},"agent_actions":{"view_html":"https://pith.science/pith/XJ7DKOMFJUQKPQS2WHMLEE2JLF","download_json":"https://pith.science/pith/XJ7DKOMFJUQKPQS2WHMLEE2JLF.json","view_paper":"https://pith.science/paper/XJ7DKOMF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05628&json=true","fetch_graph":"https://pith.science/api/pith-number/XJ7DKOMFJUQKPQS2WHMLEE2JLF/graph.json","fetch_events":"https://pith.science/api/pith-number/XJ7DKOMFJUQKPQS2WHMLEE2JLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJ7DKOMFJUQKPQS2WHMLEE2JLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJ7DKOMFJUQKPQS2WHMLEE2JLF/action/storage_attestation","attest_author":"https://pith.science/pith/XJ7DKOMFJUQKPQS2WHMLEE2JLF/action/author_attestation","sign_citation":"https://pith.science/pith/XJ7DKOMFJUQKPQS2WHMLEE2JLF/action/citation_signature","submit_replication":"https://pith.science/pith/XJ7DKOMFJUQKPQS2WHMLEE2JLF/action/replication_record"}},"created_at":"2026-07-05T06:19:08.363746+00:00","updated_at":"2026-07-05T06:19:08.363746+00:00"}