{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PTD37WS3JUAJY2SWYP2QJNPVYQ","short_pith_number":"pith:PTD37WS3","schema_version":"1.0","canonical_sha256":"7cc7bfda5b4d009c6a56c3f504b5f5c43b8c90f2bc38b7d019fb360cfc21159d","source":{"kind":"arxiv","id":"2606.08978","version":1},"attestation_state":"computed","paper":{"title":"Heterophily-Aware Adaptive Knowledge Distillation for Hypergraph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Yoon Suk Kang, Joohee Cho, Yunyong Ko","submitted_at":"2026-06-08T03:23:43Z","abstract_excerpt":"Hypergraph knowledge distillation aims to retain the predictive performance of a hypergraph neural network (HNN) teacher while reducing inference costs through a lightweight student model. In this work, we observe that HNNs exhibit substantially lower prediction performance on heterophilic nodes connected through semantically diverse hyperedges, indicating that the reliability of teacher knowledge varies across nodes. Motivated by this observation, we propose HADES, a heterophily-aware adaptive distillation method for hypergraph neural networks. HADES quantifies node heterophily and leverages "},"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":"2606.08978","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T03:23:43Z","cross_cats_sorted":[],"title_canon_sha256":"53d66cf87aecdb1554d82791ef80589f6b806f69c072b3dde014e4f57eb197b8","abstract_canon_sha256":"ab2f6c6f7049bff0803570e4cc45543d7abf39ee531abdb5b844deb4fd3a2089"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:51.386768Z","signature_b64":"DNYJrCDJMVkoRayFEf6RdgfdqLayVvETnmBGoivJN1XfUSiUnwz8VUxQNNWqmVcSSLHl1+faSUj2K2hXwbljAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cc7bfda5b4d009c6a56c3f504b5f5c43b8c90f2bc38b7d019fb360cfc21159d","last_reissued_at":"2026-06-09T02:07:51.385920Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:51.385920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterophily-Aware Adaptive Knowledge Distillation for Hypergraph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Yoon Suk Kang, Joohee Cho, Yunyong Ko","submitted_at":"2026-06-08T03:23:43Z","abstract_excerpt":"Hypergraph knowledge distillation aims to retain the predictive performance of a hypergraph neural network (HNN) teacher while reducing inference costs through a lightweight student model. In this work, we observe that HNNs exhibit substantially lower prediction performance on heterophilic nodes connected through semantically diverse hyperedges, indicating that the reliability of teacher knowledge varies across nodes. Motivated by this observation, we propose HADES, a heterophily-aware adaptive distillation method for hypergraph neural networks. HADES quantifies node heterophily and leverages "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08978","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/2606.08978/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":"2606.08978","created_at":"2026-06-09T02:07:51.386078+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.08978v1","created_at":"2026-06-09T02:07:51.386078+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08978","created_at":"2026-06-09T02:07:51.386078+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTD37WS3JUAJ","created_at":"2026-06-09T02:07:51.386078+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTD37WS3JUAJY2SW","created_at":"2026-06-09T02:07:51.386078+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTD37WS3","created_at":"2026-06-09T02:07:51.386078+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/PTD37WS3JUAJY2SWYP2QJNPVYQ","json":"https://pith.science/pith/PTD37WS3JUAJY2SWYP2QJNPVYQ.json","graph_json":"https://pith.science/api/pith-number/PTD37WS3JUAJY2SWYP2QJNPVYQ/graph.json","events_json":"https://pith.science/api/pith-number/PTD37WS3JUAJY2SWYP2QJNPVYQ/events.json","paper":"https://pith.science/paper/PTD37WS3"},"agent_actions":{"view_html":"https://pith.science/pith/PTD37WS3JUAJY2SWYP2QJNPVYQ","download_json":"https://pith.science/pith/PTD37WS3JUAJY2SWYP2QJNPVYQ.json","view_paper":"https://pith.science/paper/PTD37WS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.08978&json=true","fetch_graph":"https://pith.science/api/pith-number/PTD37WS3JUAJY2SWYP2QJNPVYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/PTD37WS3JUAJY2SWYP2QJNPVYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTD37WS3JUAJY2SWYP2QJNPVYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTD37WS3JUAJY2SWYP2QJNPVYQ/action/storage_attestation","attest_author":"https://pith.science/pith/PTD37WS3JUAJY2SWYP2QJNPVYQ/action/author_attestation","sign_citation":"https://pith.science/pith/PTD37WS3JUAJY2SWYP2QJNPVYQ/action/citation_signature","submit_replication":"https://pith.science/pith/PTD37WS3JUAJY2SWYP2QJNPVYQ/action/replication_record"}},"created_at":"2026-06-09T02:07:51.386078+00:00","updated_at":"2026-06-09T02:07:51.386078+00:00"}