{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BPK2Y47CGCSR4NSA3F43ZNJZKF","short_pith_number":"pith:BPK2Y47C","schema_version":"1.0","canonical_sha256":"0bd5ac73e230a51e3640d979bcb53951679d1c4b309d42bce048d1689e4eb13b","source":{"kind":"arxiv","id":"2412.11180","version":3},"attestation_state":"computed","paper":{"title":"TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Jieming Shi, Qing Li, Shiqi Shen, Zhihao Ding, Ziang Zhou","submitted_at":"2024-12-15T13:18:56Z","abstract_excerpt":"Graph Neural Networks (GNNs) are pivotal in graph-based learning, particularly excelling in node classification. However, their scalability is hindered by the need for multi-hop data during inference, limiting their application in latency-sensitive scenarios. Recent efforts to distill GNNs into multi-layer perceptrons (MLPs) for faster inference often underutilize the layer-level insights of GNNs. In this paper, we present TINED, a novel approach that distills GNNs to MLPs on a layer-by-layer basis using Teacher Injection and Dirichlet Energy Distillation techniques. We focus on two key operat"},"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":"2412.11180","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-15T13:18:56Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"a4dc34e10065b7a19f8c6c4c32f06dcf050d0e5c1dfd3537ecbb189b059a2638","abstract_canon_sha256":"3f1ffd129c4c99d88e6c79f7253e7a092375975d7faba777ac082bb97b724412"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:38.526553Z","signature_b64":"39V3cHttiRiQrOptJF1EHheXdAdVVEYkgmKBCyLbhyvuLDxV4z7Q4mcPZYCk9ooHUizxr+ZMREW8XfDMXNaFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bd5ac73e230a51e3640d979bcb53951679d1c4b309d42bce048d1689e4eb13b","last_reissued_at":"2026-07-05T11:11:38.525976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:38.525976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TINED: GNNs-to-MLPs by Teacher Injection and Dirichlet Energy Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.LG","authors_text":"Jieming Shi, Qing Li, Shiqi Shen, Zhihao Ding, Ziang Zhou","submitted_at":"2024-12-15T13:18:56Z","abstract_excerpt":"Graph Neural Networks (GNNs) are pivotal in graph-based learning, particularly excelling in node classification. However, their scalability is hindered by the need for multi-hop data during inference, limiting their application in latency-sensitive scenarios. Recent efforts to distill GNNs into multi-layer perceptrons (MLPs) for faster inference often underutilize the layer-level insights of GNNs. In this paper, we present TINED, a novel approach that distills GNNs to MLPs on a layer-by-layer basis using Teacher Injection and Dirichlet Energy Distillation techniques. We focus on two key operat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11180","kind":"arxiv","version":3},"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/2412.11180/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":"2412.11180","created_at":"2026-07-05T11:11:38.526033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11180v3","created_at":"2026-07-05T11:11:38.526033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11180","created_at":"2026-07-05T11:11:38.526033+00:00"},{"alias_kind":"pith_short_12","alias_value":"BPK2Y47CGCSR","created_at":"2026-07-05T11:11:38.526033+00:00"},{"alias_kind":"pith_short_16","alias_value":"BPK2Y47CGCSR4NSA","created_at":"2026-07-05T11:11:38.526033+00:00"},{"alias_kind":"pith_short_8","alias_value":"BPK2Y47C","created_at":"2026-07-05T11:11:38.526033+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/BPK2Y47CGCSR4NSA3F43ZNJZKF","json":"https://pith.science/pith/BPK2Y47CGCSR4NSA3F43ZNJZKF.json","graph_json":"https://pith.science/api/pith-number/BPK2Y47CGCSR4NSA3F43ZNJZKF/graph.json","events_json":"https://pith.science/api/pith-number/BPK2Y47CGCSR4NSA3F43ZNJZKF/events.json","paper":"https://pith.science/paper/BPK2Y47C"},"agent_actions":{"view_html":"https://pith.science/pith/BPK2Y47CGCSR4NSA3F43ZNJZKF","download_json":"https://pith.science/pith/BPK2Y47CGCSR4NSA3F43ZNJZKF.json","view_paper":"https://pith.science/paper/BPK2Y47C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11180&json=true","fetch_graph":"https://pith.science/api/pith-number/BPK2Y47CGCSR4NSA3F43ZNJZKF/graph.json","fetch_events":"https://pith.science/api/pith-number/BPK2Y47CGCSR4NSA3F43ZNJZKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BPK2Y47CGCSR4NSA3F43ZNJZKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BPK2Y47CGCSR4NSA3F43ZNJZKF/action/storage_attestation","attest_author":"https://pith.science/pith/BPK2Y47CGCSR4NSA3F43ZNJZKF/action/author_attestation","sign_citation":"https://pith.science/pith/BPK2Y47CGCSR4NSA3F43ZNJZKF/action/citation_signature","submit_replication":"https://pith.science/pith/BPK2Y47CGCSR4NSA3F43ZNJZKF/action/replication_record"}},"created_at":"2026-07-05T11:11:38.526033+00:00","updated_at":"2026-07-05T11:11:38.526033+00:00"}