{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:Z7I4H7SB2YFSLPSXE7BZKJJIII","short_pith_number":"pith:Z7I4H7SB","schema_version":"1.0","canonical_sha256":"cfd1c3fe41d60b25be5727c39525284215efaae9dafc3e6a0c664a62af9fce1f","source":{"kind":"arxiv","id":"2205.03811","version":2},"attestation_state":"computed","paper":{"title":"Data-Free Adversarial Knowledge Distillation for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carl Yang, Chuan Shi, Lichao Sun, Lingjuan Lyu, Yuanxin Zhuang","submitted_at":"2022-05-08T08:19:40Z","abstract_excerpt":"Graph neural networks (GNNs) have been widely used in modeling graph structured data, owing to its impressive performance in a wide range of practical applications. Recently, knowledge distillation (KD) for GNNs has enabled remarkable progress in graph model compression and knowledge transfer. However, most of the existing KD methods require a large volume of real data, which are not readily available in practice, and may preclude their applicability in scenarios where the teacher model is trained on rare or hard to acquire datasets. To address this problem, we propose the first end-to-end fra"},"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":"2205.03811","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-08T08:19:40Z","cross_cats_sorted":[],"title_canon_sha256":"47a4e237d6bad569d53087504af489926327ac9b80176946c035259150a0d196","abstract_canon_sha256":"937398ad657b5ab8d430085d1d55e581d099c16cd33ef460af3bb3684271a240"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:16.654958Z","signature_b64":"nTFY8c5Fpk5IH+c9IAYYFRyzCj/dpHoe3YyLOVGwvgs6C+lgD0d99BYXQSLxaq2uZiit0whh7nqpZJwLI0cmDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfd1c3fe41d60b25be5727c39525284215efaae9dafc3e6a0c664a62af9fce1f","last_reissued_at":"2026-07-05T04:32:16.654436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:16.654436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Free Adversarial Knowledge Distillation for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carl Yang, Chuan Shi, Lichao Sun, Lingjuan Lyu, Yuanxin Zhuang","submitted_at":"2022-05-08T08:19:40Z","abstract_excerpt":"Graph neural networks (GNNs) have been widely used in modeling graph structured data, owing to its impressive performance in a wide range of practical applications. Recently, knowledge distillation (KD) for GNNs has enabled remarkable progress in graph model compression and knowledge transfer. However, most of the existing KD methods require a large volume of real data, which are not readily available in practice, and may preclude their applicability in scenarios where the teacher model is trained on rare or hard to acquire datasets. To address this problem, we propose the first end-to-end fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.03811","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/2205.03811/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":"2205.03811","created_at":"2026-07-05T04:32:16.654495+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.03811v2","created_at":"2026-07-05T04:32:16.654495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.03811","created_at":"2026-07-05T04:32:16.654495+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7I4H7SB2YFS","created_at":"2026-07-05T04:32:16.654495+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7I4H7SB2YFSLPSX","created_at":"2026-07-05T04:32:16.654495+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7I4H7SB","created_at":"2026-07-05T04:32:16.654495+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06814","citing_title":"From Model to Data (M2D): Shifting Complexity from GNNs to Graphs for Transparent Graph Learning","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z7I4H7SB2YFSLPSXE7BZKJJIII","json":"https://pith.science/pith/Z7I4H7SB2YFSLPSXE7BZKJJIII.json","graph_json":"https://pith.science/api/pith-number/Z7I4H7SB2YFSLPSXE7BZKJJIII/graph.json","events_json":"https://pith.science/api/pith-number/Z7I4H7SB2YFSLPSXE7BZKJJIII/events.json","paper":"https://pith.science/paper/Z7I4H7SB"},"agent_actions":{"view_html":"https://pith.science/pith/Z7I4H7SB2YFSLPSXE7BZKJJIII","download_json":"https://pith.science/pith/Z7I4H7SB2YFSLPSXE7BZKJJIII.json","view_paper":"https://pith.science/paper/Z7I4H7SB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.03811&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7I4H7SB2YFSLPSXE7BZKJJIII/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7I4H7SB2YFSLPSXE7BZKJJIII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7I4H7SB2YFSLPSXE7BZKJJIII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7I4H7SB2YFSLPSXE7BZKJJIII/action/storage_attestation","attest_author":"https://pith.science/pith/Z7I4H7SB2YFSLPSXE7BZKJJIII/action/author_attestation","sign_citation":"https://pith.science/pith/Z7I4H7SB2YFSLPSXE7BZKJJIII/action/citation_signature","submit_replication":"https://pith.science/pith/Z7I4H7SB2YFSLPSXE7BZKJJIII/action/replication_record"}},"created_at":"2026-07-05T04:32:16.654495+00:00","updated_at":"2026-07-05T04:32:16.654495+00:00"}