{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FDFDS7RIZDANLBJ2AAFAOXOEGP","short_pith_number":"pith:FDFDS7RI","schema_version":"1.0","canonical_sha256":"28ca397e28c8c0d5853a000a075dc433dc9ffb952d6e3de11b92f80ebc5ce980","source":{"kind":"arxiv","id":"2508.13054","version":1},"attestation_state":"computed","paper":{"title":"Quantum Relational Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"quant-ph","authors_text":"Chen-Yu Liu, Enrico Rinaldi, Keisuke Murota, Kuan-Cheng Chen, Samuel Yen-Chi Chen","submitted_at":"2025-08-18T16:20:31Z","abstract_excerpt":"Knowledge distillation (KD) is a widely adopted technique for compressing large models into smaller, more efficient student models that can be deployed on devices with limited computational resources. Among various KD methods, Relational Knowledge Distillation (RKD) improves student performance by aligning relational structures in the feature space, such as pairwise distances and angles. In this work, we propose Quantum Relational Knowledge Distillation (QRKD), which extends RKD by incorporating quantum relational information. Specifically, we map classical features into a Hilbert space, inter"},"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":"2508.13054","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2025-08-18T16:20:31Z","cross_cats_sorted":[],"title_canon_sha256":"00b0c791d5cdbece46c7b00a01bf0690db77dce6e4f54243d9d84f7d17f2f44a","abstract_canon_sha256":"9c935c556c9e9844b8a1be91856ba79b43a770af98de3d56cdd466444d2d5e5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:31.701625Z","signature_b64":"tXJzyY2p925sswfYXovPhUKRc5P7nr9boKSIcTVsNcktbhGlIy4LViBzw6ECOuvG/PnwZpqlzO/c5U3uG1FbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28ca397e28c8c0d5853a000a075dc433dc9ffb952d6e3de11b92f80ebc5ce980","last_reissued_at":"2026-07-05T11:55:31.701119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:31.701119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantum Relational Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"quant-ph","authors_text":"Chen-Yu Liu, Enrico Rinaldi, Keisuke Murota, Kuan-Cheng Chen, Samuel Yen-Chi Chen","submitted_at":"2025-08-18T16:20:31Z","abstract_excerpt":"Knowledge distillation (KD) is a widely adopted technique for compressing large models into smaller, more efficient student models that can be deployed on devices with limited computational resources. Among various KD methods, Relational Knowledge Distillation (RKD) improves student performance by aligning relational structures in the feature space, such as pairwise distances and angles. In this work, we propose Quantum Relational Knowledge Distillation (QRKD), which extends RKD by incorporating quantum relational information. Specifically, we map classical features into a Hilbert space, inter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13054","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/2508.13054/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":"2508.13054","created_at":"2026-07-05T11:55:31.701178+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13054v1","created_at":"2026-07-05T11:55:31.701178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13054","created_at":"2026-07-05T11:55:31.701178+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDFDS7RIZDAN","created_at":"2026-07-05T11:55:31.701178+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDFDS7RIZDANLBJ2","created_at":"2026-07-05T11:55:31.701178+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDFDS7RI","created_at":"2026-07-05T11:55:31.701178+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.11092","citing_title":"MerLin: A Discovery Engine for Photonic and Hybrid Quantum Machine Learning","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11112","citing_title":"Quantum-Gated Task-interaction Knowledge Distillation for Pre-trained Model-based Class-Incremental Learning","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDFDS7RIZDANLBJ2AAFAOXOEGP","json":"https://pith.science/pith/FDFDS7RIZDANLBJ2AAFAOXOEGP.json","graph_json":"https://pith.science/api/pith-number/FDFDS7RIZDANLBJ2AAFAOXOEGP/graph.json","events_json":"https://pith.science/api/pith-number/FDFDS7RIZDANLBJ2AAFAOXOEGP/events.json","paper":"https://pith.science/paper/FDFDS7RI"},"agent_actions":{"view_html":"https://pith.science/pith/FDFDS7RIZDANLBJ2AAFAOXOEGP","download_json":"https://pith.science/pith/FDFDS7RIZDANLBJ2AAFAOXOEGP.json","view_paper":"https://pith.science/paper/FDFDS7RI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13054&json=true","fetch_graph":"https://pith.science/api/pith-number/FDFDS7RIZDANLBJ2AAFAOXOEGP/graph.json","fetch_events":"https://pith.science/api/pith-number/FDFDS7RIZDANLBJ2AAFAOXOEGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDFDS7RIZDANLBJ2AAFAOXOEGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDFDS7RIZDANLBJ2AAFAOXOEGP/action/storage_attestation","attest_author":"https://pith.science/pith/FDFDS7RIZDANLBJ2AAFAOXOEGP/action/author_attestation","sign_citation":"https://pith.science/pith/FDFDS7RIZDANLBJ2AAFAOXOEGP/action/citation_signature","submit_replication":"https://pith.science/pith/FDFDS7RIZDANLBJ2AAFAOXOEGP/action/replication_record"}},"created_at":"2026-07-05T11:55:31.701178+00:00","updated_at":"2026-07-05T11:55:31.701178+00:00"}