{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LMQDDPWE3R5YWGGNULLQLFF3EW","short_pith_number":"pith:LMQDDPWE","schema_version":"1.0","canonical_sha256":"5b2031bec4dc7b8b18cda2d70594bb259d076152019c0acd62b21dbf99a0dea5","source":{"kind":"arxiv","id":"2011.14554","version":1},"attestation_state":"computed","paper":{"title":"A Selective Survey on Versatile Knowledge Distillation Paradigm for Neural Network Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gaurav Pooniwala, Jeong-Hoe Ku, Jihun Oh, SangJeong Lee, YoungYoon Lee","submitted_at":"2020-11-30T05:22:02Z","abstract_excerpt":"This paper aims to provide a selective survey about knowledge distillation(KD) framework for researchers and practitioners to take advantage of it for developing new optimized models in the deep neural network field. To this end, we give a brief overview of knowledge distillation and some related works including learning using privileged information(LUPI) and generalized distillation(GD). Even though knowledge distillation based on the teacher-student architecture was initially devised as a model compression technique, it has found versatile applications over various frameworks.\n  In this pape"},"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":"2011.14554","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-30T05:22:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73e0b98b9e573d9cc67affcfddcbb0e39dccba52bb46e36c256bcf30c5f0f034","abstract_canon_sha256":"981a07976e1142d06f05e4addd1ddcc26fe62bfdec9889a1705d13cacc19973e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:55:21.352216Z","signature_b64":"k+ykd0Xeshik684aV5y88LfinP5GN1K5H56zJlP/miIE2JcEo2WhELdeVqfOOtpvNuTHaop8lkaERhRCfxDTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b2031bec4dc7b8b18cda2d70594bb259d076152019c0acd62b21dbf99a0dea5","last_reissued_at":"2026-07-05T01:55:21.351813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:55:21.351813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Selective Survey on Versatile Knowledge Distillation Paradigm for Neural Network Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gaurav Pooniwala, Jeong-Hoe Ku, Jihun Oh, SangJeong Lee, YoungYoon Lee","submitted_at":"2020-11-30T05:22:02Z","abstract_excerpt":"This paper aims to provide a selective survey about knowledge distillation(KD) framework for researchers and practitioners to take advantage of it for developing new optimized models in the deep neural network field. To this end, we give a brief overview of knowledge distillation and some related works including learning using privileged information(LUPI) and generalized distillation(GD). Even though knowledge distillation based on the teacher-student architecture was initially devised as a model compression technique, it has found versatile applications over various frameworks.\n  In this pape"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14554","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/2011.14554/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":"2011.14554","created_at":"2026-07-05T01:55:21.351871+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.14554v1","created_at":"2026-07-05T01:55:21.351871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14554","created_at":"2026-07-05T01:55:21.351871+00:00"},{"alias_kind":"pith_short_12","alias_value":"LMQDDPWE3R5Y","created_at":"2026-07-05T01:55:21.351871+00:00"},{"alias_kind":"pith_short_16","alias_value":"LMQDDPWE3R5YWGGN","created_at":"2026-07-05T01:55:21.351871+00:00"},{"alias_kind":"pith_short_8","alias_value":"LMQDDPWE","created_at":"2026-07-05T01:55:21.351871+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/LMQDDPWE3R5YWGGNULLQLFF3EW","json":"https://pith.science/pith/LMQDDPWE3R5YWGGNULLQLFF3EW.json","graph_json":"https://pith.science/api/pith-number/LMQDDPWE3R5YWGGNULLQLFF3EW/graph.json","events_json":"https://pith.science/api/pith-number/LMQDDPWE3R5YWGGNULLQLFF3EW/events.json","paper":"https://pith.science/paper/LMQDDPWE"},"agent_actions":{"view_html":"https://pith.science/pith/LMQDDPWE3R5YWGGNULLQLFF3EW","download_json":"https://pith.science/pith/LMQDDPWE3R5YWGGNULLQLFF3EW.json","view_paper":"https://pith.science/paper/LMQDDPWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.14554&json=true","fetch_graph":"https://pith.science/api/pith-number/LMQDDPWE3R5YWGGNULLQLFF3EW/graph.json","fetch_events":"https://pith.science/api/pith-number/LMQDDPWE3R5YWGGNULLQLFF3EW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LMQDDPWE3R5YWGGNULLQLFF3EW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LMQDDPWE3R5YWGGNULLQLFF3EW/action/storage_attestation","attest_author":"https://pith.science/pith/LMQDDPWE3R5YWGGNULLQLFF3EW/action/author_attestation","sign_citation":"https://pith.science/pith/LMQDDPWE3R5YWGGNULLQLFF3EW/action/citation_signature","submit_replication":"https://pith.science/pith/LMQDDPWE3R5YWGGNULLQLFF3EW/action/replication_record"}},"created_at":"2026-07-05T01:55:21.351871+00:00","updated_at":"2026-07-05T01:55:21.351871+00:00"}