{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZHOVX6CS4XIRUVMYLFGP2IIPVY","short_pith_number":"pith:ZHOVX6CS","schema_version":"1.0","canonical_sha256":"c9dd5bf852e5d11a5598594cfd210fae392c0cc39e2afeb9dbe280a2413b72e6","source":{"kind":"arxiv","id":"2102.07650","version":4},"attestation_state":"computed","paper":{"title":"Learning Student-Friendly Teacher Networks for Knowledge Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bohyung Han, Changwook Jeong, Dae Sin Kim, Dae Young Park, Moon-Hyun Cha","submitted_at":"2021-02-12T07:00:17Z","abstract_excerpt":"We propose a novel knowledge distillation approach to facilitate the transfer of dark knowledge from a teacher to a student. Contrary to most of the existing methods that rely on effective training of student models given pretrained teachers, we aim to learn the teacher models that are friendly to students and, consequently, more appropriate for knowledge transfer. In other words, at the time of optimizing a teacher model, the proposed algorithm learns the student branches jointly to obtain student-friendly representations. Since the main goal of our approach lies in training teacher models an"},"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":"2102.07650","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-12T07:00:17Z","cross_cats_sorted":[],"title_canon_sha256":"e6a2ec3b829d9caff900583c5c2b51f68b2a9209b938e365d6b58c51f91d43b4","abstract_canon_sha256":"5b4297eacaf3dfa0556e90bb011bfca8309fa0302f979c9ac705aa182435fde2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:47.630407Z","signature_b64":"RP6wpN+EIstoXPmLm0PYCI84OsDEh5NdWfApJDkl1cEpmbPDoyqjZNFhP6nqdxeOEbLs6o88Ovne4DyQINlmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9dd5bf852e5d11a5598594cfd210fae392c0cc39e2afeb9dbe280a2413b72e6","last_reissued_at":"2026-07-05T03:50:47.629928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:47.629928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Student-Friendly Teacher Networks for Knowledge Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bohyung Han, Changwook Jeong, Dae Sin Kim, Dae Young Park, Moon-Hyun Cha","submitted_at":"2021-02-12T07:00:17Z","abstract_excerpt":"We propose a novel knowledge distillation approach to facilitate the transfer of dark knowledge from a teacher to a student. Contrary to most of the existing methods that rely on effective training of student models given pretrained teachers, we aim to learn the teacher models that are friendly to students and, consequently, more appropriate for knowledge transfer. In other words, at the time of optimizing a teacher model, the proposed algorithm learns the student branches jointly to obtain student-friendly representations. Since the main goal of our approach lies in training teacher models an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07650","kind":"arxiv","version":4},"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/2102.07650/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":"2102.07650","created_at":"2026-07-05T03:50:47.629982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.07650v4","created_at":"2026-07-05T03:50:47.629982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07650","created_at":"2026-07-05T03:50:47.629982+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZHOVX6CS4XIR","created_at":"2026-07-05T03:50:47.629982+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZHOVX6CS4XIRUVMY","created_at":"2026-07-05T03:50:47.629982+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZHOVX6CS","created_at":"2026-07-05T03:50:47.629982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23041","citing_title":"ReMem: Mutual Information-Aware Fine-tuning of Pretrained Vision Transformers for Effective Knowledge Distillation","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZHOVX6CS4XIRUVMYLFGP2IIPVY","json":"https://pith.science/pith/ZHOVX6CS4XIRUVMYLFGP2IIPVY.json","graph_json":"https://pith.science/api/pith-number/ZHOVX6CS4XIRUVMYLFGP2IIPVY/graph.json","events_json":"https://pith.science/api/pith-number/ZHOVX6CS4XIRUVMYLFGP2IIPVY/events.json","paper":"https://pith.science/paper/ZHOVX6CS"},"agent_actions":{"view_html":"https://pith.science/pith/ZHOVX6CS4XIRUVMYLFGP2IIPVY","download_json":"https://pith.science/pith/ZHOVX6CS4XIRUVMYLFGP2IIPVY.json","view_paper":"https://pith.science/paper/ZHOVX6CS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.07650&json=true","fetch_graph":"https://pith.science/api/pith-number/ZHOVX6CS4XIRUVMYLFGP2IIPVY/graph.json","fetch_events":"https://pith.science/api/pith-number/ZHOVX6CS4XIRUVMYLFGP2IIPVY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZHOVX6CS4XIRUVMYLFGP2IIPVY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZHOVX6CS4XIRUVMYLFGP2IIPVY/action/storage_attestation","attest_author":"https://pith.science/pith/ZHOVX6CS4XIRUVMYLFGP2IIPVY/action/author_attestation","sign_citation":"https://pith.science/pith/ZHOVX6CS4XIRUVMYLFGP2IIPVY/action/citation_signature","submit_replication":"https://pith.science/pith/ZHOVX6CS4XIRUVMYLFGP2IIPVY/action/replication_record"}},"created_at":"2026-07-05T03:50:47.629982+00:00","updated_at":"2026-07-05T03:50:47.629982+00:00"}