{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HTAQDTHRLKXJQ4UM6R7HKR75WU","short_pith_number":"pith:HTAQDTHR","schema_version":"1.0","canonical_sha256":"3cc101ccf15aae98728cf47e7547fdb5274ff46e50b40ca4a963cb2aa979793e","source":{"kind":"arxiv","id":"2304.04615","version":1},"attestation_state":"computed","paper":{"title":"A Survey on Recent Teacher-student Learning Studies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Minghong Gao","submitted_at":"2023-04-10T14:30:28Z","abstract_excerpt":"Knowledge distillation is a method of transferring the knowledge from a complex deep neural network (DNN) to a smaller and faster DNN, while preserving its accuracy. Recent variants of knowledge distillation include teaching assistant distillation, curriculum distillation, mask distillation, and decoupling distillation, which aim to improve the performance of knowledge distillation by introducing additional components or by changing the learning process. Teaching assistant distillation involves an intermediate model called the teaching assistant, while curriculum distillation follows a curricu"},"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":"2304.04615","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-10T14:30:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"01258d9f46036eeacbec82738b14570726f8b65732b60a7038dc07eae9a98b76","abstract_canon_sha256":"42b0e0674251db826bf34f30bbda6181fa743d4c03cfcf6b38c97af2f89e0f7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:28.161176Z","signature_b64":"Ksy6jJtRkClanK3VFBeevk+nKTmq0rNLwaIrjwox/bugQbLvJ5/7Uxm2S8ziQ0FyzErqM2oZtqT6bMO93T+KDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cc101ccf15aae98728cf47e7547fdb5274ff46e50b40ca4a963cb2aa979793e","last_reissued_at":"2026-07-05T05:59:28.160790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:28.160790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Recent Teacher-student Learning Studies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Minghong Gao","submitted_at":"2023-04-10T14:30:28Z","abstract_excerpt":"Knowledge distillation is a method of transferring the knowledge from a complex deep neural network (DNN) to a smaller and faster DNN, while preserving its accuracy. Recent variants of knowledge distillation include teaching assistant distillation, curriculum distillation, mask distillation, and decoupling distillation, which aim to improve the performance of knowledge distillation by introducing additional components or by changing the learning process. Teaching assistant distillation involves an intermediate model called the teaching assistant, while curriculum distillation follows a curricu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04615","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/2304.04615/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":"2304.04615","created_at":"2026-07-05T05:59:28.160846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04615v1","created_at":"2026-07-05T05:59:28.160846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04615","created_at":"2026-07-05T05:59:28.160846+00:00"},{"alias_kind":"pith_short_12","alias_value":"HTAQDTHRLKXJ","created_at":"2026-07-05T05:59:28.160846+00:00"},{"alias_kind":"pith_short_16","alias_value":"HTAQDTHRLKXJQ4UM","created_at":"2026-07-05T05:59:28.160846+00:00"},{"alias_kind":"pith_short_8","alias_value":"HTAQDTHR","created_at":"2026-07-05T05:59:28.160846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.13825","citing_title":"Feature Alignment and Representation Transfer in Knowledge Distillation for Large Language Models","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HTAQDTHRLKXJQ4UM6R7HKR75WU","json":"https://pith.science/pith/HTAQDTHRLKXJQ4UM6R7HKR75WU.json","graph_json":"https://pith.science/api/pith-number/HTAQDTHRLKXJQ4UM6R7HKR75WU/graph.json","events_json":"https://pith.science/api/pith-number/HTAQDTHRLKXJQ4UM6R7HKR75WU/events.json","paper":"https://pith.science/paper/HTAQDTHR"},"agent_actions":{"view_html":"https://pith.science/pith/HTAQDTHRLKXJQ4UM6R7HKR75WU","download_json":"https://pith.science/pith/HTAQDTHRLKXJQ4UM6R7HKR75WU.json","view_paper":"https://pith.science/paper/HTAQDTHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04615&json=true","fetch_graph":"https://pith.science/api/pith-number/HTAQDTHRLKXJQ4UM6R7HKR75WU/graph.json","fetch_events":"https://pith.science/api/pith-number/HTAQDTHRLKXJQ4UM6R7HKR75WU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HTAQDTHRLKXJQ4UM6R7HKR75WU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HTAQDTHRLKXJQ4UM6R7HKR75WU/action/storage_attestation","attest_author":"https://pith.science/pith/HTAQDTHRLKXJQ4UM6R7HKR75WU/action/author_attestation","sign_citation":"https://pith.science/pith/HTAQDTHRLKXJQ4UM6R7HKR75WU/action/citation_signature","submit_replication":"https://pith.science/pith/HTAQDTHRLKXJQ4UM6R7HKR75WU/action/replication_record"}},"created_at":"2026-07-05T05:59:28.160846+00:00","updated_at":"2026-07-05T05:59:28.160846+00:00"}