{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:E34DGV35PG4VDWEWJ7J7TMG754","short_pith_number":"pith:E34DGV35","schema_version":"1.0","canonical_sha256":"26f833577d79b951d8964fd3f9b0dfef234084a2431e9ea5fa189e175b8fc3cd","source":{"kind":"arxiv","id":"2308.04268","version":1},"attestation_state":"computed","paper":{"title":"Teacher-Student Architecture for Knowledge Distillation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengming Hu, Dan Liu, Haolun Wu, Ju Wang, Xi Chen, Xuan Li, Xue Liu","submitted_at":"2023-08-08T14:09:33Z","abstract_excerpt":"Although Deep neural networks (DNNs) have shown a strong capacity to solve large-scale problems in many areas, such DNNs are hard to be deployed in real-world systems due to their voluminous parameters. To tackle this issue, Teacher-Student architectures were proposed, where simple student networks with a few parameters can achieve comparable performance to deep teacher networks with many parameters. Recently, Teacher-Student architectures have been effectively and widely embraced on various knowledge distillation (KD) objectives, including knowledge compression, knowledge expansion, knowledge"},"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":"2308.04268","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-08T14:09:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"35c995958a113c807c7c2574e10ef897ae9165f0a2cfca6cfac65ce90c3d786a","abstract_canon_sha256":"a53bbfee2a4e182aba307ba1304ce0bb93a61f8ad0fb424952deaf8fd5ac95d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:24.865769Z","signature_b64":"zO7le0CQkkYfPngy/P61Oboyzm3/afAsJTdHLSpNA14TO38WANtPBFsWS3UbFvbKCSVcBD9Ex1vZG8JqOdEMDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26f833577d79b951d8964fd3f9b0dfef234084a2431e9ea5fa189e175b8fc3cd","last_reissued_at":"2026-07-05T06:39:24.865271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:24.865271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Teacher-Student Architecture for Knowledge Distillation: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chengming Hu, Dan Liu, Haolun Wu, Ju Wang, Xi Chen, Xuan Li, Xue Liu","submitted_at":"2023-08-08T14:09:33Z","abstract_excerpt":"Although Deep neural networks (DNNs) have shown a strong capacity to solve large-scale problems in many areas, such DNNs are hard to be deployed in real-world systems due to their voluminous parameters. To tackle this issue, Teacher-Student architectures were proposed, where simple student networks with a few parameters can achieve comparable performance to deep teacher networks with many parameters. Recently, Teacher-Student architectures have been effectively and widely embraced on various knowledge distillation (KD) objectives, including knowledge compression, knowledge expansion, knowledge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04268","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/2308.04268/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":"2308.04268","created_at":"2026-07-05T06:39:24.865333+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.04268v1","created_at":"2026-07-05T06:39:24.865333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04268","created_at":"2026-07-05T06:39:24.865333+00:00"},{"alias_kind":"pith_short_12","alias_value":"E34DGV35PG4V","created_at":"2026-07-05T06:39:24.865333+00:00"},{"alias_kind":"pith_short_16","alias_value":"E34DGV35PG4VDWEW","created_at":"2026-07-05T06:39:24.865333+00:00"},{"alias_kind":"pith_short_8","alias_value":"E34DGV35","created_at":"2026-07-05T06:39:24.865333+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01974","citing_title":"A Multi-Branch Hierarchy-Aware Framework for Heterogeneous Audio Classification","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29209","citing_title":"AnyBody: Free-Form Whole-Body Humanoid Control from Arbitrary Keypoint Guidance","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13233","citing_title":"Doppler Prompting for Stable mmWave-based Human Pose Estimation","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06691","citing_title":"KD-MARL: Resource-Aware Knowledge Distillation in Multi-Agent Reinforcement Learning","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E34DGV35PG4VDWEWJ7J7TMG754","json":"https://pith.science/pith/E34DGV35PG4VDWEWJ7J7TMG754.json","graph_json":"https://pith.science/api/pith-number/E34DGV35PG4VDWEWJ7J7TMG754/graph.json","events_json":"https://pith.science/api/pith-number/E34DGV35PG4VDWEWJ7J7TMG754/events.json","paper":"https://pith.science/paper/E34DGV35"},"agent_actions":{"view_html":"https://pith.science/pith/E34DGV35PG4VDWEWJ7J7TMG754","download_json":"https://pith.science/pith/E34DGV35PG4VDWEWJ7J7TMG754.json","view_paper":"https://pith.science/paper/E34DGV35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.04268&json=true","fetch_graph":"https://pith.science/api/pith-number/E34DGV35PG4VDWEWJ7J7TMG754/graph.json","fetch_events":"https://pith.science/api/pith-number/E34DGV35PG4VDWEWJ7J7TMG754/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E34DGV35PG4VDWEWJ7J7TMG754/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E34DGV35PG4VDWEWJ7J7TMG754/action/storage_attestation","attest_author":"https://pith.science/pith/E34DGV35PG4VDWEWJ7J7TMG754/action/author_attestation","sign_citation":"https://pith.science/pith/E34DGV35PG4VDWEWJ7J7TMG754/action/citation_signature","submit_replication":"https://pith.science/pith/E34DGV35PG4VDWEWJ7J7TMG754/action/replication_record"}},"created_at":"2026-07-05T06:39:24.865333+00:00","updated_at":"2026-07-05T06:39:24.865333+00:00"}