{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZDVY66IT6VOYD6TNDVNAAZMTHM","short_pith_number":"pith:ZDVY66IT","schema_version":"1.0","canonical_sha256":"c8eb8f7913f55d81fa6d1d5a0065933b2b6fbc7c8ffc1e35ebb7ea91ba53a250","source":{"kind":"arxiv","id":"2004.05937","version":7},"attestation_state":"computed","paper":{"title":"Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Kuk-Jin Yoon, Lin Wang","submitted_at":"2020-04-13T13:45:38Z","abstract_excerpt":"Deep neural models in recent years have been successful in almost every field, including extremely complex problem statements. However, these models are huge in size, with millions (and even billions) of parameters, thus demanding more heavy computation power and failing to be deployed on edge devices. Besides, the performance boost is highly dependent on redundant labeled data. To achieve faster speeds and to handle the problems caused by the lack of data, knowledge distillation (KD) has been proposed to transfer information learned from one model to another. KD is often characterized by the "},"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":"2004.05937","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-04-13T13:45:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f88526bfecee1c30e62e539ebb34d32bd0d462d3403f6a40f8abfc7cd52c2263","abstract_canon_sha256":"e2598d2c1b9fb2dadef80d364a67809173c9ecf0bc7463749e7724f7bd42f426"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:05.437636Z","signature_b64":"+4MFVmCMsTP8lFx88jAV6303dS79a+KSqfvY6NZjll9cf/4dLlxiurUgOOnbkcJs7aBCOLcbYnLb8dwvFNJSDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8eb8f7913f55d81fa6d1d5a0065933b2b6fbc7c8ffc1e35ebb7ea91ba53a250","last_reissued_at":"2026-07-05T02:50:05.437111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:05.437111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Kuk-Jin Yoon, Lin Wang","submitted_at":"2020-04-13T13:45:38Z","abstract_excerpt":"Deep neural models in recent years have been successful in almost every field, including extremely complex problem statements. However, these models are huge in size, with millions (and even billions) of parameters, thus demanding more heavy computation power and failing to be deployed on edge devices. Besides, the performance boost is highly dependent on redundant labeled data. To achieve faster speeds and to handle the problems caused by the lack of data, knowledge distillation (KD) has been proposed to transfer information learned from one model to another. KD is often characterized by the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05937","kind":"arxiv","version":7},"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/2004.05937/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":"2004.05937","created_at":"2026-07-05T02:50:05.437179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.05937v7","created_at":"2026-07-05T02:50:05.437179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05937","created_at":"2026-07-05T02:50:05.437179+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDVY66IT6VOY","created_at":"2026-07-05T02:50:05.437179+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDVY66IT6VOYD6TN","created_at":"2026-07-05T02:50:05.437179+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDVY66IT","created_at":"2026-07-05T02:50:05.437179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20232","citing_title":"ATMS-KD: Adaptive Temperature and Mixed Sample Knowledge Distillation for a Lightweight Residual CNN in Agricultural Embedded Systems","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZDVY66IT6VOYD6TNDVNAAZMTHM","json":"https://pith.science/pith/ZDVY66IT6VOYD6TNDVNAAZMTHM.json","graph_json":"https://pith.science/api/pith-number/ZDVY66IT6VOYD6TNDVNAAZMTHM/graph.json","events_json":"https://pith.science/api/pith-number/ZDVY66IT6VOYD6TNDVNAAZMTHM/events.json","paper":"https://pith.science/paper/ZDVY66IT"},"agent_actions":{"view_html":"https://pith.science/pith/ZDVY66IT6VOYD6TNDVNAAZMTHM","download_json":"https://pith.science/pith/ZDVY66IT6VOYD6TNDVNAAZMTHM.json","view_paper":"https://pith.science/paper/ZDVY66IT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.05937&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDVY66IT6VOYD6TNDVNAAZMTHM/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDVY66IT6VOYD6TNDVNAAZMTHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDVY66IT6VOYD6TNDVNAAZMTHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDVY66IT6VOYD6TNDVNAAZMTHM/action/storage_attestation","attest_author":"https://pith.science/pith/ZDVY66IT6VOYD6TNDVNAAZMTHM/action/author_attestation","sign_citation":"https://pith.science/pith/ZDVY66IT6VOYD6TNDVNAAZMTHM/action/citation_signature","submit_replication":"https://pith.science/pith/ZDVY66IT6VOYD6TNDVNAAZMTHM/action/replication_record"}},"created_at":"2026-07-05T02:50:05.437179+00:00","updated_at":"2026-07-05T02:50:05.437179+00:00"}