{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QWCMOCWW3SPRS3QJHYI6FLG67V","short_pith_number":"pith:QWCMOCWW","schema_version":"1.0","canonical_sha256":"8584c70ad6dc9f196e093e11e2acdefd797a1fc27efca4c38b65562e93f82703","source":{"kind":"arxiv","id":"2006.07114","version":2},"attestation_state":"computed","paper":{"title":"Knowledge Distillation Meets Self-Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Guodong Xu, Xiaoxiao Li, Ziwei Liu","submitted_at":"2020-06-12T12:18:52Z","abstract_excerpt":"Knowledge distillation, which involves extracting the \"dark knowledge\" from a teacher network to guide the learning of a student network, has emerged as an important technique for model compression and transfer learning. Unlike previous works that exploit architecture-specific cues such as activation and attention for distillation, here we wish to explore a more general and model-agnostic approach for extracting \"richer dark knowledge\" from the pre-trained teacher model. We show that the seemingly different self-supervision task can serve as a simple yet powerful solution. For example, when pe"},"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":"2006.07114","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-06-12T12:18:52Z","cross_cats_sorted":[],"title_canon_sha256":"7fd7a7738f48f52305d904171c51c99e86f2928cca72456da7a81d02368751a0","abstract_canon_sha256":"5bc08c261c8928949cc9d6ccfe297c46ac52134b406dc99047511505be6efbb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:18:03.507719Z","signature_b64":"s+wT8sxmPzdmoOlzqGdq0AF4SMTMKf6YZ0xx6dJXFtmm6gX+PbLefwSv5Hscq4jEfXFDFNV7PPn5/Qq3EDuWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8584c70ad6dc9f196e093e11e2acdefd797a1fc27efca4c38b65562e93f82703","last_reissued_at":"2026-07-05T01:18:03.507358Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:18:03.507358Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Distillation Meets Self-Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Guodong Xu, Xiaoxiao Li, Ziwei Liu","submitted_at":"2020-06-12T12:18:52Z","abstract_excerpt":"Knowledge distillation, which involves extracting the \"dark knowledge\" from a teacher network to guide the learning of a student network, has emerged as an important technique for model compression and transfer learning. Unlike previous works that exploit architecture-specific cues such as activation and attention for distillation, here we wish to explore a more general and model-agnostic approach for extracting \"richer dark knowledge\" from the pre-trained teacher model. We show that the seemingly different self-supervision task can serve as a simple yet powerful solution. For example, when pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07114","kind":"arxiv","version":2},"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/2006.07114/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":"2006.07114","created_at":"2026-07-05T01:18:03.507415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07114v2","created_at":"2026-07-05T01:18:03.507415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07114","created_at":"2026-07-05T01:18:03.507415+00:00"},{"alias_kind":"pith_short_12","alias_value":"QWCMOCWW3SPR","created_at":"2026-07-05T01:18:03.507415+00:00"},{"alias_kind":"pith_short_16","alias_value":"QWCMOCWW3SPRS3QJ","created_at":"2026-07-05T01:18:03.507415+00:00"},{"alias_kind":"pith_short_8","alias_value":"QWCMOCWW","created_at":"2026-07-05T01:18:03.507415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01987","citing_title":"Equally Critical: Samples, Targets, and Their Mappings in Datasets","ref_index":44,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QWCMOCWW3SPRS3QJHYI6FLG67V","json":"https://pith.science/pith/QWCMOCWW3SPRS3QJHYI6FLG67V.json","graph_json":"https://pith.science/api/pith-number/QWCMOCWW3SPRS3QJHYI6FLG67V/graph.json","events_json":"https://pith.science/api/pith-number/QWCMOCWW3SPRS3QJHYI6FLG67V/events.json","paper":"https://pith.science/paper/QWCMOCWW"},"agent_actions":{"view_html":"https://pith.science/pith/QWCMOCWW3SPRS3QJHYI6FLG67V","download_json":"https://pith.science/pith/QWCMOCWW3SPRS3QJHYI6FLG67V.json","view_paper":"https://pith.science/paper/QWCMOCWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07114&json=true","fetch_graph":"https://pith.science/api/pith-number/QWCMOCWW3SPRS3QJHYI6FLG67V/graph.json","fetch_events":"https://pith.science/api/pith-number/QWCMOCWW3SPRS3QJHYI6FLG67V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QWCMOCWW3SPRS3QJHYI6FLG67V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QWCMOCWW3SPRS3QJHYI6FLG67V/action/storage_attestation","attest_author":"https://pith.science/pith/QWCMOCWW3SPRS3QJHYI6FLG67V/action/author_attestation","sign_citation":"https://pith.science/pith/QWCMOCWW3SPRS3QJHYI6FLG67V/action/citation_signature","submit_replication":"https://pith.science/pith/QWCMOCWW3SPRS3QJHYI6FLG67V/action/replication_record"}},"created_at":"2026-07-05T01:18:03.507415+00:00","updated_at":"2026-07-05T01:18:03.507415+00:00"}