{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AN2M2CFHGQNYVZ5KX4MEMWZIAB","short_pith_number":"pith:AN2M2CFH","schema_version":"1.0","canonical_sha256":"0374cd08a7341b8ae7aabf18465b28006601b4ed004ee9cea75d1704f2790935","source":{"kind":"arxiv","id":"1812.01819","version":2},"attestation_state":"computed","paper":{"title":"An Embarrassingly Simple Approach for Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Dahua Lin, Junjie Yan, Liang Wan, Mengya Gao, Quanquan Li, Xiaoou Tang, Yujun Shen","submitted_at":"2018-12-05T05:09:45Z","abstract_excerpt":"Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model. Previous KD methods typically train a student by minimizing a task-related loss and the KD loss simultaneously, using a pre-defined loss weight to balance these two terms. In this work, we propose to first transfer the backbone knowledge from a teacher to the student, and then only learn the task-head of the student network. Such a decomposition of the training process circumvents the need of choosing an appropriate loss weight, which is ofte"},"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":"1812.01819","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-12-05T05:09:45Z","cross_cats_sorted":[],"title_canon_sha256":"a0b00427611d8ce0d1106a0c120b44a747b0a6a4764eb4911b6b4b5716309c4c","abstract_canon_sha256":"b5a4f9bae3d1a75d57070bdb312c74f0ab1c2406eeea7610eb31de596a90a3e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:55.499387Z","signature_b64":"UzvkWrzauwjYmfkvzvitxj2cWCBHnnGBeTWUewGV9EyDgSwfg2zpbDJFbctFqQufgtuhn7ND9Q1YOdSk0bDxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0374cd08a7341b8ae7aabf18465b28006601b4ed004ee9cea75d1704f2790935","last_reissued_at":"2026-07-05T00:02:55.498903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:55.498903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Embarrassingly Simple Approach for Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Change Loy, Dahua Lin, Junjie Yan, Liang Wan, Mengya Gao, Quanquan Li, Xiaoou Tang, Yujun Shen","submitted_at":"2018-12-05T05:09:45Z","abstract_excerpt":"Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model. Previous KD methods typically train a student by minimizing a task-related loss and the KD loss simultaneously, using a pre-defined loss weight to balance these two terms. In this work, we propose to first transfer the backbone knowledge from a teacher to the student, and then only learn the task-head of the student network. Such a decomposition of the training process circumvents the need of choosing an appropriate loss weight, which is ofte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.01819","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/1812.01819/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":"1812.01819","created_at":"2026-07-05T00:02:55.498951+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.01819v2","created_at":"2026-07-05T00:02:55.498951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.01819","created_at":"2026-07-05T00:02:55.498951+00:00"},{"alias_kind":"pith_short_12","alias_value":"AN2M2CFHGQNY","created_at":"2026-07-05T00:02:55.498951+00:00"},{"alias_kind":"pith_short_16","alias_value":"AN2M2CFHGQNYVZ5K","created_at":"2026-07-05T00:02:55.498951+00:00"},{"alias_kind":"pith_short_8","alias_value":"AN2M2CFH","created_at":"2026-07-05T00:02:55.498951+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AN2M2CFHGQNYVZ5KX4MEMWZIAB","json":"https://pith.science/pith/AN2M2CFHGQNYVZ5KX4MEMWZIAB.json","graph_json":"https://pith.science/api/pith-number/AN2M2CFHGQNYVZ5KX4MEMWZIAB/graph.json","events_json":"https://pith.science/api/pith-number/AN2M2CFHGQNYVZ5KX4MEMWZIAB/events.json","paper":"https://pith.science/paper/AN2M2CFH"},"agent_actions":{"view_html":"https://pith.science/pith/AN2M2CFHGQNYVZ5KX4MEMWZIAB","download_json":"https://pith.science/pith/AN2M2CFHGQNYVZ5KX4MEMWZIAB.json","view_paper":"https://pith.science/paper/AN2M2CFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.01819&json=true","fetch_graph":"https://pith.science/api/pith-number/AN2M2CFHGQNYVZ5KX4MEMWZIAB/graph.json","fetch_events":"https://pith.science/api/pith-number/AN2M2CFHGQNYVZ5KX4MEMWZIAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AN2M2CFHGQNYVZ5KX4MEMWZIAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AN2M2CFHGQNYVZ5KX4MEMWZIAB/action/storage_attestation","attest_author":"https://pith.science/pith/AN2M2CFHGQNYVZ5KX4MEMWZIAB/action/author_attestation","sign_citation":"https://pith.science/pith/AN2M2CFHGQNYVZ5KX4MEMWZIAB/action/citation_signature","submit_replication":"https://pith.science/pith/AN2M2CFHGQNYVZ5KX4MEMWZIAB/action/replication_record"}},"created_at":"2026-07-05T00:02:55.498951+00:00","updated_at":"2026-07-05T00:02:55.498951+00:00"}