{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LDCCABLW6BBEBNXYHOQ56IVDV2","short_pith_number":"pith:LDCCABLW","schema_version":"1.0","canonical_sha256":"58c4200576f04240b6f83ba1df22a3ae8c22a385c77703a042b06b77fe08bcc8","source":{"kind":"arxiv","id":"2412.09874","version":1},"attestation_state":"computed","paper":{"title":"Can Students Beyond The Teacher? Distilling Knowledge from Teacher's Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Houxiang Zhang, Jianhua Zhang, Ruyu Liu, Shengyong Chen, Xu Cheng, Yi Gao","submitted_at":"2024-12-13T05:40:20Z","abstract_excerpt":"Knowledge distillation (KD) is a model compression technique that transfers knowledge from a large teacher model to a smaller student model to enhance its performance. Existing methods often assume that the student model is inherently inferior to the teacher model. However, we identify that the fundamental issue affecting student performance is the bias transferred by the teacher. Current KD frameworks transmit both right and wrong knowledge, introducing bias that misleads the student model. To address this issue, we propose a novel strategy to rectify bias and greatly improve the student mode"},"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":"2412.09874","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-13T05:40:20Z","cross_cats_sorted":[],"title_canon_sha256":"e9c0990269a3d4947602c9eb02e0fc816a4f9710d6c0229b567d5d2e2358abed","abstract_canon_sha256":"0e418a9919eac049aed6cfb271426215118c87fd2cc8521d57e0f1ec07442fd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:43.165447Z","signature_b64":"iPk8uGsTFVAnCXmxfzn7DKM44uqhtPUOXfLC6lITaivaeSb/nUO9u82gRXvMiPNGHJ28futjW90NjEh5f1TjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58c4200576f04240b6f83ba1df22a3ae8c22a385c77703a042b06b77fe08bcc8","last_reissued_at":"2026-07-05T09:48:43.164945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:43.164945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Students Beyond The Teacher? Distilling Knowledge from Teacher's Bias","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Houxiang Zhang, Jianhua Zhang, Ruyu Liu, Shengyong Chen, Xu Cheng, Yi Gao","submitted_at":"2024-12-13T05:40:20Z","abstract_excerpt":"Knowledge distillation (KD) is a model compression technique that transfers knowledge from a large teacher model to a smaller student model to enhance its performance. Existing methods often assume that the student model is inherently inferior to the teacher model. However, we identify that the fundamental issue affecting student performance is the bias transferred by the teacher. Current KD frameworks transmit both right and wrong knowledge, introducing bias that misleads the student model. To address this issue, we propose a novel strategy to rectify bias and greatly improve the student mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09874","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/2412.09874/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":"2412.09874","created_at":"2026-07-05T09:48:43.165006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09874v1","created_at":"2026-07-05T09:48:43.165006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09874","created_at":"2026-07-05T09:48:43.165006+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDCCABLW6BBE","created_at":"2026-07-05T09:48:43.165006+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDCCABLW6BBEBNXY","created_at":"2026-07-05T09:48:43.165006+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDCCABLW","created_at":"2026-07-05T09:48:43.165006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08851","citing_title":"Cross-Lingual Attention Distillation with Personality-Informed Generative Augmentation for Multilingual Personality Recognition","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDCCABLW6BBEBNXYHOQ56IVDV2","json":"https://pith.science/pith/LDCCABLW6BBEBNXYHOQ56IVDV2.json","graph_json":"https://pith.science/api/pith-number/LDCCABLW6BBEBNXYHOQ56IVDV2/graph.json","events_json":"https://pith.science/api/pith-number/LDCCABLW6BBEBNXYHOQ56IVDV2/events.json","paper":"https://pith.science/paper/LDCCABLW"},"agent_actions":{"view_html":"https://pith.science/pith/LDCCABLW6BBEBNXYHOQ56IVDV2","download_json":"https://pith.science/pith/LDCCABLW6BBEBNXYHOQ56IVDV2.json","view_paper":"https://pith.science/paper/LDCCABLW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09874&json=true","fetch_graph":"https://pith.science/api/pith-number/LDCCABLW6BBEBNXYHOQ56IVDV2/graph.json","fetch_events":"https://pith.science/api/pith-number/LDCCABLW6BBEBNXYHOQ56IVDV2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDCCABLW6BBEBNXYHOQ56IVDV2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDCCABLW6BBEBNXYHOQ56IVDV2/action/storage_attestation","attest_author":"https://pith.science/pith/LDCCABLW6BBEBNXYHOQ56IVDV2/action/author_attestation","sign_citation":"https://pith.science/pith/LDCCABLW6BBEBNXYHOQ56IVDV2/action/citation_signature","submit_replication":"https://pith.science/pith/LDCCABLW6BBEBNXYHOQ56IVDV2/action/replication_record"}},"created_at":"2026-07-05T09:48:43.165006+00:00","updated_at":"2026-07-05T09:48:43.165006+00:00"}