{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GYFDKWM3TYQDJ57UJMDRQVX6YF","short_pith_number":"pith:GYFDKWM3","schema_version":"1.0","canonical_sha256":"360a35599b9e2034f7f44b071856fec1695271a114552b52476efb9b549762c0","source":{"kind":"arxiv","id":"2106.01489","version":3},"attestation_state":"computed","paper":{"title":"Not All Knowledge Is Created Equal: Mutual Distillation of Confident Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Christoph Meinel, David A. Clifton, Di Hu, Haojin Yang, Neil M. Robertson, Xinshao Wang, Ziyun Li","submitted_at":"2021-06-02T22:06:55Z","abstract_excerpt":"Mutual knowledge distillation (MKD) improves a model by distilling knowledge from another model. However, \\textit{not all knowledge is certain and correct}, especially under adverse conditions. For example, label noise usually leads to less reliable models due to undesired memorization \\cite{zhang2017understanding,arpit2017closer}. Wrong knowledge misleads the learning rather than helps. This problem can be handled by two aspects: (i) improving the reliability of a model where the knowledge is from (i.e., knowledge source's reliability); (ii) selecting reliable knowledge for distillation. In t"},"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":"2106.01489","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-02T22:06:55Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"ddb3aef43515a81275fe87bdebad955555c0e7592bbc578e4d9b5453c8f86553","abstract_canon_sha256":"3c83d0f1f198ea35dbc2d771379599171787cf7eaa2e06f066f0d7437e67bb0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:16:30.888312Z","signature_b64":"T7sNTQzOlsGGDAGeAXACZSaNZ2b4gLzzl1mcgJHo7syRB9ZNGeTG+0ZCa+raHxZity78E7kxqILTL3Uhk+5SDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"360a35599b9e2034f7f44b071856fec1695271a114552b52476efb9b549762c0","last_reissued_at":"2026-07-05T05:16:30.887844Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:16:30.887844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Not All Knowledge Is Created Equal: Mutual Distillation of Confident Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Christoph Meinel, David A. Clifton, Di Hu, Haojin Yang, Neil M. Robertson, Xinshao Wang, Ziyun Li","submitted_at":"2021-06-02T22:06:55Z","abstract_excerpt":"Mutual knowledge distillation (MKD) improves a model by distilling knowledge from another model. However, \\textit{not all knowledge is certain and correct}, especially under adverse conditions. For example, label noise usually leads to less reliable models due to undesired memorization \\cite{zhang2017understanding,arpit2017closer}. Wrong knowledge misleads the learning rather than helps. This problem can be handled by two aspects: (i) improving the reliability of a model where the knowledge is from (i.e., knowledge source's reliability); (ii) selecting reliable knowledge for distillation. In t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.01489","kind":"arxiv","version":3},"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/2106.01489/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":"2106.01489","created_at":"2026-07-05T05:16:30.887902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.01489v3","created_at":"2026-07-05T05:16:30.887902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.01489","created_at":"2026-07-05T05:16:30.887902+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYFDKWM3TYQD","created_at":"2026-07-05T05:16:30.887902+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYFDKWM3TYQDJ57U","created_at":"2026-07-05T05:16:30.887902+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYFDKWM3","created_at":"2026-07-05T05:16:30.887902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04038","citing_title":"FLAME: Condensing Ensemble Diversity into a Single Network for Efficient Sequential Recommendation","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYFDKWM3TYQDJ57UJMDRQVX6YF","json":"https://pith.science/pith/GYFDKWM3TYQDJ57UJMDRQVX6YF.json","graph_json":"https://pith.science/api/pith-number/GYFDKWM3TYQDJ57UJMDRQVX6YF/graph.json","events_json":"https://pith.science/api/pith-number/GYFDKWM3TYQDJ57UJMDRQVX6YF/events.json","paper":"https://pith.science/paper/GYFDKWM3"},"agent_actions":{"view_html":"https://pith.science/pith/GYFDKWM3TYQDJ57UJMDRQVX6YF","download_json":"https://pith.science/pith/GYFDKWM3TYQDJ57UJMDRQVX6YF.json","view_paper":"https://pith.science/paper/GYFDKWM3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.01489&json=true","fetch_graph":"https://pith.science/api/pith-number/GYFDKWM3TYQDJ57UJMDRQVX6YF/graph.json","fetch_events":"https://pith.science/api/pith-number/GYFDKWM3TYQDJ57UJMDRQVX6YF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYFDKWM3TYQDJ57UJMDRQVX6YF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYFDKWM3TYQDJ57UJMDRQVX6YF/action/storage_attestation","attest_author":"https://pith.science/pith/GYFDKWM3TYQDJ57UJMDRQVX6YF/action/author_attestation","sign_citation":"https://pith.science/pith/GYFDKWM3TYQDJ57UJMDRQVX6YF/action/citation_signature","submit_replication":"https://pith.science/pith/GYFDKWM3TYQDJ57UJMDRQVX6YF/action/replication_record"}},"created_at":"2026-07-05T05:16:30.887902+00:00","updated_at":"2026-07-05T05:16:30.887902+00:00"}