{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VIL7MKORM2KFHDLNIANPSG3DR2","short_pith_number":"pith:VIL7MKOR","schema_version":"1.0","canonical_sha256":"aa17f629d16694538d6d401af91b638ea82d50cf3fabd9b71d6853496fc9f863","source":{"kind":"arxiv","id":"2111.11747","version":1},"attestation_state":"computed","paper":{"title":"Semi-Online Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengkai Huang, Yanxia Liu, Zhiqiang Liu","submitted_at":"2021-11-23T09:44:58Z","abstract_excerpt":"Knowledge distillation is an effective and stable method for model compression via knowledge transfer. Conventional knowledge distillation (KD) is to transfer knowledge from a large and well pre-trained teacher network to a small student network, which is a one-way process. Recently, deep mutual learning (DML) has been proposed to help student networks learn collaboratively and simultaneously. However, to the best of our knowledge, KD and DML have never been jointly explored in a unified framework to solve the knowledge distillation problem. In this paper, we investigate that the teacher model"},"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":"2111.11747","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-23T09:44:58Z","cross_cats_sorted":[],"title_canon_sha256":"4f6b6ade485cb6557581f62705467f6bff5f1cfb35b7ffed6db04327ac37f38b","abstract_canon_sha256":"c68a744f9421aa339b04e709f17684901ea9c4dcc06bcbb44b3df4fb98f1affe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:12.386351Z","signature_b64":"jCj9cr2BO29av7K1Nqnd6BS63FhcYfpGuqUKJaLaFU8hldgGoFccWTeTawys0Wy//PFoQ5ycBHG9nE3G3igQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa17f629d16694538d6d401af91b638ea82d50cf3fabd9b71d6853496fc9f863","last_reissued_at":"2026-07-05T03:34:12.385901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:12.385901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Online Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengkai Huang, Yanxia Liu, Zhiqiang Liu","submitted_at":"2021-11-23T09:44:58Z","abstract_excerpt":"Knowledge distillation is an effective and stable method for model compression via knowledge transfer. Conventional knowledge distillation (KD) is to transfer knowledge from a large and well pre-trained teacher network to a small student network, which is a one-way process. Recently, deep mutual learning (DML) has been proposed to help student networks learn collaboratively and simultaneously. However, to the best of our knowledge, KD and DML have never been jointly explored in a unified framework to solve the knowledge distillation problem. In this paper, we investigate that the teacher model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11747","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/2111.11747/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":"2111.11747","created_at":"2026-07-05T03:34:12.385963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.11747v1","created_at":"2026-07-05T03:34:12.385963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11747","created_at":"2026-07-05T03:34:12.385963+00:00"},{"alias_kind":"pith_short_12","alias_value":"VIL7MKORM2KF","created_at":"2026-07-05T03:34:12.385963+00:00"},{"alias_kind":"pith_short_16","alias_value":"VIL7MKORM2KFHDLN","created_at":"2026-07-05T03:34:12.385963+00:00"},{"alias_kind":"pith_short_8","alias_value":"VIL7MKOR","created_at":"2026-07-05T03:34:12.385963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.27600","citing_title":"Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26760","citing_title":"Factorized Latent Reasoning for LLM-based Recommendation","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VIL7MKORM2KFHDLNIANPSG3DR2","json":"https://pith.science/pith/VIL7MKORM2KFHDLNIANPSG3DR2.json","graph_json":"https://pith.science/api/pith-number/VIL7MKORM2KFHDLNIANPSG3DR2/graph.json","events_json":"https://pith.science/api/pith-number/VIL7MKORM2KFHDLNIANPSG3DR2/events.json","paper":"https://pith.science/paper/VIL7MKOR"},"agent_actions":{"view_html":"https://pith.science/pith/VIL7MKORM2KFHDLNIANPSG3DR2","download_json":"https://pith.science/pith/VIL7MKORM2KFHDLNIANPSG3DR2.json","view_paper":"https://pith.science/paper/VIL7MKOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.11747&json=true","fetch_graph":"https://pith.science/api/pith-number/VIL7MKORM2KFHDLNIANPSG3DR2/graph.json","fetch_events":"https://pith.science/api/pith-number/VIL7MKORM2KFHDLNIANPSG3DR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VIL7MKORM2KFHDLNIANPSG3DR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VIL7MKORM2KFHDLNIANPSG3DR2/action/storage_attestation","attest_author":"https://pith.science/pith/VIL7MKORM2KFHDLNIANPSG3DR2/action/author_attestation","sign_citation":"https://pith.science/pith/VIL7MKORM2KFHDLNIANPSG3DR2/action/citation_signature","submit_replication":"https://pith.science/pith/VIL7MKORM2KFHDLNIANPSG3DR2/action/replication_record"}},"created_at":"2026-07-05T03:34:12.385963+00:00","updated_at":"2026-07-05T03:34:12.385963+00:00"}