{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GYXGUCA3DJYJVMUJEICKT5IF4I","short_pith_number":"pith:GYXGUCA3","schema_version":"1.0","canonical_sha256":"362e6a081b1a709ab2892204a9f505e2358ef4095deba620df5babc56fe3acaf","source":{"kind":"arxiv","id":"2011.07449","version":1},"attestation_state":"computed","paper":{"title":"Online Ensemble Model Compression using Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Devesh Walawalkar, Marios Savvides, Zhiqiang Shen","submitted_at":"2020-11-15T04:46:29Z","abstract_excerpt":"This paper presents a novel knowledge distillation based model compression framework consisting of a student ensemble. It enables distillation of simultaneously learnt ensemble knowledge onto each of the compressed student models. Each model learns unique representations from the data distribution due to its distinct architecture. This helps the ensemble generalize better by combining every model's knowledge. The distilled students and ensemble teacher are trained simultaneously without requiring any pretrained weights. Moreover, our proposed method can deliver multi-compressed students with s"},"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":"2011.07449","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-11-15T04:46:29Z","cross_cats_sorted":[],"title_canon_sha256":"7561507c95b81acc4fee9e24b968c78a6e4eb70151f35fe837741946e1a02fda","abstract_canon_sha256":"5ebd4934cd9109e7f145cd3ea3e98cb219d625ed475039dc5af73c2f3f4c4975"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:49.880902Z","signature_b64":"TGKXUHfZAk5EtmcN0koyBRFxhwc5coe+04uYgMB5pBE2JPCzyI4Wr/WJb9XmX9frL2wkCphU8+CMnbAPqBjyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"362e6a081b1a709ab2892204a9f505e2358ef4095deba620df5babc56fe3acaf","last_reissued_at":"2026-07-05T01:51:49.880396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:49.880396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Ensemble Model Compression using Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Devesh Walawalkar, Marios Savvides, Zhiqiang Shen","submitted_at":"2020-11-15T04:46:29Z","abstract_excerpt":"This paper presents a novel knowledge distillation based model compression framework consisting of a student ensemble. It enables distillation of simultaneously learnt ensemble knowledge onto each of the compressed student models. Each model learns unique representations from the data distribution due to its distinct architecture. This helps the ensemble generalize better by combining every model's knowledge. The distilled students and ensemble teacher are trained simultaneously without requiring any pretrained weights. Moreover, our proposed method can deliver multi-compressed students with s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.07449","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/2011.07449/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":"2011.07449","created_at":"2026-07-05T01:51:49.880460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.07449v1","created_at":"2026-07-05T01:51:49.880460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.07449","created_at":"2026-07-05T01:51:49.880460+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYXGUCA3DJYJ","created_at":"2026-07-05T01:51:49.880460+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYXGUCA3DJYJVMUJ","created_at":"2026-07-05T01:51:49.880460+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYXGUCA3","created_at":"2026-07-05T01:51:49.880460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06849","citing_title":"Model Fusion via Neuron Transplantation","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYXGUCA3DJYJVMUJEICKT5IF4I","json":"https://pith.science/pith/GYXGUCA3DJYJVMUJEICKT5IF4I.json","graph_json":"https://pith.science/api/pith-number/GYXGUCA3DJYJVMUJEICKT5IF4I/graph.json","events_json":"https://pith.science/api/pith-number/GYXGUCA3DJYJVMUJEICKT5IF4I/events.json","paper":"https://pith.science/paper/GYXGUCA3"},"agent_actions":{"view_html":"https://pith.science/pith/GYXGUCA3DJYJVMUJEICKT5IF4I","download_json":"https://pith.science/pith/GYXGUCA3DJYJVMUJEICKT5IF4I.json","view_paper":"https://pith.science/paper/GYXGUCA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.07449&json=true","fetch_graph":"https://pith.science/api/pith-number/GYXGUCA3DJYJVMUJEICKT5IF4I/graph.json","fetch_events":"https://pith.science/api/pith-number/GYXGUCA3DJYJVMUJEICKT5IF4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYXGUCA3DJYJVMUJEICKT5IF4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYXGUCA3DJYJVMUJEICKT5IF4I/action/storage_attestation","attest_author":"https://pith.science/pith/GYXGUCA3DJYJVMUJEICKT5IF4I/action/author_attestation","sign_citation":"https://pith.science/pith/GYXGUCA3DJYJVMUJEICKT5IF4I/action/citation_signature","submit_replication":"https://pith.science/pith/GYXGUCA3DJYJVMUJEICKT5IF4I/action/replication_record"}},"created_at":"2026-07-05T01:51:49.880460+00:00","updated_at":"2026-07-05T01:51:49.880460+00:00"}