{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QETKVUJJUEJPRT6GCJQ7YGIKIX","short_pith_number":"pith:QETKVUJJ","schema_version":"1.0","canonical_sha256":"8126aad129a112f8cfc61261fc190a45c57d6fba3c8083a77d886ba7fb3b5981","source":{"kind":"arxiv","id":"1904.09149","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Distillation via Route Constrained Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Baoyun Peng, Ding Liang, Jiaheng Liu, Junjie Yan, Xiao Jin, Xiaolin Hu, Yichao Wu, Yu Liu","submitted_at":"2019-04-19T11:24:20Z","abstract_excerpt":"Distillation-based learning boosts the performance of the miniaturized neural network based on the hypothesis that the representation of a teacher model can be used as structured and relatively weak supervision, and thus would be easily learned by a miniaturized model. However, we find that the representation of a converged heavy model is still a strong constraint for training a small student model, which leads to a high lower bound of congruence loss. In this work, inspired by curriculum learning we consider the knowledge distillation from the perspective of curriculum learning by routing. In"},"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":"1904.09149","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-19T11:24:20Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2b429fa75c57a4a29d6dc6835946cc71f16be24b9f4fba3bf452f62f08808c3a","abstract_canon_sha256":"37d5d3e2b9f4baf43318e1bc4453c42f8dee9ad4bb3f9d7724a585b2b06e7ad4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:08.186180Z","signature_b64":"e8e/VTvF7t/LRK8BNloFTaKe+/VezutfzZeRbnegXSjU4rpetOo2kCdB+AZqojmt/90xYHpAzDwgETroaHdmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8126aad129a112f8cfc61261fc190a45c57d6fba3c8083a77d886ba7fb3b5981","last_reissued_at":"2026-05-17T23:48:08.185532Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:08.185532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Distillation via Route Constrained Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Baoyun Peng, Ding Liang, Jiaheng Liu, Junjie Yan, Xiao Jin, Xiaolin Hu, Yichao Wu, Yu Liu","submitted_at":"2019-04-19T11:24:20Z","abstract_excerpt":"Distillation-based learning boosts the performance of the miniaturized neural network based on the hypothesis that the representation of a teacher model can be used as structured and relatively weak supervision, and thus would be easily learned by a miniaturized model. However, we find that the representation of a converged heavy model is still a strong constraint for training a small student model, which leads to a high lower bound of congruence loss. In this work, inspired by curriculum learning we consider the knowledge distillation from the perspective of curriculum learning by routing. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09149","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":""},"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":"1904.09149","created_at":"2026-05-17T23:48:08.185626+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.09149v1","created_at":"2026-05-17T23:48:08.185626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09149","created_at":"2026-05-17T23:48:08.185626+00:00"},{"alias_kind":"pith_short_12","alias_value":"QETKVUJJUEJP","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"QETKVUJJUEJPRT6G","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"QETKVUJJ","created_at":"2026-05-18T12:33:27.125529+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/QETKVUJJUEJPRT6GCJQ7YGIKIX","json":"https://pith.science/pith/QETKVUJJUEJPRT6GCJQ7YGIKIX.json","graph_json":"https://pith.science/api/pith-number/QETKVUJJUEJPRT6GCJQ7YGIKIX/graph.json","events_json":"https://pith.science/api/pith-number/QETKVUJJUEJPRT6GCJQ7YGIKIX/events.json","paper":"https://pith.science/paper/QETKVUJJ"},"agent_actions":{"view_html":"https://pith.science/pith/QETKVUJJUEJPRT6GCJQ7YGIKIX","download_json":"https://pith.science/pith/QETKVUJJUEJPRT6GCJQ7YGIKIX.json","view_paper":"https://pith.science/paper/QETKVUJJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.09149&json=true","fetch_graph":"https://pith.science/api/pith-number/QETKVUJJUEJPRT6GCJQ7YGIKIX/graph.json","fetch_events":"https://pith.science/api/pith-number/QETKVUJJUEJPRT6GCJQ7YGIKIX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QETKVUJJUEJPRT6GCJQ7YGIKIX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QETKVUJJUEJPRT6GCJQ7YGIKIX/action/storage_attestation","attest_author":"https://pith.science/pith/QETKVUJJUEJPRT6GCJQ7YGIKIX/action/author_attestation","sign_citation":"https://pith.science/pith/QETKVUJJUEJPRT6GCJQ7YGIKIX/action/citation_signature","submit_replication":"https://pith.science/pith/QETKVUJJUEJPRT6GCJQ7YGIKIX/action/replication_record"}},"created_at":"2026-05-17T23:48:08.185626+00:00","updated_at":"2026-05-17T23:48:08.185626+00:00"}