{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OBFWZHGW7IYO4EJVRDHKF46PTZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7a0ebfa4f30d09f55f0a37687861e6957b5215ed28d6803b1908a65c376ccd47","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-05-21T01:49:51Z","title_canon_sha256":"ef3b1552cbc3b3f174485d14a97d4c81d250c2ba73bd5f888b6e9a46079aa2d7"},"schema_version":"1.0","source":{"id":"2005.10419","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.10419","created_at":"2026-07-05T01:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2005.10419v1","created_at":"2026-07-05T01:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.10419","created_at":"2026-07-05T01:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"OBFWZHGW7IYO","created_at":"2026-07-05T01:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"OBFWZHGW7IYO4EJV","created_at":"2026-07-05T01:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"OBFWZHGW","created_at":"2026-07-05T01:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:c3cc76b5b0cc7c38934ffc3fff613762a923bfd3bd63c07f2e3dc9f5b0964c99","target":"graph","created_at":"2026-07-05T01:04:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2005.10419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge distillation is a technique for improving the performance of a simple \"student\" model by replacing its one-hot training labels with a distribution over labels obtained from a complex \"teacher\" model. While this simple approach has proven widely effective, a basic question remains unresolved: why does distillation help? In this paper, we present a statistical perspective on distillation which addresses this question, and provides a novel connection to extreme multiclass retrieval techniques. Our core observation is that the teacher seeks to estimate the underlying (Bayes) class-probab","authors_text":"Aditya Krishna Menon, Ankit Singh Rawat, Sanjiv Kumar, Sashank J. Reddi, Seungyeon Kim","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-05-21T01:49:51Z","title":"Why distillation helps: a statistical perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.10419","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d8ed96443e82ad739dbd3619fbf411a62a2e1e53f560a6c492840b12e0240685","target":"record","created_at":"2026-07-05T01:04:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7a0ebfa4f30d09f55f0a37687861e6957b5215ed28d6803b1908a65c376ccd47","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-05-21T01:49:51Z","title_canon_sha256":"ef3b1552cbc3b3f174485d14a97d4c81d250c2ba73bd5f888b6e9a46079aa2d7"},"schema_version":"1.0","source":{"id":"2005.10419","kind":"arxiv","version":1}},"canonical_sha256":"704b6c9cd6fa30ee113588cea2f3cf9e57a815eb63fbf1a0a2d70f9d1f8b2c03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"704b6c9cd6fa30ee113588cea2f3cf9e57a815eb63fbf1a0a2d70f9d1f8b2c03","first_computed_at":"2026-07-05T01:04:53.966470Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:04:53.966470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dAc8NHktJ/Bv05LRBuSj6bKvtrgKosT6T/qZsHuycFN6SSZCw80xwZzcu1pWhXN7ziHiRCFBd1xNEZUPVkjMCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:04:53.966899Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.10419","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8ed96443e82ad739dbd3619fbf411a62a2e1e53f560a6c492840b12e0240685","sha256:c3cc76b5b0cc7c38934ffc3fff613762a923bfd3bd63c07f2e3dc9f5b0964c99"],"state_sha256":"3afe281d668d73139312c91e3de311b3080b3da5f9761c438e0523a36c85e937"}