{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:SZ32ZXJZ5WEO3OCJNKVKHZAH4A","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":"097e11ec9ab7130cd98086be71d82fc13f286191a073c906253784ec0fb59855","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-09T20:56:03Z","title_canon_sha256":"7958c90213517a3bda6f77fc4cdb280b493287a9d81d4cccea2d80835da4036f"},"schema_version":"1.0","source":{"id":"1804.03235","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.03235","created_at":"2026-07-05T01:28:39Z"},{"alias_kind":"arxiv_version","alias_value":"1804.03235v2","created_at":"2026-07-05T01:28:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.03235","created_at":"2026-07-05T01:28:39Z"},{"alias_kind":"pith_short_12","alias_value":"SZ32ZXJZ5WEO","created_at":"2026-07-05T01:28:39Z"},{"alias_kind":"pith_short_16","alias_value":"SZ32ZXJZ5WEO3OCJ","created_at":"2026-07-05T01:28:39Z"},{"alias_kind":"pith_short_8","alias_value":"SZ32ZXJZ","created_at":"2026-07-05T01:28:39Z"}],"graph_snapshots":[{"event_id":"sha256:551938dc79e8337de51076034de800559608e8dd0563265cf9a6148dbd76aefa","target":"graph","created_at":"2026-07-05T01:28:39Z","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/1804.03235/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Techniques such as ensembling and distillation promise model quality improvements when paired with almost any base model. However, due to increased test-time cost (for ensembles) and increased complexity of the training pipeline (for distillation), these techniques are challenging to use in industrial settings. In this paper we explore a variant of distillation which is relatively straightforward to use as it does not require a complicated multi-stage setup or many new hyperparameters. Our first claim is that online distillation enables us to use extra parallelism to fit very large datasets ab","authors_text":"Alexandre Passos, Gabriel Pereyra, Geoffrey E. Hinton, George E. Dahl, Robert Ormandi, Rohan Anil","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-09T20:56:03Z","title":"Large scale distributed neural network training through online distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.03235","kind":"arxiv","version":2},"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:ad15e94ff580ffbc07d50d499284f4ac3270cd33a9149b025b128bb5e1b47e42","target":"record","created_at":"2026-07-05T01:28:39Z","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":"097e11ec9ab7130cd98086be71d82fc13f286191a073c906253784ec0fb59855","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-09T20:56:03Z","title_canon_sha256":"7958c90213517a3bda6f77fc4cdb280b493287a9d81d4cccea2d80835da4036f"},"schema_version":"1.0","source":{"id":"1804.03235","kind":"arxiv","version":2}},"canonical_sha256":"9677acdd39ed88edb8496aaaa3e407e02c0cec12b8acd730cb7f7aad24e99de8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9677acdd39ed88edb8496aaaa3e407e02c0cec12b8acd730cb7f7aad24e99de8","first_computed_at":"2026-07-05T01:28:39.924832Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:28:39.924832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vbM2NIHzcOJWUqtFOEFXrdXmXZI1hnPne1wCTvDbI88dGubF3CUE7r4hwwEem+Utf1AkhxDvs5QvPIkHZfBpBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:28:39.925342Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.03235","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad15e94ff580ffbc07d50d499284f4ac3270cd33a9149b025b128bb5e1b47e42","sha256:551938dc79e8337de51076034de800559608e8dd0563265cf9a6148dbd76aefa"],"state_sha256":"724619b2e75e81f34279ecf85c3b872e3e7432f1cab6d4016ea6b83b87ee7413"}