{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UJRDM2WDDVUZOFLNN4SIPLDGDD","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":"d6ab32ba39699653010c77c3041e4d26d1d098a258b21f3ffe8fdba32f95dc80","cross_cats_sorted":["cs.NA","math.NA","math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-15T19:08:58Z","title_canon_sha256":"9e5b23967091d11d58906ae9ace5da3bde0945b9d9f5dc1dbe1d338724262dd6"},"schema_version":"1.0","source":{"id":"2107.07572","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.07572","created_at":"2026-07-05T04:30:51Z"},{"alias_kind":"arxiv_version","alias_value":"2107.07572v2","created_at":"2026-07-05T04:30:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07572","created_at":"2026-07-05T04:30:51Z"},{"alias_kind":"pith_short_12","alias_value":"UJRDM2WDDVUZ","created_at":"2026-07-05T04:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"UJRDM2WDDVUZOFLN","created_at":"2026-07-05T04:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"UJRDM2WD","created_at":"2026-07-05T04:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:52eb62df57b35ff0b2ad9b7d3cdcc830c83fd029bd02dc297e3ce09158f22b65","target":"graph","created_at":"2026-07-05T04:30:51Z","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/2107.07572/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a globally convergent multilevel training method for deep residual networks (ResNets). The devised method can be seen as a novel variant of the recursive multilevel trust-region (RMTR) method, which operates in hybrid (stochastic-deterministic) settings by adaptively adjusting mini-batch sizes during the training. The multilevel hierarchy and the transfer operators are constructed by exploiting a dynamical system's viewpoint, which interprets forward propagation through the ResNet as a forward Euler discretization of an initial value problem. In contrast to traditional training appr","authors_text":"Alena Kopani\\v{c}\\'akov\\'a, Rolf Krause","cross_cats":["cs.NA","math.NA","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-15T19:08:58Z","title":"Globally Convergent Multilevel Training of Deep Residual Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07572","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":"sha256:96781aff3cf96e22a884baf4a30941f5515fbef32701ec37331a1da17313f7be","target":"record","created_at":"2026-07-05T04:30:51Z","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":"d6ab32ba39699653010c77c3041e4d26d1d098a258b21f3ffe8fdba32f95dc80","cross_cats_sorted":["cs.NA","math.NA","math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-15T19:08:58Z","title_canon_sha256":"9e5b23967091d11d58906ae9ace5da3bde0945b9d9f5dc1dbe1d338724262dd6"},"schema_version":"1.0","source":{"id":"2107.07572","kind":"arxiv","version":2}},"canonical_sha256":"a262366ac31d6997156d6f2487ac6618f88d325fee23110e87895b9892766afc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a262366ac31d6997156d6f2487ac6618f88d325fee23110e87895b9892766afc","first_computed_at":"2026-07-05T04:30:51.838004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:30:51.838004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Cvoo86hrABgIF5oVXnXKkc1V85jo0cqw8O9R7u9CETfluPQXaggkFCQ3OTHXB+tJ1CvIrojFS86ggapzzeRRDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:30:51.838393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.07572","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96781aff3cf96e22a884baf4a30941f5515fbef32701ec37331a1da17313f7be","sha256:52eb62df57b35ff0b2ad9b7d3cdcc830c83fd029bd02dc297e3ce09158f22b65"],"state_sha256":"b0a6604a63171b95db48ccff6243ca13f3fb995c65186925b35d45758a90a5ed"}