{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:O5IZPS6D4I7U4JM2IFVQ5FJYT7","short_pith_number":"pith:O5IZPS6D","canonical_record":{"source":{"id":"2006.15602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-28T13:34:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9b22c93b7d364716b8211ea084addaf5382740fe80e25b65d1c92fab70f68a0e","abstract_canon_sha256":"61d41461f0ab77484f9844efccbfdde239354a939d5c054b13f4551adbc9be0a"},"schema_version":"1.0"},"canonical_sha256":"775197cbc3e23f4e259a416b0e95389fccc2f41093edd7f4ef04dc0621774c17","source":{"kind":"arxiv","id":"2006.15602","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.15602","created_at":"2026-07-05T01:14:07Z"},{"alias_kind":"arxiv_version","alias_value":"2006.15602v1","created_at":"2026-07-05T01:14:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15602","created_at":"2026-07-05T01:14:07Z"},{"alias_kind":"pith_short_12","alias_value":"O5IZPS6D4I7U","created_at":"2026-07-05T01:14:07Z"},{"alias_kind":"pith_short_16","alias_value":"O5IZPS6D4I7U4JM2","created_at":"2026-07-05T01:14:07Z"},{"alias_kind":"pith_short_8","alias_value":"O5IZPS6D","created_at":"2026-07-05T01:14:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:O5IZPS6D4I7U4JM2IFVQ5FJYT7","target":"record","payload":{"canonical_record":{"source":{"id":"2006.15602","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-28T13:34:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9b22c93b7d364716b8211ea084addaf5382740fe80e25b65d1c92fab70f68a0e","abstract_canon_sha256":"61d41461f0ab77484f9844efccbfdde239354a939d5c054b13f4551adbc9be0a"},"schema_version":"1.0"},"canonical_sha256":"775197cbc3e23f4e259a416b0e95389fccc2f41093edd7f4ef04dc0621774c17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:14:07.321340Z","signature_b64":"ck8zB9IwwkGRJhPBV7StMZBSp16U5ehTIqaCC6ksJh3KL9MjjyjwklIMHRVVWWl2Ps8IReKm8i0o4vyqadBGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"775197cbc3e23f4e259a416b0e95389fccc2f41093edd7f4ef04dc0621774c17","last_reissued_at":"2026-07-05T01:14:07.320912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:14:07.320912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.15602","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:14:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8vJDCIEX5YfUHwKXZSyiQbQIzqi1FS9jRc0cY1gymxuNlpCiuJ+jeDPhPE8mhGng3IsVe4vDOE6TtuCvEd35Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:18:08.956769Z"},"content_sha256":"e4f9dc645011127017078ef8ae8a69f222ea22cc669bf96b44e3d97ca9dc09e5","schema_version":"1.0","event_id":"sha256:e4f9dc645011127017078ef8ae8a69f222ea22cc669bf96b44e3d97ca9dc09e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:O5IZPS6D4I7U4JM2IFVQ5FJYT7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Multilevel Approach to Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alena Kopani\\v{c}\\'akov\\'a, Rolf Krause, Vanessa Braglia","submitted_at":"2020-06-28T13:34:48Z","abstract_excerpt":"We propose a novel training method based on nonlinear multilevel minimization techniques, commonly used for solving discretized large scale partial differential equations. Our multilevel training method constructs a multilevel hierarchy by reducing the number of samples. The training of the original model is then enhanced by internally training surrogate models constructed with fewer samples. We construct the surrogate models using first-order consistency approach. This gives rise to surrogate models, whose gradients are stochastic estimators of the full gradient, but with reduced variance com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15602","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/2006.15602/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:14:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"svRNgXjaSTEDjzGYMzFpW3re0oOrWn6lT/gATNkn0SiG6oo/M6e3s80hoSH+pktUUl8FrhS0mlRD1nJc3yw0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:18:08.957137Z"},"content_sha256":"8b57707bb238caa1dd0621287441c237d7ff7a15d7d84d9392e7c837c87d1dc9","schema_version":"1.0","event_id":"sha256:8b57707bb238caa1dd0621287441c237d7ff7a15d7d84d9392e7c837c87d1dc9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O5IZPS6D4I7U4JM2IFVQ5FJYT7/bundle.json","state_url":"https://pith.science/pith/O5IZPS6D4I7U4JM2IFVQ5FJYT7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O5IZPS6D4I7U4JM2IFVQ5FJYT7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T11:18:08Z","links":{"resolver":"https://pith.science/pith/O5IZPS6D4I7U4JM2IFVQ5FJYT7","bundle":"https://pith.science/pith/O5IZPS6D4I7U4JM2IFVQ5FJYT7/bundle.json","state":"https://pith.science/pith/O5IZPS6D4I7U4JM2IFVQ5FJYT7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O5IZPS6D4I7U4JM2IFVQ5FJYT7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:O5IZPS6D4I7U4JM2IFVQ5FJYT7","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":"61d41461f0ab77484f9844efccbfdde239354a939d5c054b13f4551adbc9be0a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-28T13:34:48Z","title_canon_sha256":"9b22c93b7d364716b8211ea084addaf5382740fe80e25b65d1c92fab70f68a0e"},"schema_version":"1.0","source":{"id":"2006.15602","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.15602","created_at":"2026-07-05T01:14:07Z"},{"alias_kind":"arxiv_version","alias_value":"2006.15602v1","created_at":"2026-07-05T01:14:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15602","created_at":"2026-07-05T01:14:07Z"},{"alias_kind":"pith_short_12","alias_value":"O5IZPS6D4I7U","created_at":"2026-07-05T01:14:07Z"},{"alias_kind":"pith_short_16","alias_value":"O5IZPS6D4I7U4JM2","created_at":"2026-07-05T01:14:07Z"},{"alias_kind":"pith_short_8","alias_value":"O5IZPS6D","created_at":"2026-07-05T01:14:07Z"}],"graph_snapshots":[{"event_id":"sha256:8b57707bb238caa1dd0621287441c237d7ff7a15d7d84d9392e7c837c87d1dc9","target":"graph","created_at":"2026-07-05T01:14:07Z","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/2006.15602/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel training method based on nonlinear multilevel minimization techniques, commonly used for solving discretized large scale partial differential equations. Our multilevel training method constructs a multilevel hierarchy by reducing the number of samples. The training of the original model is then enhanced by internally training surrogate models constructed with fewer samples. We construct the surrogate models using first-order consistency approach. This gives rise to surrogate models, whose gradients are stochastic estimators of the full gradient, but with reduced variance com","authors_text":"Alena Kopani\\v{c}\\'akov\\'a, Rolf Krause, Vanessa Braglia","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-28T13:34:48Z","title":"A Multilevel Approach to Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15602","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:e4f9dc645011127017078ef8ae8a69f222ea22cc669bf96b44e3d97ca9dc09e5","target":"record","created_at":"2026-07-05T01:14:07Z","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":"61d41461f0ab77484f9844efccbfdde239354a939d5c054b13f4551adbc9be0a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-28T13:34:48Z","title_canon_sha256":"9b22c93b7d364716b8211ea084addaf5382740fe80e25b65d1c92fab70f68a0e"},"schema_version":"1.0","source":{"id":"2006.15602","kind":"arxiv","version":1}},"canonical_sha256":"775197cbc3e23f4e259a416b0e95389fccc2f41093edd7f4ef04dc0621774c17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"775197cbc3e23f4e259a416b0e95389fccc2f41093edd7f4ef04dc0621774c17","first_computed_at":"2026-07-05T01:14:07.320912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:14:07.320912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ck8zB9IwwkGRJhPBV7StMZBSp16U5ehTIqaCC6ksJh3KL9MjjyjwklIMHRVVWWl2Ps8IReKm8i0o4vyqadBGBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:14:07.321340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.15602","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4f9dc645011127017078ef8ae8a69f222ea22cc669bf96b44e3d97ca9dc09e5","sha256:8b57707bb238caa1dd0621287441c237d7ff7a15d7d84d9392e7c837c87d1dc9"],"state_sha256":"9af52c583a090ee370bc2bd82338890bed3b4b37d924bcdaaddd393c5d6877e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dYVLA3hbxsB6DEdIWBSZAK/uNh3l/iMHSEw7GqB5xIuc1DL51tLS0kA/qL9Ldm487ETLDZImpLid3rPuZDj8Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:18:08.959104Z","bundle_sha256":"06efda48f26a85b2711f7f1b092c7f432cfbd7d650cd9ce05ca8cb79854676c0"}}