{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DHD2GUN2CMUIFDYQKEVPBL4GZP","short_pith_number":"pith:DHD2GUN2","canonical_record":{"source":{"id":"2105.09821","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-20T15:13:30Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"78d46832b109657581a70871425bcea59e256e03cd51f55e65d890a5921da5b5","abstract_canon_sha256":"b6a92caea93a452594365c29e77135a73545e751bc68cfb974c244223acb1687"},"schema_version":"1.0"},"canonical_sha256":"19c7a351ba1328828f10512af0af86cbd0f201adaf0f0f6091dedfe64b424311","source":{"kind":"arxiv","id":"2105.09821","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.09821","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"arxiv_version","alias_value":"2105.09821v2","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.09821","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"pith_short_12","alias_value":"DHD2GUN2CMUI","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"pith_short_16","alias_value":"DHD2GUN2CMUIFDYQ","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"pith_short_8","alias_value":"DHD2GUN2","created_at":"2026-07-05T03:24:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DHD2GUN2CMUIFDYQKEVPBL4GZP","target":"record","payload":{"canonical_record":{"source":{"id":"2105.09821","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-20T15:13:30Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"78d46832b109657581a70871425bcea59e256e03cd51f55e65d890a5921da5b5","abstract_canon_sha256":"b6a92caea93a452594365c29e77135a73545e751bc68cfb974c244223acb1687"},"schema_version":"1.0"},"canonical_sha256":"19c7a351ba1328828f10512af0af86cbd0f201adaf0f0f6091dedfe64b424311","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:29.717801Z","signature_b64":"GE3WIp49snP5B0oHRzkEF3njG8UVBJlI56PQ6guJ9fFJgjK3ykuHXRJmmADs7JaIdYQpQX9L0PW6I9HVlIiEAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19c7a351ba1328828f10512af0af86cbd0f201adaf0f0f6091dedfe64b424311","last_reissued_at":"2026-07-05T03:24:29.717320Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:29.717320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.09821","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:24:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pZHalVBX/lmWHNeOltPNjRjIuAFWfbTn8oXr7cS9MxkwOHquGjAmVQxugbFRdd7/67CifGCIZrysA7urQ2/WCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T21:03:32.700161Z"},"content_sha256":"cdf5af2f46f23f75b258e4dee25afd2aff714b58295f511b7f06b066f43dc356","schema_version":"1.0","event_id":"sha256:cdf5af2f46f23f75b258e4dee25afd2aff714b58295f511b7f06b066f43dc356"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DHD2GUN2CMUIFDYQKEVPBL4GZP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DEHB: Evolutionary Hyperband for Scalable, Robust and Efficient Hyperparameter Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Frank Hutter, Neeratyoy Mallik, Noor Awad","submitted_at":"2021-05-20T15:13:30Z","abstract_excerpt":"Modern machine learning algorithms crucially rely on several design decisions to achieve strong performance, making the problem of Hyperparameter Optimization (HPO) more important than ever. Here, we combine the advantages of the popular bandit-based HPO method Hyperband (HB) and the evolutionary search approach of Differential Evolution (DE) to yield a new HPO method which we call DEHB. Comprehensive results on a very broad range of HPO problems, as well as a wide range of tabular benchmarks from neural architecture search, demonstrate that DEHB achieves strong performance far more robustly t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.09821","kind":"arxiv","version":2},"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/2105.09821/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":"2026-07-05T03:24:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UHE5cyRr6gomtZA3jhtjYUMvlA8k10KKtspznWN8VIL566+elMQYvCEzMxz6SB2zOxz2XDK5adzb3O5R2OfVCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-11T21:03:32.700562Z"},"content_sha256":"efe1e68c0249008210425ee081f6df9ab863e98aa833dc56b6b0502f3c724686","schema_version":"1.0","event_id":"sha256:efe1e68c0249008210425ee081f6df9ab863e98aa833dc56b6b0502f3c724686"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DHD2GUN2CMUIFDYQKEVPBL4GZP/bundle.json","state_url":"https://pith.science/pith/DHD2GUN2CMUIFDYQKEVPBL4GZP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DHD2GUN2CMUIFDYQKEVPBL4GZP/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":"2026-07-11T21:03:32Z","links":{"resolver":"https://pith.science/pith/DHD2GUN2CMUIFDYQKEVPBL4GZP","bundle":"https://pith.science/pith/DHD2GUN2CMUIFDYQKEVPBL4GZP/bundle.json","state":"https://pith.science/pith/DHD2GUN2CMUIFDYQKEVPBL4GZP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DHD2GUN2CMUIFDYQKEVPBL4GZP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DHD2GUN2CMUIFDYQKEVPBL4GZP","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":"b6a92caea93a452594365c29e77135a73545e751bc68cfb974c244223acb1687","cross_cats_sorted":["cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-20T15:13:30Z","title_canon_sha256":"78d46832b109657581a70871425bcea59e256e03cd51f55e65d890a5921da5b5"},"schema_version":"1.0","source":{"id":"2105.09821","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.09821","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"arxiv_version","alias_value":"2105.09821v2","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.09821","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"pith_short_12","alias_value":"DHD2GUN2CMUI","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"pith_short_16","alias_value":"DHD2GUN2CMUIFDYQ","created_at":"2026-07-05T03:24:29Z"},{"alias_kind":"pith_short_8","alias_value":"DHD2GUN2","created_at":"2026-07-05T03:24:29Z"}],"graph_snapshots":[{"event_id":"sha256:efe1e68c0249008210425ee081f6df9ab863e98aa833dc56b6b0502f3c724686","target":"graph","created_at":"2026-07-05T03:24:29Z","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/2105.09821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern machine learning algorithms crucially rely on several design decisions to achieve strong performance, making the problem of Hyperparameter Optimization (HPO) more important than ever. Here, we combine the advantages of the popular bandit-based HPO method Hyperband (HB) and the evolutionary search approach of Differential Evolution (DE) to yield a new HPO method which we call DEHB. Comprehensive results on a very broad range of HPO problems, as well as a wide range of tabular benchmarks from neural architecture search, demonstrate that DEHB achieves strong performance far more robustly t","authors_text":"Frank Hutter, Neeratyoy Mallik, Noor Awad","cross_cats":["cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-20T15:13:30Z","title":"DEHB: Evolutionary Hyperband for Scalable, Robust and Efficient Hyperparameter Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.09821","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:cdf5af2f46f23f75b258e4dee25afd2aff714b58295f511b7f06b066f43dc356","target":"record","created_at":"2026-07-05T03:24:29Z","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":"b6a92caea93a452594365c29e77135a73545e751bc68cfb974c244223acb1687","cross_cats_sorted":["cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-20T15:13:30Z","title_canon_sha256":"78d46832b109657581a70871425bcea59e256e03cd51f55e65d890a5921da5b5"},"schema_version":"1.0","source":{"id":"2105.09821","kind":"arxiv","version":2}},"canonical_sha256":"19c7a351ba1328828f10512af0af86cbd0f201adaf0f0f6091dedfe64b424311","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19c7a351ba1328828f10512af0af86cbd0f201adaf0f0f6091dedfe64b424311","first_computed_at":"2026-07-05T03:24:29.717320Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:29.717320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GE3WIp49snP5B0oHRzkEF3njG8UVBJlI56PQ6guJ9fFJgjK3ykuHXRJmmADs7JaIdYQpQX9L0PW6I9HVlIiEAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:29.717801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.09821","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdf5af2f46f23f75b258e4dee25afd2aff714b58295f511b7f06b066f43dc356","sha256:efe1e68c0249008210425ee081f6df9ab863e98aa833dc56b6b0502f3c724686"],"state_sha256":"f8c8629c2a3053f5db34a4595e93087bc67cafbeae19bfe0d7f01f5cf92648c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8sGuqnMh2DLUgnx2RlqwboSWGs2FXD4n+BmlTl84G8vNsFfZpmS+wPqsV+/0OfRRgALvvpBfpmnVSelS71KqCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-11T21:03:32.702717Z","bundle_sha256":"94ac5c05ca8f193a814cf84412fa33e449a9b582241048e18b34839e89ba3b56"}}