{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5VQXUL6KBXRDVAYDYS7OOFKTRF","short_pith_number":"pith:5VQXUL6K","canonical_record":{"source":{"id":"2302.00441","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-01T13:39:07Z","cross_cats_sorted":[],"title_canon_sha256":"b002326e5503140f4b477f0faf0f4b6a01c594675339fbf730795b5585a9835c","abstract_canon_sha256":"b45b85147e69076d5bc50a62ff8f0ca7baf613520c4c1053fc75a160b3a88c48"},"schema_version":"1.0"},"canonical_sha256":"ed617a2fca0de23a8303c4bee71553895102257ce8296886f261e747ca6b58a5","source":{"kind":"arxiv","id":"2302.00441","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.00441","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2302.00441v3","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00441","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"5VQXUL6KBXRD","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"5VQXUL6KBXRDVAYD","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"5VQXUL6K","created_at":"2026-07-05T07:04:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5VQXUL6KBXRDVAYDYS7OOFKTRF","target":"record","payload":{"canonical_record":{"source":{"id":"2302.00441","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-01T13:39:07Z","cross_cats_sorted":[],"title_canon_sha256":"b002326e5503140f4b477f0faf0f4b6a01c594675339fbf730795b5585a9835c","abstract_canon_sha256":"b45b85147e69076d5bc50a62ff8f0ca7baf613520c4c1053fc75a160b3a88c48"},"schema_version":"1.0"},"canonical_sha256":"ed617a2fca0de23a8303c4bee71553895102257ce8296886f261e747ca6b58a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:45.099495Z","signature_b64":"BeQCg1lUyJyqI6TsIG6o0wY2xAll7czLiT9FqdiqE0OayX1i/sr5+Rk5Wl/eKo59/YljpwKrGAkQYjhzrNayCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed617a2fca0de23a8303c4bee71553895102257ce8296886f261e747ca6b58a5","last_reissued_at":"2026-07-05T07:04:45.099074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:45.099074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.00441","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:04:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZCTb/VPUDBdBgJ3UanvN5axv3dW4AXfrwH2WeDL0TdNFhTx+fjSYBAISlZxkDqsua4xT3T2XXaqSry/dYNpZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T02:36:15.914579Z"},"content_sha256":"4d92099202e6d075d8d8136535edf849dc9e5696467d61aaf5a11c840c8dbb96","schema_version":"1.0","event_id":"sha256:4d92099202e6d075d8d8136535edf849dc9e5696467d61aaf5a11c840c8dbb96"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5VQXUL6KBXRDVAYDYS7OOFKTRF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Laws for Hyperparameter Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arlind Kadra, Josif Grabocka, Maciej Janowski, Martin Wistuba","submitted_at":"2023-02-01T13:39:07Z","abstract_excerpt":"Hyperparameter optimization is an important subfield of machine learning that focuses on tuning the hyperparameters of a chosen algorithm to achieve peak performance. Recently, there has been a stream of methods that tackle the issue of hyperparameter optimization, however, most of the methods do not exploit the dominant power law nature of learning curves for Bayesian optimization. In this work, we propose Deep Power Laws (DPL), an ensemble of neural network models conditioned to yield predictions that follow a power-law scaling pattern. Our method dynamically decides which configurations to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00441","kind":"arxiv","version":3},"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/2302.00441/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":"2026-07-05T07:04:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TwidQ4o/E4JCwVk1JFpN/WhDiXl14ZdhqVpcwGqVyTvlD9MOlnDAB+1IMvpl8akauB1xWgRSfD+t8QVH4S3eCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-24T02:36:15.915089Z"},"content_sha256":"6deeb5437655a3c2dc5841bd2b232abc1c296186153c020efac9ce76fc1671e2","schema_version":"1.0","event_id":"sha256:6deeb5437655a3c2dc5841bd2b232abc1c296186153c020efac9ce76fc1671e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5VQXUL6KBXRDVAYDYS7OOFKTRF/bundle.json","state_url":"https://pith.science/pith/5VQXUL6KBXRDVAYDYS7OOFKTRF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5VQXUL6KBXRDVAYDYS7OOFKTRF/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":"2026-08-24T02:36:15Z","links":{"resolver":"https://pith.science/pith/5VQXUL6KBXRDVAYDYS7OOFKTRF","bundle":"https://pith.science/pith/5VQXUL6KBXRDVAYDYS7OOFKTRF/bundle.json","state":"https://pith.science/pith/5VQXUL6KBXRDVAYDYS7OOFKTRF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5VQXUL6KBXRDVAYDYS7OOFKTRF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5VQXUL6KBXRDVAYDYS7OOFKTRF","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":"b45b85147e69076d5bc50a62ff8f0ca7baf613520c4c1053fc75a160b3a88c48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-01T13:39:07Z","title_canon_sha256":"b002326e5503140f4b477f0faf0f4b6a01c594675339fbf730795b5585a9835c"},"schema_version":"1.0","source":{"id":"2302.00441","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.00441","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2302.00441v3","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.00441","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"5VQXUL6KBXRD","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"5VQXUL6KBXRDVAYD","created_at":"2026-07-05T07:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"5VQXUL6K","created_at":"2026-07-05T07:04:45Z"}],"graph_snapshots":[{"event_id":"sha256:6deeb5437655a3c2dc5841bd2b232abc1c296186153c020efac9ce76fc1671e2","target":"graph","created_at":"2026-07-05T07:04:45Z","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/2302.00441/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hyperparameter optimization is an important subfield of machine learning that focuses on tuning the hyperparameters of a chosen algorithm to achieve peak performance. Recently, there has been a stream of methods that tackle the issue of hyperparameter optimization, however, most of the methods do not exploit the dominant power law nature of learning curves for Bayesian optimization. In this work, we propose Deep Power Laws (DPL), an ensemble of neural network models conditioned to yield predictions that follow a power-law scaling pattern. Our method dynamically decides which configurations to ","authors_text":"Arlind Kadra, Josif Grabocka, Maciej Janowski, Martin Wistuba","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-01T13:39:07Z","title":"Scaling Laws for Hyperparameter Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.00441","kind":"arxiv","version":3},"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":"sha256:4d92099202e6d075d8d8136535edf849dc9e5696467d61aaf5a11c840c8dbb96","target":"record","created_at":"2026-07-05T07:04:45Z","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":"b45b85147e69076d5bc50a62ff8f0ca7baf613520c4c1053fc75a160b3a88c48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-01T13:39:07Z","title_canon_sha256":"b002326e5503140f4b477f0faf0f4b6a01c594675339fbf730795b5585a9835c"},"schema_version":"1.0","source":{"id":"2302.00441","kind":"arxiv","version":3}},"canonical_sha256":"ed617a2fca0de23a8303c4bee71553895102257ce8296886f261e747ca6b58a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed617a2fca0de23a8303c4bee71553895102257ce8296886f261e747ca6b58a5","first_computed_at":"2026-07-05T07:04:45.099074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:45.099074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BeQCg1lUyJyqI6TsIG6o0wY2xAll7czLiT9FqdiqE0OayX1i/sr5+Rk5Wl/eKo59/YljpwKrGAkQYjhzrNayCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:45.099495Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.00441","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d92099202e6d075d8d8136535edf849dc9e5696467d61aaf5a11c840c8dbb96","sha256:6deeb5437655a3c2dc5841bd2b232abc1c296186153c020efac9ce76fc1671e2"],"state_sha256":"a2a9eebae6991f65f9c270449f42dc23e6ee4c0d79a624e33153c0a7929525ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bL/lPXUT4DWpFBLX3LJYXCnBedgrEqqenD6WADoEMZdkoiqVfNRJQs/3oobk5DlhjB7I/CMWJ5iNo2O/JzW5Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-24T02:36:15.919888Z","bundle_sha256":"0198900534d08079c561b3dc2d7c77e13b8e5bd9e6860ac65eead592b36cfacb"}}