{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DT3DPHQ5I6UKVGM3CEUF7KML62","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":"c2e042dc53c9dd0b3f3298b25b3f18e6ce639d38e80e0c78cad64dfce915f694","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-10T12:49:22Z","title_canon_sha256":"fae021240e0e16504ffe966b9ffe01aaa62f04bfc635062394a9eafc0134d193"},"schema_version":"1.0","source":{"id":"1910.04522","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.04522","created_at":"2026-07-05T00:11:09Z"},{"alias_kind":"arxiv_version","alias_value":"1910.04522v1","created_at":"2026-07-05T00:11:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.04522","created_at":"2026-07-05T00:11:09Z"},{"alias_kind":"pith_short_12","alias_value":"DT3DPHQ5I6UK","created_at":"2026-07-05T00:11:09Z"},{"alias_kind":"pith_short_16","alias_value":"DT3DPHQ5I6UKVGM3","created_at":"2026-07-05T00:11:09Z"},{"alias_kind":"pith_short_8","alias_value":"DT3DPHQ5","created_at":"2026-07-05T00:11:09Z"}],"graph_snapshots":[{"event_id":"sha256:8dba92ee31ca52be88b48b9fe44999922f33e78898fc2c421dd4d33287b37fb9","target":"graph","created_at":"2026-07-05T00:11:09Z","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/1910.04522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose probabilistic models that can extrapolate learning curves of iterative machine learning algorithms, such as stochastic gradient descent for training deep networks, based on training data with variable-length learning curves. We study instantiations of this framework based on random forests and Bayesian recurrent neural networks. Our experiments show that these models yield better predictions than state-of-the-art models from the hyperparameter optimization literature when extrapolating the performance of neural networks trained with different hyperparameter settings.","authors_text":"Aaron Klein, Frank Hutter, Matilde Gargiani, Stefan Falkner","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-10T12:49:22Z","title":"Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.04522","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":"sha256:634dd85afe110bfca3573da86afa8b166b24c38899b106a8f014f7671ac4ba0a","target":"record","created_at":"2026-07-05T00:11:09Z","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":"c2e042dc53c9dd0b3f3298b25b3f18e6ce639d38e80e0c78cad64dfce915f694","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-10T12:49:22Z","title_canon_sha256":"fae021240e0e16504ffe966b9ffe01aaa62f04bfc635062394a9eafc0134d193"},"schema_version":"1.0","source":{"id":"1910.04522","kind":"arxiv","version":1}},"canonical_sha256":"1cf6379e1d47a8aa999b11285fa98bf6a72a6a063f23ef94cf75ce878f0c1d44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cf6379e1d47a8aa999b11285fa98bf6a72a6a063f23ef94cf75ce878f0c1d44","first_computed_at":"2026-07-05T00:11:09.127095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:11:09.127095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8eS32X9G926B2H0lXgQnnmWxIOQAV9pacZnUdR2Sz3TINqV/R+N1KochjarpSlnKcOUAV0t4UaSNdn8VzY4fAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:11:09.127511Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.04522","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:634dd85afe110bfca3573da86afa8b166b24c38899b106a8f014f7671ac4ba0a","sha256:8dba92ee31ca52be88b48b9fe44999922f33e78898fc2c421dd4d33287b37fb9"],"state_sha256":"aef3b984c4d6d218941298b3c22eee35cdcce1d83626cb397186399b628c9905"}