{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:DY7MWLHE57L356JACJNKW22BYD","short_pith_number":"pith:DY7MWLHE","canonical_record":{"source":{"id":"1903.03088","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-07T18:26:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f583d281fc8ec4e0442b044fd0e3654e51002e3921acb1696fabfc33a7e5d3d3","abstract_canon_sha256":"60162ffe65299b5f100bd09cfdda781f27f92ba707275a5a03c88d044e6411ed"},"schema_version":"1.0"},"canonical_sha256":"1e3ecb2ce4efd7bef920125aab6b41c0dd4e56b433f3d7d5c58593929315b8f3","source":{"kind":"arxiv","id":"1903.03088","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.03088","created_at":"2026-05-17T23:51:50Z"},{"alias_kind":"arxiv_version","alias_value":"1903.03088v1","created_at":"2026-05-17T23:51:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03088","created_at":"2026-05-17T23:51:50Z"},{"alias_kind":"pith_short_12","alias_value":"DY7MWLHE57L3","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DY7MWLHE57L356JA","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DY7MWLHE","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:DY7MWLHE57L356JACJNKW22BYD","target":"record","payload":{"canonical_record":{"source":{"id":"1903.03088","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-07T18:26:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f583d281fc8ec4e0442b044fd0e3654e51002e3921acb1696fabfc33a7e5d3d3","abstract_canon_sha256":"60162ffe65299b5f100bd09cfdda781f27f92ba707275a5a03c88d044e6411ed"},"schema_version":"1.0"},"canonical_sha256":"1e3ecb2ce4efd7bef920125aab6b41c0dd4e56b433f3d7d5c58593929315b8f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:50.143513Z","signature_b64":"FrIvegQyM9uzBqzzJ9OdSMyAZPEjvqGWh7FYD5OqvxCN6UPD8t4QNzd6rtIClOU/6jFy3Q3/2Hw6T1ZF+M+2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e3ecb2ce4efd7bef920125aab6b41c0dd4e56b433f3d7d5c58593929315b8f3","last_reissued_at":"2026-05-17T23:51:50.142842Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:50.142842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.03088","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":"2026-05-17T23:51:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KNrxDwbmlOiyC5raI1EXT7Nc3T4RtzlbpsFzuzkFJzhdJ1tI+BjSnf9xkhOx4A4dBhUHZWJ6JOGM2DGcKwZCBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T18:12:13.859454Z"},"content_sha256":"c6cfd8199a152f401ae66c198ee6d3e803a2a09bcef770fa4d3605d0f80352e8","schema_version":"1.0","event_id":"sha256:c6cfd8199a152f401ae66c198ee6d3e803a2a09bcef770fa4d3605d0f80352e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:DY7MWLHE57L356JACJNKW22BYD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Duvenaud, Jon Lorraine, Matthew MacKay, Paul Vicol, Roger Grosse","submitted_at":"2019-03-07T18:26:46Z","abstract_excerpt":"Hyperparameter optimization can be formulated as a bilevel optimization problem, where the optimal parameters on the training set depend on the hyperparameters. We aim to adapt regularization hyperparameters for neural networks by fitting compact approximations to the best-response function, which maps hyperparameters to optimal weights and biases. We show how to construct scalable best-response approximations for neural networks by modeling the best-response as a single network whose hidden units are gated conditionally on the regularizer. We justify this approximation by showing the exact be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03088","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":""},"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":"2026-05-17T23:51:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3lD+4MC2VhtHReDv2QEbP672O22gBCFy3yb8CwEUD9aWrI2cfuu8YRc7OxE1RUbm0xXMwtL6Pg5S+Ob8JNnoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T18:12:13.860031Z"},"content_sha256":"ebca081f3483e6ab38b42f250ae9c4fad9215721105f9deedd196345fabd22f5","schema_version":"1.0","event_id":"sha256:ebca081f3483e6ab38b42f250ae9c4fad9215721105f9deedd196345fabd22f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DY7MWLHE57L356JACJNKW22BYD/bundle.json","state_url":"https://pith.science/pith/DY7MWLHE57L356JACJNKW22BYD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DY7MWLHE57L356JACJNKW22BYD/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":"2026-05-21T18:12:13Z","links":{"resolver":"https://pith.science/pith/DY7MWLHE57L356JACJNKW22BYD","bundle":"https://pith.science/pith/DY7MWLHE57L356JACJNKW22BYD/bundle.json","state":"https://pith.science/pith/DY7MWLHE57L356JACJNKW22BYD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DY7MWLHE57L356JACJNKW22BYD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DY7MWLHE57L356JACJNKW22BYD","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":"60162ffe65299b5f100bd09cfdda781f27f92ba707275a5a03c88d044e6411ed","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-07T18:26:46Z","title_canon_sha256":"f583d281fc8ec4e0442b044fd0e3654e51002e3921acb1696fabfc33a7e5d3d3"},"schema_version":"1.0","source":{"id":"1903.03088","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.03088","created_at":"2026-05-17T23:51:50Z"},{"alias_kind":"arxiv_version","alias_value":"1903.03088v1","created_at":"2026-05-17T23:51:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03088","created_at":"2026-05-17T23:51:50Z"},{"alias_kind":"pith_short_12","alias_value":"DY7MWLHE57L3","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DY7MWLHE57L356JA","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DY7MWLHE","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:ebca081f3483e6ab38b42f250ae9c4fad9215721105f9deedd196345fabd22f5","target":"graph","created_at":"2026-05-17T23:51:50Z","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"},"paper":{"abstract_excerpt":"Hyperparameter optimization can be formulated as a bilevel optimization problem, where the optimal parameters on the training set depend on the hyperparameters. We aim to adapt regularization hyperparameters for neural networks by fitting compact approximations to the best-response function, which maps hyperparameters to optimal weights and biases. We show how to construct scalable best-response approximations for neural networks by modeling the best-response as a single network whose hidden units are gated conditionally on the regularizer. We justify this approximation by showing the exact be","authors_text":"David Duvenaud, Jon Lorraine, Matthew MacKay, Paul Vicol, Roger Grosse","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-07T18:26:46Z","title":"Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03088","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:c6cfd8199a152f401ae66c198ee6d3e803a2a09bcef770fa4d3605d0f80352e8","target":"record","created_at":"2026-05-17T23:51:50Z","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":"60162ffe65299b5f100bd09cfdda781f27f92ba707275a5a03c88d044e6411ed","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-07T18:26:46Z","title_canon_sha256":"f583d281fc8ec4e0442b044fd0e3654e51002e3921acb1696fabfc33a7e5d3d3"},"schema_version":"1.0","source":{"id":"1903.03088","kind":"arxiv","version":1}},"canonical_sha256":"1e3ecb2ce4efd7bef920125aab6b41c0dd4e56b433f3d7d5c58593929315b8f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e3ecb2ce4efd7bef920125aab6b41c0dd4e56b433f3d7d5c58593929315b8f3","first_computed_at":"2026-05-17T23:51:50.142842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:50.142842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FrIvegQyM9uzBqzzJ9OdSMyAZPEjvqGWh7FYD5OqvxCN6UPD8t4QNzd6rtIClOU/6jFy3Q3/2Hw6T1ZF+M+2Cg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:50.143513Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.03088","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6cfd8199a152f401ae66c198ee6d3e803a2a09bcef770fa4d3605d0f80352e8","sha256:ebca081f3483e6ab38b42f250ae9c4fad9215721105f9deedd196345fabd22f5"],"state_sha256":"bf4d49fc41216d081060fbc49b25da3db9bf8d5ac30dd58d2bc7ad910f5f66e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wYD0wBNGT2dEVW1NjmjH4CkxGdE9rrT1b/PsVFJM+6WhI4WkGN6eAaFJuH8owf9q/zc9jZqOxCpkoIkpykxABw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T18:12:13.862197Z","bundle_sha256":"3212f7c1c8d6138cd4e98d530deee233f5cd04fff36b3c59828c00c44100b58d"}}