{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:KJDBXXD62OJMRENOMA6QLATRLG","short_pith_number":"pith:KJDBXXD6","canonical_record":{"source":{"id":"1511.06727","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-20T19:10:16Z","cross_cats_sorted":[],"title_canon_sha256":"63e19169786e02c1487b7dd8f4813711dc68464d701343b41b9c8a426c7bb98d","abstract_canon_sha256":"1b19529f09a78032fe1579421dd6286762d809d55e17ab730af824a1ef8e14b9"},"schema_version":"1.0"},"canonical_sha256":"52461bdc7ed392c891ae603d05827159b334be00260dfc94664e68291ab872eb","source":{"kind":"arxiv","id":"1511.06727","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06727","created_at":"2026-05-18T01:12:19Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06727v3","created_at":"2026-05-18T01:12:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06727","created_at":"2026-05-18T01:12:19Z"},{"alias_kind":"pith_short_12","alias_value":"KJDBXXD62OJM","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"KJDBXXD62OJMRENO","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"KJDBXXD6","created_at":"2026-05-18T12:29:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:KJDBXXD62OJMRENOMA6QLATRLG","target":"record","payload":{"canonical_record":{"source":{"id":"1511.06727","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-20T19:10:16Z","cross_cats_sorted":[],"title_canon_sha256":"63e19169786e02c1487b7dd8f4813711dc68464d701343b41b9c8a426c7bb98d","abstract_canon_sha256":"1b19529f09a78032fe1579421dd6286762d809d55e17ab730af824a1ef8e14b9"},"schema_version":"1.0"},"canonical_sha256":"52461bdc7ed392c891ae603d05827159b334be00260dfc94664e68291ab872eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:19.879368Z","signature_b64":"RQqzCf9mh3/6i3X4RL4pevt3JoE0crhHu4lCNpxaMcR59G31upPkLhg9JsYnsi1TueUibtwBxmHSJptOebpoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52461bdc7ed392c891ae603d05827159b334be00260dfc94664e68291ab872eb","last_reissued_at":"2026-05-18T01:12:19.878987Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:19.878987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.06727","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":"2026-05-18T01:12:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MPsexM3ib6DL+dY4D5/+PWGICLO0WJMFzLn03V82yNJwTTN0VUsVjQPIzB0Ej7sYEqwEdTaUXfCaF/NEkwV3AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T02:24:57.734652Z"},"content_sha256":"61d3aa0b7d0a18b8d7641ca6532172ae9bcab878cbddf8ceb43e6f25c130da08","schema_version":"1.0","event_id":"sha256:61d3aa0b7d0a18b8d7641ca6532172ae9bcab878cbddf8ceb43e6f25c130da08"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:KJDBXXD62OJMRENOMA6QLATRLG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jelena Luketina, Klaus Greff, Mathias Berglund, Tapani Raiko","submitted_at":"2015-11-20T19:10:16Z","abstract_excerpt":"Hyperparameter selection generally relies on running multiple full training trials, with selection based on validation set performance. We propose a gradient-based approach for locally adjusting hyperparameters during training of the model. Hyperparameters are adjusted so as to make the model parameter gradients, and hence updates, more advantageous for the validation cost. We explore the approach for tuning regularization hyperparameters and find that in experiments on MNIST, SVHN and CIFAR-10, the resulting regularization levels are within the optimal regions. The additional computational co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06727","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":""},"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":"2026-05-18T01:12:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q39wZzTKFVMun1SebuTvaeGFANvmuhBEu1K76eWjHKhRTyZ+nSHM3bz72qJ1dXLsGs3yKvA/PrgsAZnKff1KDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-20T02:24:57.734993Z"},"content_sha256":"26c39c3d95b0aa0c267d2e093e4fefa0602b8142a1661f27488e93cc10347bf4","schema_version":"1.0","event_id":"sha256:26c39c3d95b0aa0c267d2e093e4fefa0602b8142a1661f27488e93cc10347bf4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJDBXXD62OJMRENOMA6QLATRLG/bundle.json","state_url":"https://pith.science/pith/KJDBXXD62OJMRENOMA6QLATRLG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJDBXXD62OJMRENOMA6QLATRLG/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":"2026-06-20T02:24:57Z","links":{"resolver":"https://pith.science/pith/KJDBXXD62OJMRENOMA6QLATRLG","bundle":"https://pith.science/pith/KJDBXXD62OJMRENOMA6QLATRLG/bundle.json","state":"https://pith.science/pith/KJDBXXD62OJMRENOMA6QLATRLG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJDBXXD62OJMRENOMA6QLATRLG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:KJDBXXD62OJMRENOMA6QLATRLG","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":"1b19529f09a78032fe1579421dd6286762d809d55e17ab730af824a1ef8e14b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-20T19:10:16Z","title_canon_sha256":"63e19169786e02c1487b7dd8f4813711dc68464d701343b41b9c8a426c7bb98d"},"schema_version":"1.0","source":{"id":"1511.06727","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06727","created_at":"2026-05-18T01:12:19Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06727v3","created_at":"2026-05-18T01:12:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06727","created_at":"2026-05-18T01:12:19Z"},{"alias_kind":"pith_short_12","alias_value":"KJDBXXD62OJM","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_16","alias_value":"KJDBXXD62OJMRENO","created_at":"2026-05-18T12:29:29Z"},{"alias_kind":"pith_short_8","alias_value":"KJDBXXD6","created_at":"2026-05-18T12:29:29Z"}],"graph_snapshots":[{"event_id":"sha256:26c39c3d95b0aa0c267d2e093e4fefa0602b8142a1661f27488e93cc10347bf4","target":"graph","created_at":"2026-05-18T01:12:19Z","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 selection generally relies on running multiple full training trials, with selection based on validation set performance. We propose a gradient-based approach for locally adjusting hyperparameters during training of the model. Hyperparameters are adjusted so as to make the model parameter gradients, and hence updates, more advantageous for the validation cost. We explore the approach for tuning regularization hyperparameters and find that in experiments on MNIST, SVHN and CIFAR-10, the resulting regularization levels are within the optimal regions. The additional computational co","authors_text":"Jelena Luketina, Klaus Greff, Mathias Berglund, Tapani Raiko","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-20T19:10:16Z","title":"Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06727","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":"sha256:61d3aa0b7d0a18b8d7641ca6532172ae9bcab878cbddf8ceb43e6f25c130da08","target":"record","created_at":"2026-05-18T01:12:19Z","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":"1b19529f09a78032fe1579421dd6286762d809d55e17ab730af824a1ef8e14b9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-20T19:10:16Z","title_canon_sha256":"63e19169786e02c1487b7dd8f4813711dc68464d701343b41b9c8a426c7bb98d"},"schema_version":"1.0","source":{"id":"1511.06727","kind":"arxiv","version":3}},"canonical_sha256":"52461bdc7ed392c891ae603d05827159b334be00260dfc94664e68291ab872eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52461bdc7ed392c891ae603d05827159b334be00260dfc94664e68291ab872eb","first_computed_at":"2026-05-18T01:12:19.878987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:19.878987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RQqzCf9mh3/6i3X4RL4pevt3JoE0crhHu4lCNpxaMcR59G31upPkLhg9JsYnsi1TueUibtwBxmHSJptOebpoDA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:19.879368Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.06727","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61d3aa0b7d0a18b8d7641ca6532172ae9bcab878cbddf8ceb43e6f25c130da08","sha256:26c39c3d95b0aa0c267d2e093e4fefa0602b8142a1661f27488e93cc10347bf4"],"state_sha256":"25002796d174e4a1e5995871e36d73a5fe19895bd35b0ec73fe00322327aff17"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T319RWCsOwLM4PcAK8Ibt1PuOX5i2t0dGp21hWxgCHMXsvfKW8s3g4oQrZQXGZrt49SkFjwNRnvm+zkVj/r9CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-20T02:24:57.736867Z","bundle_sha256":"8fef4af6722a95da713bfcf82b929074152a61d03ac8ec8e34b752d3b93df41b"}}