{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:D5BTKMVMMFIBQTOHKQMFQGA2FO","short_pith_number":"pith:D5BTKMVM","canonical_record":{"source":{"id":"2304.14766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T11:24:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0d12e76c9ab908f3a98fec7783ca3ce67772319890869d3bb3277a72ef6d023f","abstract_canon_sha256":"91cc26583f611617afcea2bd8c12fe86da32071f5a6a081404449a0fb49ef41c"},"schema_version":"1.0"},"canonical_sha256":"1f433532ac6150184dc7541858181a2bbc5a33398900f2da6df90772ee10856e","source":{"kind":"arxiv","id":"2304.14766","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14766","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14766v1","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14766","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"pith_short_12","alias_value":"D5BTKMVMMFIB","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"pith_short_16","alias_value":"D5BTKMVMMFIBQTOH","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"pith_short_8","alias_value":"D5BTKMVM","created_at":"2026-07-05T06:05:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:D5BTKMVMMFIBQTOHKQMFQGA2FO","target":"record","payload":{"canonical_record":{"source":{"id":"2304.14766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T11:24:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0d12e76c9ab908f3a98fec7783ca3ce67772319890869d3bb3277a72ef6d023f","abstract_canon_sha256":"91cc26583f611617afcea2bd8c12fe86da32071f5a6a081404449a0fb49ef41c"},"schema_version":"1.0"},"canonical_sha256":"1f433532ac6150184dc7541858181a2bbc5a33398900f2da6df90772ee10856e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:20.692007Z","signature_b64":"Uwk4ULfM+dYkTpUfA8subi0oLv5CchYf80A/DpgxRS5YEbZdOor9pkdOI6xU+319zZjBplsQVPlz79MNnVgWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f433532ac6150184dc7541858181a2bbc5a33398900f2da6df90772ee10856e","last_reissued_at":"2026-07-05T06:05:20.691653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:20.691653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.14766","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":"2026-07-05T06:05:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eBEN+PWyIOUUbEetzz0T3SMj5HBTkp7erNAOSAZP6HL1wj7PdYpkomhEkMicS0WwBl1gncFMbJVDDg14JvJtAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:07:47.324548Z"},"content_sha256":"fd6630598be4d3d6f35b83a05c829e034d6d98c8a0cf82755590dd444ae3c5df","schema_version":"1.0","event_id":"sha256:fd6630598be4d3d6f35b83a05c829e034d6d98c8a0cf82755590dd444ae3c5df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:D5BTKMVMMFIBQTOHKQMFQGA2FO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hyperparameter Optimization through Neural Network Partitioning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bruno Mlodozeniec, Christos Louizos, Matthias Reisser","submitted_at":"2023-04-28T11:24:41Z","abstract_excerpt":"Well-tuned hyperparameters are crucial for obtaining good generalization behavior in neural networks. They can enforce appropriate inductive biases, regularize the model and improve performance -- especially in the presence of limited data. In this work, we propose a simple and efficient way for optimizing hyperparameters inspired by the marginal likelihood, an optimization objective that requires no validation data. Our method partitions the training data and a neural network model into $K$ data shards and parameter partitions, respectively. Each partition is associated with and optimized onl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14766","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.14766/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":"2026-07-05T06:05:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fvM+7EHxRL/jGqAyPcXIaOZZD3COWCUuQ6NlvCmkyrBobdWrf7LXP0LaySu2w+ZXdGNAjxs430nfXzEfau0XAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:07:47.324932Z"},"content_sha256":"3adf28f6bb51784908c811b5ecbc46166184b58a532ff8587358f7e4cb6f3082","schema_version":"1.0","event_id":"sha256:3adf28f6bb51784908c811b5ecbc46166184b58a532ff8587358f7e4cb6f3082"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D5BTKMVMMFIBQTOHKQMFQGA2FO/bundle.json","state_url":"https://pith.science/pith/D5BTKMVMMFIBQTOHKQMFQGA2FO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D5BTKMVMMFIBQTOHKQMFQGA2FO/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":"2026-07-07T07:07:47Z","links":{"resolver":"https://pith.science/pith/D5BTKMVMMFIBQTOHKQMFQGA2FO","bundle":"https://pith.science/pith/D5BTKMVMMFIBQTOHKQMFQGA2FO/bundle.json","state":"https://pith.science/pith/D5BTKMVMMFIBQTOHKQMFQGA2FO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D5BTKMVMMFIBQTOHKQMFQGA2FO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:D5BTKMVMMFIBQTOHKQMFQGA2FO","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":"91cc26583f611617afcea2bd8c12fe86da32071f5a6a081404449a0fb49ef41c","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T11:24:41Z","title_canon_sha256":"0d12e76c9ab908f3a98fec7783ca3ce67772319890869d3bb3277a72ef6d023f"},"schema_version":"1.0","source":{"id":"2304.14766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14766","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14766v1","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14766","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"pith_short_12","alias_value":"D5BTKMVMMFIB","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"pith_short_16","alias_value":"D5BTKMVMMFIBQTOH","created_at":"2026-07-05T06:05:20Z"},{"alias_kind":"pith_short_8","alias_value":"D5BTKMVM","created_at":"2026-07-05T06:05:20Z"}],"graph_snapshots":[{"event_id":"sha256:3adf28f6bb51784908c811b5ecbc46166184b58a532ff8587358f7e4cb6f3082","target":"graph","created_at":"2026-07-05T06:05:20Z","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/2304.14766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Well-tuned hyperparameters are crucial for obtaining good generalization behavior in neural networks. They can enforce appropriate inductive biases, regularize the model and improve performance -- especially in the presence of limited data. In this work, we propose a simple and efficient way for optimizing hyperparameters inspired by the marginal likelihood, an optimization objective that requires no validation data. Our method partitions the training data and a neural network model into $K$ data shards and parameter partitions, respectively. Each partition is associated with and optimized onl","authors_text":"Bruno Mlodozeniec, Christos Louizos, Matthias Reisser","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T11:24:41Z","title":"Hyperparameter Optimization through Neural Network Partitioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14766","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:fd6630598be4d3d6f35b83a05c829e034d6d98c8a0cf82755590dd444ae3c5df","target":"record","created_at":"2026-07-05T06:05:20Z","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":"91cc26583f611617afcea2bd8c12fe86da32071f5a6a081404449a0fb49ef41c","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T11:24:41Z","title_canon_sha256":"0d12e76c9ab908f3a98fec7783ca3ce67772319890869d3bb3277a72ef6d023f"},"schema_version":"1.0","source":{"id":"2304.14766","kind":"arxiv","version":1}},"canonical_sha256":"1f433532ac6150184dc7541858181a2bbc5a33398900f2da6df90772ee10856e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f433532ac6150184dc7541858181a2bbc5a33398900f2da6df90772ee10856e","first_computed_at":"2026-07-05T06:05:20.691653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:05:20.691653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uwk4ULfM+dYkTpUfA8subi0oLv5CchYf80A/DpgxRS5YEbZdOor9pkdOI6xU+319zZjBplsQVPlz79MNnVgWDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:05:20.692007Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.14766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd6630598be4d3d6f35b83a05c829e034d6d98c8a0cf82755590dd444ae3c5df","sha256:3adf28f6bb51784908c811b5ecbc46166184b58a532ff8587358f7e4cb6f3082"],"state_sha256":"a7e78a7301e6b1db3828260296f4003f03c84e828c9dfcb6770cb525a7558510"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"anU75g9NfvRl8aBd7NhpF/N5Iyq/ZOOVexUL0G695dq2XWXzFRHsMtalVy3eB2M8pLWmVYkRSHRUx+/975aiDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:07:47.326974Z","bundle_sha256":"d65c1d50e25b98083bb287f6e755bf375b6a2c176a2bc6e9143af732a16cd22f"}}