{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2MVB3RX5HXCY2UDVGFHGST2IBG","short_pith_number":"pith:2MVB3RX5","canonical_record":{"source":{"id":"2102.09026","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-17T21:03:05Z","cross_cats_sorted":[],"title_canon_sha256":"d6449d153d814b49695042c245ec1a89b629d285d06166020791ece309a0c7b6","abstract_canon_sha256":"d909133e0e794de8020e5aa4c7ba1e57f1ee6f0eb75695a5f54f20379ab6d714"},"schema_version":"1.0"},"canonical_sha256":"d32a1dc6fd3dc58d5075314e694f4809be603e8aa1903a9e2994d614ecbdf0cd","source":{"kind":"arxiv","id":"2102.09026","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.09026","created_at":"2026-07-05T02:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"2102.09026v1","created_at":"2026-07-05T02:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09026","created_at":"2026-07-05T02:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"2MVB3RX5HXCY","created_at":"2026-07-05T02:16:18Z"},{"alias_kind":"pith_short_16","alias_value":"2MVB3RX5HXCY2UDV","created_at":"2026-07-05T02:16:18Z"},{"alias_kind":"pith_short_8","alias_value":"2MVB3RX5","created_at":"2026-07-05T02:16:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2MVB3RX5HXCY2UDVGFHGST2IBG","target":"record","payload":{"canonical_record":{"source":{"id":"2102.09026","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-17T21:03:05Z","cross_cats_sorted":[],"title_canon_sha256":"d6449d153d814b49695042c245ec1a89b629d285d06166020791ece309a0c7b6","abstract_canon_sha256":"d909133e0e794de8020e5aa4c7ba1e57f1ee6f0eb75695a5f54f20379ab6d714"},"schema_version":"1.0"},"canonical_sha256":"d32a1dc6fd3dc58d5075314e694f4809be603e8aa1903a9e2994d614ecbdf0cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:16:18.689104Z","signature_b64":"MvsOuUo1mdpt4zBwjyZ5V/9nM5X75xqgd1RSEq8gKDMjvXJihxa+CiLcwgcw72XUgwhhGRx7cUJSKAcfpBwVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d32a1dc6fd3dc58d5075314e694f4809be603e8aa1903a9e2994d614ecbdf0cd","last_reissued_at":"2026-07-05T02:16:18.688576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:16:18.688576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.09026","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":"2026-07-05T02:16:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IKciqWJGJ7VYkT1mE2nqujVs/GHzkJgl5PChblM7f78KRLqIe2O4cYGfaAlQEiTGxHFneZYywxNHMGHuwmU4Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:20:26.542570Z"},"content_sha256":"d23752f9cc7edecfaa68defe13300c5a31a26db377d36d3c13531c583b0dce0a","schema_version":"1.0","event_id":"sha256:d23752f9cc7edecfaa68defe13300c5a31a26db377d36d3c13531c583b0dce0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2MVB3RX5HXCY2UDVGFHGST2IBG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Large-Scale Hyperparameters via Automated Learning Algorithm","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Gu, Guodong Liu, Heng Huang, Xiang Geng, Yanfu Zhang","submitted_at":"2021-02-17T21:03:05Z","abstract_excerpt":"Modern machine learning algorithms usually involve tuning multiple (from one to thousands) hyperparameters which play a pivotal role in terms of model generalizability. Black-box optimization and gradient-based algorithms are two dominant approaches to hyperparameter optimization while they have totally distinct advantages. How to design a new hyperparameter optimization technique inheriting all benefits from both approaches is still an open problem. To address this challenging problem, in this paper, we propose a new hyperparameter optimization method with zeroth-order hyper-gradients (HOZOG)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09026","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/2102.09026/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":"2026-07-05T02:16:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QcJZ0BfYPmX5KkU49G71wcUa5ImEiRzIgSsqmlfJag1PTrwKY9U/8OV/L5FUkjvCh3KGiikQ8cco4YUaLCmZDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:20:26.543461Z"},"content_sha256":"ca62bf8d410e6655221c5092ffaef011b6d92b8239d1b701424f3b3ddf0c0a10","schema_version":"1.0","event_id":"sha256:ca62bf8d410e6655221c5092ffaef011b6d92b8239d1b701424f3b3ddf0c0a10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2MVB3RX5HXCY2UDVGFHGST2IBG/bundle.json","state_url":"https://pith.science/pith/2MVB3RX5HXCY2UDVGFHGST2IBG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2MVB3RX5HXCY2UDVGFHGST2IBG/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":"2026-08-10T09:20:26Z","links":{"resolver":"https://pith.science/pith/2MVB3RX5HXCY2UDVGFHGST2IBG","bundle":"https://pith.science/pith/2MVB3RX5HXCY2UDVGFHGST2IBG/bundle.json","state":"https://pith.science/pith/2MVB3RX5HXCY2UDVGFHGST2IBG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2MVB3RX5HXCY2UDVGFHGST2IBG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2MVB3RX5HXCY2UDVGFHGST2IBG","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":"d909133e0e794de8020e5aa4c7ba1e57f1ee6f0eb75695a5f54f20379ab6d714","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-17T21:03:05Z","title_canon_sha256":"d6449d153d814b49695042c245ec1a89b629d285d06166020791ece309a0c7b6"},"schema_version":"1.0","source":{"id":"2102.09026","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.09026","created_at":"2026-07-05T02:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"2102.09026v1","created_at":"2026-07-05T02:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09026","created_at":"2026-07-05T02:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"2MVB3RX5HXCY","created_at":"2026-07-05T02:16:18Z"},{"alias_kind":"pith_short_16","alias_value":"2MVB3RX5HXCY2UDV","created_at":"2026-07-05T02:16:18Z"},{"alias_kind":"pith_short_8","alias_value":"2MVB3RX5","created_at":"2026-07-05T02:16:18Z"}],"graph_snapshots":[{"event_id":"sha256:ca62bf8d410e6655221c5092ffaef011b6d92b8239d1b701424f3b3ddf0c0a10","target":"graph","created_at":"2026-07-05T02:16:18Z","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/2102.09026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern machine learning algorithms usually involve tuning multiple (from one to thousands) hyperparameters which play a pivotal role in terms of model generalizability. Black-box optimization and gradient-based algorithms are two dominant approaches to hyperparameter optimization while they have totally distinct advantages. How to design a new hyperparameter optimization technique inheriting all benefits from both approaches is still an open problem. To address this challenging problem, in this paper, we propose a new hyperparameter optimization method with zeroth-order hyper-gradients (HOZOG)","authors_text":"Bin Gu, Guodong Liu, Heng Huang, Xiang Geng, Yanfu Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-17T21:03:05Z","title":"Optimizing Large-Scale Hyperparameters via Automated Learning Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09026","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:d23752f9cc7edecfaa68defe13300c5a31a26db377d36d3c13531c583b0dce0a","target":"record","created_at":"2026-07-05T02:16:18Z","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":"d909133e0e794de8020e5aa4c7ba1e57f1ee6f0eb75695a5f54f20379ab6d714","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-17T21:03:05Z","title_canon_sha256":"d6449d153d814b49695042c245ec1a89b629d285d06166020791ece309a0c7b6"},"schema_version":"1.0","source":{"id":"2102.09026","kind":"arxiv","version":1}},"canonical_sha256":"d32a1dc6fd3dc58d5075314e694f4809be603e8aa1903a9e2994d614ecbdf0cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d32a1dc6fd3dc58d5075314e694f4809be603e8aa1903a9e2994d614ecbdf0cd","first_computed_at":"2026-07-05T02:16:18.688576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:16:18.688576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MvsOuUo1mdpt4zBwjyZ5V/9nM5X75xqgd1RSEq8gKDMjvXJihxa+CiLcwgcw72XUgwhhGRx7cUJSKAcfpBwVDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:16:18.689104Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.09026","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d23752f9cc7edecfaa68defe13300c5a31a26db377d36d3c13531c583b0dce0a","sha256:ca62bf8d410e6655221c5092ffaef011b6d92b8239d1b701424f3b3ddf0c0a10"],"state_sha256":"9c2481d45dee956c766333662617ab0b0275e719e09cf24a9abe55eb71fd889f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HZaIwc2mTlANA0JQ2CSc5TSvGqkfwFs6aPFOEF17Pf9y2lVKwWQEqWWFZv9hjwves9dvtqmnSx1KlLbvTwMaCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:20:26.549858Z","bundle_sha256":"40737ea978318a07d7cd5d1c4ac78cf7a4b7ef0c511a4994cf9054eb16dfe1b6"}}