{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:O2OBFROQA7NUI5U7M65ISZZBGX","short_pith_number":"pith:O2OBFROQ","schema_version":"1.0","canonical_sha256":"769c12c5d007db44769f67ba89672135e1284b4cbc2d5d9967ecade9b7448417","source":{"kind":"arxiv","id":"2109.14925","version":2},"attestation_state":"computed","paper":{"title":"Genealogical Population-Based Training for Hyperparameter Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antoine Scardigli, David Naccache, Matteo Vilucchio, Paul Fournier","submitted_at":"2021-09-30T08:49:41Z","abstract_excerpt":"HyperParameter Optimization (HPO) aims at finding the best HyperParameters (HPs) of learning models, such as neural networks, in the fastest and most efficient way possible. Most recent HPO algorithms try to optimize HPs regardless of the model that obtained them, assuming that for different models, same HPs will produce very similar results. We break free from this paradigm and propose a new take on preexisting methods that we called Genealogical Population Based Training (GPBT). GPBT, via the shared histories of \"genealogically\"-related models, exploit the coupling of HPs and models in an ef"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2109.14925","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-30T08:49:41Z","cross_cats_sorted":[],"title_canon_sha256":"2558abc4a69b80cbe6c4d32fd9972981bed175ad9b2dca6c3403457b13718a7f","abstract_canon_sha256":"a165f648c28007bfac80fb520d3e379f6d791a244ad4d8b014a0883218817097"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:01.747086Z","signature_b64":"CC+yjf4KZ1ZEkyxbov9CB9BlQDDIO4hgneZf9S/JBADEbRVXaYZmPu0RQd27Fq8mGuNHGJ3wfoaGPANmoJuVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"769c12c5d007db44769f67ba89672135e1284b4cbc2d5d9967ecade9b7448417","last_reissued_at":"2026-07-05T05:59:01.746730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:01.746730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Genealogical Population-Based Training for Hyperparameter Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antoine Scardigli, David Naccache, Matteo Vilucchio, Paul Fournier","submitted_at":"2021-09-30T08:49:41Z","abstract_excerpt":"HyperParameter Optimization (HPO) aims at finding the best HyperParameters (HPs) of learning models, such as neural networks, in the fastest and most efficient way possible. Most recent HPO algorithms try to optimize HPs regardless of the model that obtained them, assuming that for different models, same HPs will produce very similar results. We break free from this paradigm and propose a new take on preexisting methods that we called Genealogical Population Based Training (GPBT). GPBT, via the shared histories of \"genealogically\"-related models, exploit the coupling of HPs and models in an ef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.14925","kind":"arxiv","version":2},"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/2109.14925/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2109.14925","created_at":"2026-07-05T05:59:01.746795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.14925v2","created_at":"2026-07-05T05:59:01.746795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.14925","created_at":"2026-07-05T05:59:01.746795+00:00"},{"alias_kind":"pith_short_12","alias_value":"O2OBFROQA7NU","created_at":"2026-07-05T05:59:01.746795+00:00"},{"alias_kind":"pith_short_16","alias_value":"O2OBFROQA7NUI5U7","created_at":"2026-07-05T05:59:01.746795+00:00"},{"alias_kind":"pith_short_8","alias_value":"O2OBFROQ","created_at":"2026-07-05T05:59:01.746795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O2OBFROQA7NUI5U7M65ISZZBGX","json":"https://pith.science/pith/O2OBFROQA7NUI5U7M65ISZZBGX.json","graph_json":"https://pith.science/api/pith-number/O2OBFROQA7NUI5U7M65ISZZBGX/graph.json","events_json":"https://pith.science/api/pith-number/O2OBFROQA7NUI5U7M65ISZZBGX/events.json","paper":"https://pith.science/paper/O2OBFROQ"},"agent_actions":{"view_html":"https://pith.science/pith/O2OBFROQA7NUI5U7M65ISZZBGX","download_json":"https://pith.science/pith/O2OBFROQA7NUI5U7M65ISZZBGX.json","view_paper":"https://pith.science/paper/O2OBFROQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.14925&json=true","fetch_graph":"https://pith.science/api/pith-number/O2OBFROQA7NUI5U7M65ISZZBGX/graph.json","fetch_events":"https://pith.science/api/pith-number/O2OBFROQA7NUI5U7M65ISZZBGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O2OBFROQA7NUI5U7M65ISZZBGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O2OBFROQA7NUI5U7M65ISZZBGX/action/storage_attestation","attest_author":"https://pith.science/pith/O2OBFROQA7NUI5U7M65ISZZBGX/action/author_attestation","sign_citation":"https://pith.science/pith/O2OBFROQA7NUI5U7M65ISZZBGX/action/citation_signature","submit_replication":"https://pith.science/pith/O2OBFROQA7NUI5U7M65ISZZBGX/action/replication_record"}},"created_at":"2026-07-05T05:59:01.746795+00:00","updated_at":"2026-07-05T05:59:01.746795+00:00"}