{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P4U7X2YUJREKVPWD3LUS4JFTLU","short_pith_number":"pith:P4U7X2YU","schema_version":"1.0","canonical_sha256":"7f29fbeb144c48aabec3dae92e24b35d1c5b2310121216bc83f21546c06b56b3","source":{"kind":"arxiv","id":"2506.03225","version":2},"attestation_state":"computed","paper":{"title":"Multiple-Frequencies Population-Based Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Auguste Lehuger, Fabien Moutarde, Marin Toromanoff, Thibault Buhet, Valentin Charraut, Wa\\\"el Doulazmi","submitted_at":"2025-06-03T11:19:21Z","abstract_excerpt":"Reinforcement Learning's high sensitivity to hyperparameters is a source of instability and inefficiency, creating significant challenges for practitioners. Hyperparameter Optimization (HPO) algorithms have been developed to address this issue, among them Population-Based Training (PBT) stands out for its ability to generate hyperparameters schedules instead of fixed configurations. PBT trains a population of agents, each with its own hyperparameters, frequently ranking them and replacing the worst performers with mutations of the best agents. These intermediate selection steps can cause PBT t"},"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":"2506.03225","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T11:19:21Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"1849fb98e33cec04381e6e9005175a2c67d42a3d73a98dc90632be1f1393c266","abstract_canon_sha256":"09aae39077fe8c87c646dec1dd5de001b96e7313f037c4aa538e3282aeec5f44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:51.717087Z","signature_b64":"M2c+xieI4eQjTLuJKiEve/Ow/phB/IBsJOqBtVOmT7+Ulcpa8VtntCjsceEtzRpgir/RCIjh4QMulHGzWzURDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f29fbeb144c48aabec3dae92e24b35d1c5b2310121216bc83f21546c06b56b3","last_reissued_at":"2026-07-05T11:38:51.716644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:51.716644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiple-Frequencies Population-Based Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Auguste Lehuger, Fabien Moutarde, Marin Toromanoff, Thibault Buhet, Valentin Charraut, Wa\\\"el Doulazmi","submitted_at":"2025-06-03T11:19:21Z","abstract_excerpt":"Reinforcement Learning's high sensitivity to hyperparameters is a source of instability and inefficiency, creating significant challenges for practitioners. Hyperparameter Optimization (HPO) algorithms have been developed to address this issue, among them Population-Based Training (PBT) stands out for its ability to generate hyperparameters schedules instead of fixed configurations. PBT trains a population of agents, each with its own hyperparameters, frequently ranking them and replacing the worst performers with mutations of the best agents. These intermediate selection steps can cause PBT t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03225","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/2506.03225/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":"2506.03225","created_at":"2026-07-05T11:38:51.716694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03225v2","created_at":"2026-07-05T11:38:51.716694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03225","created_at":"2026-07-05T11:38:51.716694+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4U7X2YUJREK","created_at":"2026-07-05T11:38:51.716694+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4U7X2YUJREKVPWD","created_at":"2026-07-05T11:38:51.716694+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4U7X2YU","created_at":"2026-07-05T11:38:51.716694+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/P4U7X2YUJREKVPWD3LUS4JFTLU","json":"https://pith.science/pith/P4U7X2YUJREKVPWD3LUS4JFTLU.json","graph_json":"https://pith.science/api/pith-number/P4U7X2YUJREKVPWD3LUS4JFTLU/graph.json","events_json":"https://pith.science/api/pith-number/P4U7X2YUJREKVPWD3LUS4JFTLU/events.json","paper":"https://pith.science/paper/P4U7X2YU"},"agent_actions":{"view_html":"https://pith.science/pith/P4U7X2YUJREKVPWD3LUS4JFTLU","download_json":"https://pith.science/pith/P4U7X2YUJREKVPWD3LUS4JFTLU.json","view_paper":"https://pith.science/paper/P4U7X2YU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03225&json=true","fetch_graph":"https://pith.science/api/pith-number/P4U7X2YUJREKVPWD3LUS4JFTLU/graph.json","fetch_events":"https://pith.science/api/pith-number/P4U7X2YUJREKVPWD3LUS4JFTLU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4U7X2YUJREKVPWD3LUS4JFTLU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4U7X2YUJREKVPWD3LUS4JFTLU/action/storage_attestation","attest_author":"https://pith.science/pith/P4U7X2YUJREKVPWD3LUS4JFTLU/action/author_attestation","sign_citation":"https://pith.science/pith/P4U7X2YUJREKVPWD3LUS4JFTLU/action/citation_signature","submit_replication":"https://pith.science/pith/P4U7X2YUJREKVPWD3LUS4JFTLU/action/replication_record"}},"created_at":"2026-07-05T11:38:51.716694+00:00","updated_at":"2026-07-05T11:38:51.716694+00:00"}