{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:F76XLWSXMAYNO7VO3M36RGRGUI","short_pith_number":"pith:F76XLWSX","canonical_record":{"source":{"id":"2007.14604","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-29T05:12:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3143d04a562a8d38fdda28844b568f7b8b6aace2e5e2cd883dbc6331aa820c6b","abstract_canon_sha256":"70692df251145ecac256d99dc93a0a8052ccaa13de1d8fb1714cab23784b53b3"},"schema_version":"1.0"},"canonical_sha256":"2ffd75da576030d77eaedb37e89a26a213e1539f6aae243e0327b2c34e346e0e","source":{"kind":"arxiv","id":"2007.14604","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.14604","created_at":"2026-07-05T01:23:26Z"},{"alias_kind":"arxiv_version","alias_value":"2007.14604v2","created_at":"2026-07-05T01:23:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.14604","created_at":"2026-07-05T01:23:26Z"},{"alias_kind":"pith_short_12","alias_value":"F76XLWSXMAYN","created_at":"2026-07-05T01:23:26Z"},{"alias_kind":"pith_short_16","alias_value":"F76XLWSXMAYNO7VO","created_at":"2026-07-05T01:23:26Z"},{"alias_kind":"pith_short_8","alias_value":"F76XLWSX","created_at":"2026-07-05T01:23:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:F76XLWSXMAYNO7VO3M36RGRGUI","target":"record","payload":{"canonical_record":{"source":{"id":"2007.14604","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-29T05:12:34Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3143d04a562a8d38fdda28844b568f7b8b6aace2e5e2cd883dbc6331aa820c6b","abstract_canon_sha256":"70692df251145ecac256d99dc93a0a8052ccaa13de1d8fb1714cab23784b53b3"},"schema_version":"1.0"},"canonical_sha256":"2ffd75da576030d77eaedb37e89a26a213e1539f6aae243e0327b2c34e346e0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:23:26.258445Z","signature_b64":"Mo5sdI0zaoMu4mShjC/U6twp2fyQu5bPw4JX+006fTln20psDIYsE9Bo5pXJEl+9jEYSKsiIjCgwyWfY9cCxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ffd75da576030d77eaedb37e89a26a213e1539f6aae243e0327b2c34e346e0e","last_reissued_at":"2026-07-05T01:23:26.258024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:23:26.258024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.14604","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:23:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aakQqtYUn6tnbIc8ugVi99apEx7vC5kVbFHPfcTf8fedldijyw16+KB0+ZSmispWdAB7XtBsljW5xylP7UVFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T12:01:54.038721Z"},"content_sha256":"d2e1504dc8c7aba10a2387d4e378b0dc9493cfd0a15390655b4a09cfb4f03e49","schema_version":"1.0","event_id":"sha256:d2e1504dc8c7aba10a2387d4e378b0dc9493cfd0a15390655b4a09cfb4f03e49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:F76XLWSXMAYNO7VO3M36RGRGUI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantity vs. Quality: On Hyperparameter Optimization for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel L. Gillen, Lars Hertel, Pierre Baldi","submitted_at":"2020-07-29T05:12:34Z","abstract_excerpt":"Reinforcement learning algorithms can show strong variation in performance between training runs with different random seeds. In this paper we explore how this affects hyperparameter optimization when the goal is to find hyperparameter settings that perform well across random seeds. In particular, we benchmark whether it is better to explore a large quantity of hyperparameter settings via pruning of bad performers, or if it is better to aim for quality of collected results by using repetitions. For this we consider the Successive Halving, Random Search, and Bayesian Optimization algorithms, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.14604","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/2007.14604/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":"2026-07-05T01:23:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cssWuTDak46Hhcl44ACkrpaIOzDkcP3k5+j5MhVZawnJN40Xmf1Y+iac7JhGwoV+akofy5ScD7b09ulbX2ibCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T12:01:54.039090Z"},"content_sha256":"f41690c8f0be0d79aed68b69f4754f31e92819e1c952464acb5154154badca42","schema_version":"1.0","event_id":"sha256:f41690c8f0be0d79aed68b69f4754f31e92819e1c952464acb5154154badca42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F76XLWSXMAYNO7VO3M36RGRGUI/bundle.json","state_url":"https://pith.science/pith/F76XLWSXMAYNO7VO3M36RGRGUI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F76XLWSXMAYNO7VO3M36RGRGUI/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":"2026-07-16T12:01:54Z","links":{"resolver":"https://pith.science/pith/F76XLWSXMAYNO7VO3M36RGRGUI","bundle":"https://pith.science/pith/F76XLWSXMAYNO7VO3M36RGRGUI/bundle.json","state":"https://pith.science/pith/F76XLWSXMAYNO7VO3M36RGRGUI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F76XLWSXMAYNO7VO3M36RGRGUI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:F76XLWSXMAYNO7VO3M36RGRGUI","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":"70692df251145ecac256d99dc93a0a8052ccaa13de1d8fb1714cab23784b53b3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-29T05:12:34Z","title_canon_sha256":"3143d04a562a8d38fdda28844b568f7b8b6aace2e5e2cd883dbc6331aa820c6b"},"schema_version":"1.0","source":{"id":"2007.14604","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.14604","created_at":"2026-07-05T01:23:26Z"},{"alias_kind":"arxiv_version","alias_value":"2007.14604v2","created_at":"2026-07-05T01:23:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.14604","created_at":"2026-07-05T01:23:26Z"},{"alias_kind":"pith_short_12","alias_value":"F76XLWSXMAYN","created_at":"2026-07-05T01:23:26Z"},{"alias_kind":"pith_short_16","alias_value":"F76XLWSXMAYNO7VO","created_at":"2026-07-05T01:23:26Z"},{"alias_kind":"pith_short_8","alias_value":"F76XLWSX","created_at":"2026-07-05T01:23:26Z"}],"graph_snapshots":[{"event_id":"sha256:f41690c8f0be0d79aed68b69f4754f31e92819e1c952464acb5154154badca42","target":"graph","created_at":"2026-07-05T01:23:26Z","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/2007.14604/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning algorithms can show strong variation in performance between training runs with different random seeds. In this paper we explore how this affects hyperparameter optimization when the goal is to find hyperparameter settings that perform well across random seeds. In particular, we benchmark whether it is better to explore a large quantity of hyperparameter settings via pruning of bad performers, or if it is better to aim for quality of collected results by using repetitions. For this we consider the Successive Halving, Random Search, and Bayesian Optimization algorithms, th","authors_text":"Daniel L. Gillen, Lars Hertel, Pierre Baldi","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-29T05:12:34Z","title":"Quantity vs. Quality: On Hyperparameter Optimization for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.14604","kind":"arxiv","version":2},"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:d2e1504dc8c7aba10a2387d4e378b0dc9493cfd0a15390655b4a09cfb4f03e49","target":"record","created_at":"2026-07-05T01:23:26Z","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":"70692df251145ecac256d99dc93a0a8052ccaa13de1d8fb1714cab23784b53b3","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-29T05:12:34Z","title_canon_sha256":"3143d04a562a8d38fdda28844b568f7b8b6aace2e5e2cd883dbc6331aa820c6b"},"schema_version":"1.0","source":{"id":"2007.14604","kind":"arxiv","version":2}},"canonical_sha256":"2ffd75da576030d77eaedb37e89a26a213e1539f6aae243e0327b2c34e346e0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ffd75da576030d77eaedb37e89a26a213e1539f6aae243e0327b2c34e346e0e","first_computed_at":"2026-07-05T01:23:26.258024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:23:26.258024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mo5sdI0zaoMu4mShjC/U6twp2fyQu5bPw4JX+006fTln20psDIYsE9Bo5pXJEl+9jEYSKsiIjCgwyWfY9cCxAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:23:26.258445Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.14604","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2e1504dc8c7aba10a2387d4e378b0dc9493cfd0a15390655b4a09cfb4f03e49","sha256:f41690c8f0be0d79aed68b69f4754f31e92819e1c952464acb5154154badca42"],"state_sha256":"da3b9eb88a81ba9d73e5a1a7917c3058f47582f2220090c38155d4a0965f93de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aO57GFsPgYG/orqB2K6aqh5S8lhEv9X8NYrRqEpTpaJ3LLaHoDlrHNE89Ge8E+xpQ+TrMcLCXT7hVpk3RsFsDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T12:01:54.041540Z","bundle_sha256":"6e9c306afcc907c120167c3c8f4a44d2ca348db2ce512b1446e5a9d8a42f8973"}}