{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:M6CNWI2R7UTXSMTFN7P2WAJLPV","short_pith_number":"pith:M6CNWI2R","canonical_record":{"source":{"id":"1902.02725","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-07T16:48:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c5abf7cafd84c6165dbf548a2f95b648cfb568adfb851e425b4e046e2a4319f7","abstract_canon_sha256":"e1b85a23c101489bce3de54d8af7c396d88e5f69189311970fda065fa1d56251"},"schema_version":"1.0"},"canonical_sha256":"6784db2351fd277932656fdfab012b7d40b660c33023cc8860bc6f45b64537ba","source":{"kind":"arxiv","id":"1902.02725","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.02725","created_at":"2026-05-17T23:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"1902.02725v1","created_at":"2026-05-17T23:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02725","created_at":"2026-05-17T23:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"M6CNWI2R7UTX","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"M6CNWI2R7UTXSMTF","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"M6CNWI2R","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:M6CNWI2R7UTXSMTFN7P2WAJLPV","target":"record","payload":{"canonical_record":{"source":{"id":"1902.02725","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-07T16:48:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c5abf7cafd84c6165dbf548a2f95b648cfb568adfb851e425b4e046e2a4319f7","abstract_canon_sha256":"e1b85a23c101489bce3de54d8af7c396d88e5f69189311970fda065fa1d56251"},"schema_version":"1.0"},"canonical_sha256":"6784db2351fd277932656fdfab012b7d40b660c33023cc8860bc6f45b64537ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:32.376676Z","signature_b64":"KjkWNto/ua1xvKW5zeIMexE+g2OcEosxdy9PHPa9Jlo+RsiDy/bWVOo6KDFncUj/1tSdpq21aRbQA6yWda0NDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6784db2351fd277932656fdfab012b7d40b660c33023cc8860bc6f45b64537ba","last_reissued_at":"2026-05-17T23:54:32.376000Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:32.376000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.02725","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":"2026-05-17T23:54:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kocM6cM4y75Za1rpiafDXGSWkiLSXkTxe2g5PqW1bdn545GC0mF/g8H/Gu91LAR4QVLYvsCHsuZbEpykQd5zCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T07:43:59.305697Z"},"content_sha256":"5882a43a7ce68dc3bb3d30d49056c840001968552582f88e7bcff9500dfadd5c","schema_version":"1.0","event_id":"sha256:5882a43a7ce68dc3bb3d30d49056c840001968552582f88e7bcff9500dfadd5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:M6CNWI2R7UTXSMTFN7P2WAJLPV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Metaoptimization on a Distributed System for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Greg Heinrich, Iuri Frosio","submitted_at":"2019-02-07T16:48:31Z","abstract_excerpt":"Training intelligent agents through reinforcement learning is a notoriously unstable procedure. Massive parallelization on GPUs and distributed systems has been exploited to generate a large amount of training experiences and consequently reduce instabilities, but the success of training remains strongly influenced by the choice of the hyperparameters. To overcome this issue, we introduce HyperTrick, a new metaoptimization algorithm, and show its effective application to tune hyperparameters in the case of deep reinforcement learning, while learning to play different Atari games on a distribut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02725","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":""},"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":"2026-05-17T23:54:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o/+WpwPaLE95vohXpBm3qteRLdzfkJEXDRcVJCxTQ8Rd95CQ2qjuRidjHPfRal5V2AH3n5ESElwAzpY7ekHDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T07:43:59.306033Z"},"content_sha256":"bc7d22a24417ad8d0563080da7b90e937d8de3debc956662f773d20531c2d486","schema_version":"1.0","event_id":"sha256:bc7d22a24417ad8d0563080da7b90e937d8de3debc956662f773d20531c2d486"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M6CNWI2R7UTXSMTFN7P2WAJLPV/bundle.json","state_url":"https://pith.science/pith/M6CNWI2R7UTXSMTFN7P2WAJLPV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M6CNWI2R7UTXSMTFN7P2WAJLPV/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":"2026-07-22T07:43:59Z","links":{"resolver":"https://pith.science/pith/M6CNWI2R7UTXSMTFN7P2WAJLPV","bundle":"https://pith.science/pith/M6CNWI2R7UTXSMTFN7P2WAJLPV/bundle.json","state":"https://pith.science/pith/M6CNWI2R7UTXSMTFN7P2WAJLPV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M6CNWI2R7UTXSMTFN7P2WAJLPV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:M6CNWI2R7UTXSMTFN7P2WAJLPV","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":"e1b85a23c101489bce3de54d8af7c396d88e5f69189311970fda065fa1d56251","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-07T16:48:31Z","title_canon_sha256":"c5abf7cafd84c6165dbf548a2f95b648cfb568adfb851e425b4e046e2a4319f7"},"schema_version":"1.0","source":{"id":"1902.02725","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.02725","created_at":"2026-05-17T23:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"1902.02725v1","created_at":"2026-05-17T23:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02725","created_at":"2026-05-17T23:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"M6CNWI2R7UTX","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"M6CNWI2R7UTXSMTF","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"M6CNWI2R","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:bc7d22a24417ad8d0563080da7b90e937d8de3debc956662f773d20531c2d486","target":"graph","created_at":"2026-05-17T23:54:32Z","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"},"paper":{"abstract_excerpt":"Training intelligent agents through reinforcement learning is a notoriously unstable procedure. Massive parallelization on GPUs and distributed systems has been exploited to generate a large amount of training experiences and consequently reduce instabilities, but the success of training remains strongly influenced by the choice of the hyperparameters. To overcome this issue, we introduce HyperTrick, a new metaoptimization algorithm, and show its effective application to tune hyperparameters in the case of deep reinforcement learning, while learning to play different Atari games on a distribut","authors_text":"Greg Heinrich, Iuri Frosio","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-07T16:48:31Z","title":"Metaoptimization on a Distributed System for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02725","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":"sha256:5882a43a7ce68dc3bb3d30d49056c840001968552582f88e7bcff9500dfadd5c","target":"record","created_at":"2026-05-17T23:54:32Z","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":"e1b85a23c101489bce3de54d8af7c396d88e5f69189311970fda065fa1d56251","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-07T16:48:31Z","title_canon_sha256":"c5abf7cafd84c6165dbf548a2f95b648cfb568adfb851e425b4e046e2a4319f7"},"schema_version":"1.0","source":{"id":"1902.02725","kind":"arxiv","version":1}},"canonical_sha256":"6784db2351fd277932656fdfab012b7d40b660c33023cc8860bc6f45b64537ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6784db2351fd277932656fdfab012b7d40b660c33023cc8860bc6f45b64537ba","first_computed_at":"2026-05-17T23:54:32.376000Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:32.376000Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KjkWNto/ua1xvKW5zeIMexE+g2OcEosxdy9PHPa9Jlo+RsiDy/bWVOo6KDFncUj/1tSdpq21aRbQA6yWda0NDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:32.376676Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.02725","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5882a43a7ce68dc3bb3d30d49056c840001968552582f88e7bcff9500dfadd5c","sha256:bc7d22a24417ad8d0563080da7b90e937d8de3debc956662f773d20531c2d486"],"state_sha256":"8716660f83d0c6ccbcaee365c60f43393112d50df34c3ee582f6f810a6b84af1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hkharbzyIgzawopeOwsyXGH7Sy/jkGw8kedpXVj+DnVIdlDwstgISb8M2puR7zpJ0J485wgaZotjJnJ6mxbPCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T07:43:59.308479Z","bundle_sha256":"7f9bb0451a1e18498e65bbbee855edb03c9ac6da4603b7c553619e9ce825cb1d"}}