{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:CUO2WDJLMP4V2BCG3NAYBRLCGB","short_pith_number":"pith:CUO2WDJL","canonical_record":{"source":{"id":"1602.04062","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-02-12T14:16:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cec570066e170e67b2f763d38b6614b9cde5fb789bee37731c55b030678426c5","abstract_canon_sha256":"8f3a2d9ac2baf29c462c94ade8143d8a689dbebd85f157d1775b9915bb9a907f"},"schema_version":"1.0"},"canonical_sha256":"151dab0d2b63f95d0446db4180c56230537cf9c10d0c1fd240e4ee4b4d4e5ba9","source":{"kind":"arxiv","id":"1602.04062","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.04062","created_at":"2026-05-18T01:12:16Z"},{"alias_kind":"arxiv_version","alias_value":"1602.04062v2","created_at":"2026-05-18T01:12:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.04062","created_at":"2026-05-18T01:12:16Z"},{"alias_kind":"pith_short_12","alias_value":"CUO2WDJLMP4V","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"CUO2WDJLMP4V2BCG","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"CUO2WDJL","created_at":"2026-05-18T12:30:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:CUO2WDJLMP4V2BCG3NAYBRLCGB","target":"record","payload":{"canonical_record":{"source":{"id":"1602.04062","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-02-12T14:16:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cec570066e170e67b2f763d38b6614b9cde5fb789bee37731c55b030678426c5","abstract_canon_sha256":"8f3a2d9ac2baf29c462c94ade8143d8a689dbebd85f157d1775b9915bb9a907f"},"schema_version":"1.0"},"canonical_sha256":"151dab0d2b63f95d0446db4180c56230537cf9c10d0c1fd240e4ee4b4d4e5ba9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:16.793926Z","signature_b64":"O8rFnnlEZ99R9lNEav55bkw/6K73K/FGmHNKRWAeXO1E804QdlurY/7kaBGubn7wDcriwyf/Dqdx1znkadAgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"151dab0d2b63f95d0446db4180c56230537cf9c10d0c1fd240e4ee4b4d4e5ba9","last_reissued_at":"2026-05-18T01:12:16.793580Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:16.793580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.04062","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":"2026-05-18T01:12:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1jHRsBuPYbpb8/Kfoyiovu29ZSYM5sMTs5P0EfIgVfqVrK0Zs23JFko59ce1Nhu0m/QgRTfRCRfDYoQjZq77Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T07:26:03.716743Z"},"content_sha256":"e0efd4bc1d4ca44fa0f43039158767dcf5206360b446f2a07b1e482cded75acf","schema_version":"1.0","event_id":"sha256:e0efd4bc1d4ca44fa0f43039158767dcf5206360b446f2a07b1e482cded75acf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:CUO2WDJLMP4V2BCG3NAYBRLCGB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Using Deep Q-Learning to Control Optimization Hyperparameters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Samantha Hansen","submitted_at":"2016-02-12T14:16:59Z","abstract_excerpt":"We present a novel definition of the reinforcement learning state, actions and reward function that allows a deep Q-network (DQN) to learn to control an optimization hyperparameter. Using Q-learning with experience replay, we train two DQNs to accept a state representation of an objective function as input and output the expected discounted return of rewards, or q-values, connected to the actions of either adjusting the learning rate or leaving it unchanged. The two DQNs learn a policy similar to a line search, but differ in the number of allowed actions. The trained DQNs in combination with a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.04062","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":""},"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":"2026-05-18T01:12:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nYEXNjGXmESIHRb+vYm6dSoNi6QRvQmlu9U0Lo0fPZgW0onG4FVMmLN4oJxFnKrxkwHJBCbjGTnR9w/QquEFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T07:26:03.717086Z"},"content_sha256":"aa4975783f63e1ac7dbee536ea56e20c5b7be3d461f02f3aaaffbf47a955bd89","schema_version":"1.0","event_id":"sha256:aa4975783f63e1ac7dbee536ea56e20c5b7be3d461f02f3aaaffbf47a955bd89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CUO2WDJLMP4V2BCG3NAYBRLCGB/bundle.json","state_url":"https://pith.science/pith/CUO2WDJLMP4V2BCG3NAYBRLCGB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CUO2WDJLMP4V2BCG3NAYBRLCGB/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":"2026-06-12T07:26:03Z","links":{"resolver":"https://pith.science/pith/CUO2WDJLMP4V2BCG3NAYBRLCGB","bundle":"https://pith.science/pith/CUO2WDJLMP4V2BCG3NAYBRLCGB/bundle.json","state":"https://pith.science/pith/CUO2WDJLMP4V2BCG3NAYBRLCGB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CUO2WDJLMP4V2BCG3NAYBRLCGB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:CUO2WDJLMP4V2BCG3NAYBRLCGB","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":"8f3a2d9ac2baf29c462c94ade8143d8a689dbebd85f157d1775b9915bb9a907f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-02-12T14:16:59Z","title_canon_sha256":"cec570066e170e67b2f763d38b6614b9cde5fb789bee37731c55b030678426c5"},"schema_version":"1.0","source":{"id":"1602.04062","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.04062","created_at":"2026-05-18T01:12:16Z"},{"alias_kind":"arxiv_version","alias_value":"1602.04062v2","created_at":"2026-05-18T01:12:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.04062","created_at":"2026-05-18T01:12:16Z"},{"alias_kind":"pith_short_12","alias_value":"CUO2WDJLMP4V","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"CUO2WDJLMP4V2BCG","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"CUO2WDJL","created_at":"2026-05-18T12:30:09Z"}],"graph_snapshots":[{"event_id":"sha256:aa4975783f63e1ac7dbee536ea56e20c5b7be3d461f02f3aaaffbf47a955bd89","target":"graph","created_at":"2026-05-18T01:12:16Z","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":"We present a novel definition of the reinforcement learning state, actions and reward function that allows a deep Q-network (DQN) to learn to control an optimization hyperparameter. Using Q-learning with experience replay, we train two DQNs to accept a state representation of an objective function as input and output the expected discounted return of rewards, or q-values, connected to the actions of either adjusting the learning rate or leaving it unchanged. The two DQNs learn a policy similar to a line search, but differ in the number of allowed actions. The trained DQNs in combination with a","authors_text":"Samantha Hansen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-02-12T14:16:59Z","title":"Using Deep Q-Learning to Control Optimization Hyperparameters"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.04062","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:e0efd4bc1d4ca44fa0f43039158767dcf5206360b446f2a07b1e482cded75acf","target":"record","created_at":"2026-05-18T01:12:16Z","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":"8f3a2d9ac2baf29c462c94ade8143d8a689dbebd85f157d1775b9915bb9a907f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-02-12T14:16:59Z","title_canon_sha256":"cec570066e170e67b2f763d38b6614b9cde5fb789bee37731c55b030678426c5"},"schema_version":"1.0","source":{"id":"1602.04062","kind":"arxiv","version":2}},"canonical_sha256":"151dab0d2b63f95d0446db4180c56230537cf9c10d0c1fd240e4ee4b4d4e5ba9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"151dab0d2b63f95d0446db4180c56230537cf9c10d0c1fd240e4ee4b4d4e5ba9","first_computed_at":"2026-05-18T01:12:16.793580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:16.793580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O8rFnnlEZ99R9lNEav55bkw/6K73K/FGmHNKRWAeXO1E804QdlurY/7kaBGubn7wDcriwyf/Dqdx1znkadAgBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:16.793926Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.04062","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0efd4bc1d4ca44fa0f43039158767dcf5206360b446f2a07b1e482cded75acf","sha256:aa4975783f63e1ac7dbee536ea56e20c5b7be3d461f02f3aaaffbf47a955bd89"],"state_sha256":"0cfd8887b67832c2f612205449177c1a15ecb8e9b7ae47510b179df45dd1b8d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uls0C//BijifhM7SGyTSNxbSh5f1aUjM0ex1Xp/Peo30yNrQxq4FXCrNNGcilIVz3B7aNfNk+7AY11eYc1UTDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T07:26:03.719238Z","bundle_sha256":"ef2702c63818ec6c38f006edd5cea5ea9dfd14457aa7bc50a87d1e7b9571f275"}}