{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ES5ETX4W3DU7QGAOOEYEHNAEAU","short_pith_number":"pith:ES5ETX4W","canonical_record":{"source":{"id":"2412.03767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-04T23:12:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"098219071e97e863e3025c4d363a97863be9739bc7e29c5c490401af5a39b027","abstract_canon_sha256":"a022b7b6d96084dc5ee88c2c7f45a2fa79d02ff5c2f477625469f188c9d95345"},"schema_version":"1.0"},"canonical_sha256":"24ba49df96d8e9f8180e713043b404050b8efbf75483f4ad9ae90db75e1a22e3","source":{"kind":"arxiv","id":"2412.03767","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03767","created_at":"2026-07-05T09:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03767v1","created_at":"2026-07-05T09:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03767","created_at":"2026-07-05T09:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"ES5ETX4W3DU7","created_at":"2026-07-05T09:44:41Z"},{"alias_kind":"pith_short_16","alias_value":"ES5ETX4W3DU7QGAO","created_at":"2026-07-05T09:44:41Z"},{"alias_kind":"pith_short_8","alias_value":"ES5ETX4W","created_at":"2026-07-05T09:44:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ES5ETX4W3DU7QGAOOEYEHNAEAU","target":"record","payload":{"canonical_record":{"source":{"id":"2412.03767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-04T23:12:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"098219071e97e863e3025c4d363a97863be9739bc7e29c5c490401af5a39b027","abstract_canon_sha256":"a022b7b6d96084dc5ee88c2c7f45a2fa79d02ff5c2f477625469f188c9d95345"},"schema_version":"1.0"},"canonical_sha256":"24ba49df96d8e9f8180e713043b404050b8efbf75483f4ad9ae90db75e1a22e3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:41.059515Z","signature_b64":"5GlQE8Olhm8+RzSTrSIPtLG6A6PdTlmI4dNeEZH8X287a3AxjdBJP9IYZ+4If4+h6VZe712i6a7cHUdAZKvACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24ba49df96d8e9f8180e713043b404050b8efbf75483f4ad9ae90db75e1a22e3","last_reissued_at":"2026-07-05T09:44:41.059003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:41.059003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.03767","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":"2026-07-05T09:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C8RpRn5Eie7ijg7hYHyKhTxcWsamgKym8Nw1PWri6fUrT3TxglURNpFymL49gahJZXhxe1+8jum1R47tbHDPBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:16:54.898166Z"},"content_sha256":"621d73e4f0632313114c02379874469bb7984062666202b40e7622906a2c080a","schema_version":"1.0","event_id":"sha256:621d73e4f0632313114c02379874469bb7984062666202b40e7622906a2c080a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ES5ETX4W3DU7QGAOOEYEHNAEAU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bolei Zhou, Chenshu Liu, Lin F. Yang, Sanae Amani, Yiran Wang, Yunfan Li","submitted_at":"2024-12-04T23:12:41Z","abstract_excerpt":"The exploration \\& exploitation dilemma poses significant challenges in reinforcement learning (RL). Recently, curiosity-based exploration methods achieved great success in tackling hard-exploration problems. However, they necessitate extensive hyperparameter tuning on different environments, which heavily limits the applicability and accessibility of this line of methods. In this paper, we characterize this problem via analysis of the agent behavior, concluding the fundamental difficulty of choosing a proper hyperparameter. We then identify the difficulty and the instability of the optimizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03767","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.03767/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":"2026-07-05T09:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+91BlLnFSVjwHE5uHF4C82VofUASDCkSDPi8wFF7AiHaDGSR5WJE5k+DAFI+AL/Gm7e9PoT4JRnoVqI6lVrtAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:16:54.899104Z"},"content_sha256":"1d3dcc0fece274d94f901e2d50bca9e8b29933df5ff3cd2f8d87165257d45054","schema_version":"1.0","event_id":"sha256:1d3dcc0fece274d94f901e2d50bca9e8b29933df5ff3cd2f8d87165257d45054"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ES5ETX4W3DU7QGAOOEYEHNAEAU/bundle.json","state_url":"https://pith.science/pith/ES5ETX4W3DU7QGAOOEYEHNAEAU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ES5ETX4W3DU7QGAOOEYEHNAEAU/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":"2026-08-06T03:16:54Z","links":{"resolver":"https://pith.science/pith/ES5ETX4W3DU7QGAOOEYEHNAEAU","bundle":"https://pith.science/pith/ES5ETX4W3DU7QGAOOEYEHNAEAU/bundle.json","state":"https://pith.science/pith/ES5ETX4W3DU7QGAOOEYEHNAEAU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ES5ETX4W3DU7QGAOOEYEHNAEAU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ES5ETX4W3DU7QGAOOEYEHNAEAU","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":"a022b7b6d96084dc5ee88c2c7f45a2fa79d02ff5c2f477625469f188c9d95345","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-04T23:12:41Z","title_canon_sha256":"098219071e97e863e3025c4d363a97863be9739bc7e29c5c490401af5a39b027"},"schema_version":"1.0","source":{"id":"2412.03767","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03767","created_at":"2026-07-05T09:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03767v1","created_at":"2026-07-05T09:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03767","created_at":"2026-07-05T09:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"ES5ETX4W3DU7","created_at":"2026-07-05T09:44:41Z"},{"alias_kind":"pith_short_16","alias_value":"ES5ETX4W3DU7QGAO","created_at":"2026-07-05T09:44:41Z"},{"alias_kind":"pith_short_8","alias_value":"ES5ETX4W","created_at":"2026-07-05T09:44:41Z"}],"graph_snapshots":[{"event_id":"sha256:1d3dcc0fece274d94f901e2d50bca9e8b29933df5ff3cd2f8d87165257d45054","target":"graph","created_at":"2026-07-05T09:44:41Z","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/2412.03767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The exploration \\& exploitation dilemma poses significant challenges in reinforcement learning (RL). Recently, curiosity-based exploration methods achieved great success in tackling hard-exploration problems. However, they necessitate extensive hyperparameter tuning on different environments, which heavily limits the applicability and accessibility of this line of methods. In this paper, we characterize this problem via analysis of the agent behavior, concluding the fundamental difficulty of choosing a proper hyperparameter. We then identify the difficulty and the instability of the optimizati","authors_text":"Bolei Zhou, Chenshu Liu, Lin F. Yang, Sanae Amani, Yiran Wang, Yunfan Li","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-04T23:12:41Z","title":"Hyper: Hyperparameter Robust Efficient Exploration in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03767","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":"sha256:621d73e4f0632313114c02379874469bb7984062666202b40e7622906a2c080a","target":"record","created_at":"2026-07-05T09:44:41Z","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":"a022b7b6d96084dc5ee88c2c7f45a2fa79d02ff5c2f477625469f188c9d95345","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-04T23:12:41Z","title_canon_sha256":"098219071e97e863e3025c4d363a97863be9739bc7e29c5c490401af5a39b027"},"schema_version":"1.0","source":{"id":"2412.03767","kind":"arxiv","version":1}},"canonical_sha256":"24ba49df96d8e9f8180e713043b404050b8efbf75483f4ad9ae90db75e1a22e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24ba49df96d8e9f8180e713043b404050b8efbf75483f4ad9ae90db75e1a22e3","first_computed_at":"2026-07-05T09:44:41.059003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:41.059003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5GlQE8Olhm8+RzSTrSIPtLG6A6PdTlmI4dNeEZH8X287a3AxjdBJP9IYZ+4If4+h6VZe712i6a7cHUdAZKvACA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:41.059515Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03767","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:621d73e4f0632313114c02379874469bb7984062666202b40e7622906a2c080a","sha256:1d3dcc0fece274d94f901e2d50bca9e8b29933df5ff3cd2f8d87165257d45054"],"state_sha256":"34878a6f7f63fe70c993a9bca1c082b979428f6c9530d3d2eb56d83fd97750ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sPMrwBoBMcIIc2zudpRKDJCpfMrZ24CqWdd4uSmjqwGaVF6V0oFokZgJLZIzLLfebW97NLxeFnlEPQc1RGg8AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:16:54.905107Z","bundle_sha256":"1226ea90dc2d32dd4007e70f4611594c72096a03dcd4f3051dfca841658154cc"}}