{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GH5F6T5W5JF5HALA36AVZJPQ2C","short_pith_number":"pith:GH5F6T5W","canonical_record":{"source":{"id":"2312.12145","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T13:28:34Z","cross_cats_sorted":[],"title_canon_sha256":"1d5bf23d6399394f86e374e941562dcdf26ce1fa388f1504aa39875f7b982fb9","abstract_canon_sha256":"09e628df9216175c6c91281fb69925c771e0589f46fc41d604b59b5de3af7958"},"schema_version":"1.0"},"canonical_sha256":"31fa5f4fb6ea4bd38160df815ca5f0d091347aad764487cf1f913932529f01a0","source":{"kind":"arxiv","id":"2312.12145","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.12145","created_at":"2026-07-05T07:26:20Z"},{"alias_kind":"arxiv_version","alias_value":"2312.12145v2","created_at":"2026-07-05T07:26:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12145","created_at":"2026-07-05T07:26:20Z"},{"alias_kind":"pith_short_12","alias_value":"GH5F6T5W5JF5","created_at":"2026-07-05T07:26:20Z"},{"alias_kind":"pith_short_16","alias_value":"GH5F6T5W5JF5HALA","created_at":"2026-07-05T07:26:20Z"},{"alias_kind":"pith_short_8","alias_value":"GH5F6T5W","created_at":"2026-07-05T07:26:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GH5F6T5W5JF5HALA36AVZJPQ2C","target":"record","payload":{"canonical_record":{"source":{"id":"2312.12145","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T13:28:34Z","cross_cats_sorted":[],"title_canon_sha256":"1d5bf23d6399394f86e374e941562dcdf26ce1fa388f1504aa39875f7b982fb9","abstract_canon_sha256":"09e628df9216175c6c91281fb69925c771e0589f46fc41d604b59b5de3af7958"},"schema_version":"1.0"},"canonical_sha256":"31fa5f4fb6ea4bd38160df815ca5f0d091347aad764487cf1f913932529f01a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:20.660777Z","signature_b64":"zZlcgjwLUf6fj3c+mDVeN8VDMVBG9TtxYylL93QFGPlQVHnSLIiWPKilJ7nuoAlY6QlA8zqJt8t/AjjmFOw4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31fa5f4fb6ea4bd38160df815ca5f0d091347aad764487cf1f913932529f01a0","last_reissued_at":"2026-07-05T07:26:20.660338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:20.660338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.12145","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":"2026-07-05T07:26:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z4NzvM/H6uD8HaEBLlqps9QQUYrM2lk2vQNqZLs3217UoqisMmQBp+HGNFN+kgFgI9cg1nl9//DbjsUGkmFdAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:03:54.897602Z"},"content_sha256":"f1a297222ebcee4ddb0a2023295e59cfeb5eec903bb8827376cef68ceedb710b","schema_version":"1.0","event_id":"sha256:f1a297222ebcee4ddb0a2023295e59cfeb5eec903bb8827376cef68ceedb710b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GH5F6T5W5JF5HALA36AVZJPQ2C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenjia Bai, Haiyin Piao, Jianye Hao, Jinyi Liu, Junjie Ye, Yang Sun, Yan Zheng, Zhen Wang, Zhi Wang","submitted_at":"2023-12-19T13:28:34Z","abstract_excerpt":"In reinforcement learning, the optimism in the face of uncertainty (OFU) is a mainstream principle for directing exploration towards less explored areas, characterized by higher uncertainty. However, in the presence of environmental stochasticity (noise), purely optimistic exploration may lead to excessive probing of high-noise areas, consequently impeding exploration efficiency. Hence, in exploring noisy environments, while optimism-driven exploration serves as a foundation, prudent attention to alleviating unnecessary over-exploration in high-noise areas becomes beneficial. In this work, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12145","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/2312.12145/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":"2026-07-05T07:26:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XhwfJJDw+iY17fpIZsi6olERqPVm6UIo1fkKZ1GjASJTs9IFRW744P5smsdyhQ9Z7ANFuJAzuLFesQVLp1wGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:03:54.898136Z"},"content_sha256":"54ddfcfe72c34821b6796bfb9cfd221affd9a79a6a5caf545cb52305669e0f90","schema_version":"1.0","event_id":"sha256:54ddfcfe72c34821b6796bfb9cfd221affd9a79a6a5caf545cb52305669e0f90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GH5F6T5W5JF5HALA36AVZJPQ2C/bundle.json","state_url":"https://pith.science/pith/GH5F6T5W5JF5HALA36AVZJPQ2C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GH5F6T5W5JF5HALA36AVZJPQ2C/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":"2026-08-06T13:03:54Z","links":{"resolver":"https://pith.science/pith/GH5F6T5W5JF5HALA36AVZJPQ2C","bundle":"https://pith.science/pith/GH5F6T5W5JF5HALA36AVZJPQ2C/bundle.json","state":"https://pith.science/pith/GH5F6T5W5JF5HALA36AVZJPQ2C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GH5F6T5W5JF5HALA36AVZJPQ2C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GH5F6T5W5JF5HALA36AVZJPQ2C","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":"09e628df9216175c6c91281fb69925c771e0589f46fc41d604b59b5de3af7958","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T13:28:34Z","title_canon_sha256":"1d5bf23d6399394f86e374e941562dcdf26ce1fa388f1504aa39875f7b982fb9"},"schema_version":"1.0","source":{"id":"2312.12145","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.12145","created_at":"2026-07-05T07:26:20Z"},{"alias_kind":"arxiv_version","alias_value":"2312.12145v2","created_at":"2026-07-05T07:26:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12145","created_at":"2026-07-05T07:26:20Z"},{"alias_kind":"pith_short_12","alias_value":"GH5F6T5W5JF5","created_at":"2026-07-05T07:26:20Z"},{"alias_kind":"pith_short_16","alias_value":"GH5F6T5W5JF5HALA","created_at":"2026-07-05T07:26:20Z"},{"alias_kind":"pith_short_8","alias_value":"GH5F6T5W","created_at":"2026-07-05T07:26:20Z"}],"graph_snapshots":[{"event_id":"sha256:54ddfcfe72c34821b6796bfb9cfd221affd9a79a6a5caf545cb52305669e0f90","target":"graph","created_at":"2026-07-05T07:26:20Z","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/2312.12145/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning, the optimism in the face of uncertainty (OFU) is a mainstream principle for directing exploration towards less explored areas, characterized by higher uncertainty. However, in the presence of environmental stochasticity (noise), purely optimistic exploration may lead to excessive probing of high-noise areas, consequently impeding exploration efficiency. Hence, in exploring noisy environments, while optimism-driven exploration serves as a foundation, prudent attention to alleviating unnecessary over-exploration in high-noise areas becomes beneficial. In this work, we ","authors_text":"Chenjia Bai, Haiyin Piao, Jianye Hao, Jinyi Liu, Junjie Ye, Yang Sun, Yan Zheng, Zhen Wang, Zhi Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T13:28:34Z","title":"OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12145","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:f1a297222ebcee4ddb0a2023295e59cfeb5eec903bb8827376cef68ceedb710b","target":"record","created_at":"2026-07-05T07:26:20Z","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":"09e628df9216175c6c91281fb69925c771e0589f46fc41d604b59b5de3af7958","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T13:28:34Z","title_canon_sha256":"1d5bf23d6399394f86e374e941562dcdf26ce1fa388f1504aa39875f7b982fb9"},"schema_version":"1.0","source":{"id":"2312.12145","kind":"arxiv","version":2}},"canonical_sha256":"31fa5f4fb6ea4bd38160df815ca5f0d091347aad764487cf1f913932529f01a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31fa5f4fb6ea4bd38160df815ca5f0d091347aad764487cf1f913932529f01a0","first_computed_at":"2026-07-05T07:26:20.660338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:26:20.660338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zZlcgjwLUf6fj3c+mDVeN8VDMVBG9TtxYylL93QFGPlQVHnSLIiWPKilJ7nuoAlY6QlA8zqJt8t/AjjmFOw4AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:26:20.660777Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.12145","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1a297222ebcee4ddb0a2023295e59cfeb5eec903bb8827376cef68ceedb710b","sha256:54ddfcfe72c34821b6796bfb9cfd221affd9a79a6a5caf545cb52305669e0f90"],"state_sha256":"ce36c97745f58fe35fef73dcd5a4e10e2615dbe051ea6eab49a6407d017bfa72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wxBm7PC1eI2PuJ2Pa5+EGiw7Rifz2abNmFBP/vYPabAyQFL4UMEh5LFq0NbAY993eqy4fShECKCukGKrRGNsCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:03:54.901529Z","bundle_sha256":"c5829e02e6935b694d1427f69c88127db97ae6379a09c1e94a52e26aca0b65d4"}}