{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZGO7K7WH5KA64Z6SYMMAURPKW7","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":"4bfd3d7ae17e382d9378a664e9386825141284881ded6a14e6aba30914d693b2","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T05:18:23Z","title_canon_sha256":"4e8ec540d3de9db707a7fcf9ca72a9fcc0ce030eab8f61fb4aca81698f456e1f"},"schema_version":"1.0","source":{"id":"2405.07473","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.07473","created_at":"2026-07-05T08:18:22Z"},{"alias_kind":"arxiv_version","alias_value":"2405.07473v1","created_at":"2026-07-05T08:18:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.07473","created_at":"2026-07-05T08:18:22Z"},{"alias_kind":"pith_short_12","alias_value":"ZGO7K7WH5KA6","created_at":"2026-07-05T08:18:22Z"},{"alias_kind":"pith_short_16","alias_value":"ZGO7K7WH5KA64Z6S","created_at":"2026-07-05T08:18:22Z"},{"alias_kind":"pith_short_8","alias_value":"ZGO7K7WH","created_at":"2026-07-05T08:18:22Z"}],"graph_snapshots":[{"event_id":"sha256:8aef09a6a268e5978fcc592f396888700dd95ed21a94f0ca5e827bb99ed8463b","target":"graph","created_at":"2026-07-05T08:18:22Z","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/2405.07473/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Reinforcement Learning (RL), artificial agents are trained to maximize numerical rewards by performing tasks. Exploration is essential in RL because agents must discover information before exploiting it. Two rewards encouraging efficient exploration are the entropy of action policy and curiosity for information gain. Entropy is well-established in literature, promoting randomized action selection. Curiosity is defined in a broad variety of ways in literature, promoting discovery of novel experiences. One example, prediction error curiosity, rewards agents for discovering observations they c","authors_text":"Jun Tani, Kenji Doya, Theodore Jerome Tinker","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T05:18:23Z","title":"Intrinsic Rewards for Exploration without Harm from Observational Noise: A Simulation Study Based on the Free Energy Principle"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.07473","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:a7bd6fb3222302575d5b7fc07fb8965bde7364cd263f5d2c912bf35c95229a11","target":"record","created_at":"2026-07-05T08:18:22Z","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":"4bfd3d7ae17e382d9378a664e9386825141284881ded6a14e6aba30914d693b2","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T05:18:23Z","title_canon_sha256":"4e8ec540d3de9db707a7fcf9ca72a9fcc0ce030eab8f61fb4aca81698f456e1f"},"schema_version":"1.0","source":{"id":"2405.07473","kind":"arxiv","version":1}},"canonical_sha256":"c99df57ec7ea81ee67d2c3180a45eab7c1f1544b2848f848b22193ec37d1a951","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c99df57ec7ea81ee67d2c3180a45eab7c1f1544b2848f848b22193ec37d1a951","first_computed_at":"2026-07-05T08:18:22.995778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:18:22.995778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t5VnQsDfJ6URZWpHCXWgrJ94cC1ebSbLtdGsY0FhJMdvVCno9gJdzeAbekGUxSfiXvwfACeh/DL0vlE+ZMDwDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:18:22.996196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.07473","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7bd6fb3222302575d5b7fc07fb8965bde7364cd263f5d2c912bf35c95229a11","sha256:8aef09a6a268e5978fcc592f396888700dd95ed21a94f0ca5e827bb99ed8463b"],"state_sha256":"75d77e4e813395e26611381d294b667e331a88eb680630b05a34b85e8bc4f22d"}