{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5A5AZ6UROAKY5EEQ44KMWDHLA7","short_pith_number":"pith:5A5AZ6UR","canonical_record":{"source":{"id":"2306.03186","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-05T18:56:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"44b8a1b077737007c6a0fb867cbac8793c6146ce20e5643bbc6a4742f9e9c7c5","abstract_canon_sha256":"e904f07ef70f3b9a5881852ac3502c09b29c08ebd49bd3f433791fa940ba16bd"},"schema_version":"1.0"},"canonical_sha256":"e83a0cfa9170158e9090e714cb0ceb07d3e2fee7d47812d845da4d1e87cae6b6","source":{"kind":"arxiv","id":"2306.03186","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03186","created_at":"2026-07-05T06:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03186v1","created_at":"2026-07-05T06:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03186","created_at":"2026-07-05T06:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"5A5AZ6UROAKY","created_at":"2026-07-05T06:17:54Z"},{"alias_kind":"pith_short_16","alias_value":"5A5AZ6UROAKY5EEQ","created_at":"2026-07-05T06:17:54Z"},{"alias_kind":"pith_short_8","alias_value":"5A5AZ6UR","created_at":"2026-07-05T06:17:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5A5AZ6UROAKY5EEQ44KMWDHLA7","target":"record","payload":{"canonical_record":{"source":{"id":"2306.03186","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-05T18:56:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"44b8a1b077737007c6a0fb867cbac8793c6146ce20e5643bbc6a4742f9e9c7c5","abstract_canon_sha256":"e904f07ef70f3b9a5881852ac3502c09b29c08ebd49bd3f433791fa940ba16bd"},"schema_version":"1.0"},"canonical_sha256":"e83a0cfa9170158e9090e714cb0ceb07d3e2fee7d47812d845da4d1e87cae6b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:54.760457Z","signature_b64":"weTlZSeK7Yfc3d15265wFahne+JzY56KKNeWmUJLLFTp70E2Xy3lBxw5/Ueqc4a2G4k3B3OI/xoiqpkka0PYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e83a0cfa9170158e9090e714cb0ceb07d3e2fee7d47812d845da4d1e87cae6b6","last_reissued_at":"2026-07-05T06:17:54.759982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:54.759982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.03186","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":"2026-07-05T06:17:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9tPR4B/Hig0GXBsY+DfmqdMJ8yWJjeFIsTARatIiSTAr4TvVmvNUZFO79+890Rur0Vmy9vN26J4C2fOUfHwdAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T14:26:39.197202Z"},"content_sha256":"6bd1c3df3e53c7f8e6828064493a85991fa9b990543447f220dff235813c6bb4","schema_version":"1.0","event_id":"sha256:6bd1c3df3e53c7f8e6828064493a85991fa9b990543447f220dff235813c6bb4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5A5AZ6UROAKY5EEQ44KMWDHLA7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akhil Bagaria, George Konidaris, Sam Lobel","submitted_at":"2023-06-05T18:56:48Z","abstract_excerpt":"We propose a new method for count-based exploration in high-dimensional state spaces. Unlike previous work which relies on density models, we show that counts can be derived by averaging samples from the Rademacher distribution (or coin flips). This insight is used to set up a simple supervised learning objective which, when optimized, yields a state's visitation count. We show that our method is significantly more effective at deducing ground-truth visitation counts than previous work; when used as an exploration bonus for a model-free reinforcement learning algorithm, it outperforms existing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03186","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/2306.03186/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":"2026-07-05T06:17:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H7XBHAimXCtyvxbMGzIt4icG/uKg5HJeY+YrWc3pLKSFvb6S5thBYpUpLYDRe4j0A8oqgLgkM1KF+saIT1HyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T14:26:39.197916Z"},"content_sha256":"a4a7c7e57ca6c8a7ed6afac1199b0ff4d0aa561d6ed3f6fde26c4ac4365587a7","schema_version":"1.0","event_id":"sha256:a4a7c7e57ca6c8a7ed6afac1199b0ff4d0aa561d6ed3f6fde26c4ac4365587a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5A5AZ6UROAKY5EEQ44KMWDHLA7/bundle.json","state_url":"https://pith.science/pith/5A5AZ6UROAKY5EEQ44KMWDHLA7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5A5AZ6UROAKY5EEQ44KMWDHLA7/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":"2026-08-20T14:26:39Z","links":{"resolver":"https://pith.science/pith/5A5AZ6UROAKY5EEQ44KMWDHLA7","bundle":"https://pith.science/pith/5A5AZ6UROAKY5EEQ44KMWDHLA7/bundle.json","state":"https://pith.science/pith/5A5AZ6UROAKY5EEQ44KMWDHLA7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5A5AZ6UROAKY5EEQ44KMWDHLA7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5A5AZ6UROAKY5EEQ44KMWDHLA7","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":"e904f07ef70f3b9a5881852ac3502c09b29c08ebd49bd3f433791fa940ba16bd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-05T18:56:48Z","title_canon_sha256":"44b8a1b077737007c6a0fb867cbac8793c6146ce20e5643bbc6a4742f9e9c7c5"},"schema_version":"1.0","source":{"id":"2306.03186","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.03186","created_at":"2026-07-05T06:17:54Z"},{"alias_kind":"arxiv_version","alias_value":"2306.03186v1","created_at":"2026-07-05T06:17:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03186","created_at":"2026-07-05T06:17:54Z"},{"alias_kind":"pith_short_12","alias_value":"5A5AZ6UROAKY","created_at":"2026-07-05T06:17:54Z"},{"alias_kind":"pith_short_16","alias_value":"5A5AZ6UROAKY5EEQ","created_at":"2026-07-05T06:17:54Z"},{"alias_kind":"pith_short_8","alias_value":"5A5AZ6UR","created_at":"2026-07-05T06:17:54Z"}],"graph_snapshots":[{"event_id":"sha256:a4a7c7e57ca6c8a7ed6afac1199b0ff4d0aa561d6ed3f6fde26c4ac4365587a7","target":"graph","created_at":"2026-07-05T06:17:54Z","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/2306.03186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a new method for count-based exploration in high-dimensional state spaces. Unlike previous work which relies on density models, we show that counts can be derived by averaging samples from the Rademacher distribution (or coin flips). This insight is used to set up a simple supervised learning objective which, when optimized, yields a state's visitation count. We show that our method is significantly more effective at deducing ground-truth visitation counts than previous work; when used as an exploration bonus for a model-free reinforcement learning algorithm, it outperforms existing","authors_text":"Akhil Bagaria, George Konidaris, Sam Lobel","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-05T18:56:48Z","title":"Flipping Coins to Estimate Pseudocounts for Exploration in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03186","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":"sha256:6bd1c3df3e53c7f8e6828064493a85991fa9b990543447f220dff235813c6bb4","target":"record","created_at":"2026-07-05T06:17:54Z","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":"e904f07ef70f3b9a5881852ac3502c09b29c08ebd49bd3f433791fa940ba16bd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-05T18:56:48Z","title_canon_sha256":"44b8a1b077737007c6a0fb867cbac8793c6146ce20e5643bbc6a4742f9e9c7c5"},"schema_version":"1.0","source":{"id":"2306.03186","kind":"arxiv","version":1}},"canonical_sha256":"e83a0cfa9170158e9090e714cb0ceb07d3e2fee7d47812d845da4d1e87cae6b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e83a0cfa9170158e9090e714cb0ceb07d3e2fee7d47812d845da4d1e87cae6b6","first_computed_at":"2026-07-05T06:17:54.759982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:54.759982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"weTlZSeK7Yfc3d15265wFahne+JzY56KKNeWmUJLLFTp70E2Xy3lBxw5/Ueqc4a2G4k3B3OI/xoiqpkka0PYDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:54.760457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.03186","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bd1c3df3e53c7f8e6828064493a85991fa9b990543447f220dff235813c6bb4","sha256:a4a7c7e57ca6c8a7ed6afac1199b0ff4d0aa561d6ed3f6fde26c4ac4365587a7"],"state_sha256":"a2b6695f5eb3a4fb4d080bd058d0de7f8654de724c046dbbd7e16b2cf3838917"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QK3hSO+p0jZLo9vJjim5Vzs9stbvdFLJt0GNx9wOPTDnO8tu2q59zBBuaDtZgx3sdRl3L6Uzz7LKYNs2VuWUCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T14:26:39.203664Z","bundle_sha256":"6444172ed14f6da049a10173e77462db2c3e5769575a3d43f7ecae73f5dd9e98"}}