{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:QGUAX5VXUWAGZ52LGBIMFVKIUF","short_pith_number":"pith:QGUAX5VX","canonical_record":{"source":{"id":"1611.04717","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-15T06:42:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"44c995d95d2ebf83168a334c26aeb1512795b28e79edc95fc42e88310f3b62eb","abstract_canon_sha256":"f532cae65df7164b0da2d43756a309389304277e965719605e35f92ad6994b9e"},"schema_version":"1.0"},"canonical_sha256":"81a80bf6b7a5806cf74b3050c2d548a17de12c1aaba8d70d5810a35fff3bda83","source":{"kind":"arxiv","id":"1611.04717","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.04717","created_at":"2026-05-18T00:28:56Z"},{"alias_kind":"arxiv_version","alias_value":"1611.04717v3","created_at":"2026-05-18T00:28:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04717","created_at":"2026-05-18T00:28:56Z"},{"alias_kind":"pith_short_12","alias_value":"QGUAX5VXUWAG","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"QGUAX5VXUWAGZ52L","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"QGUAX5VX","created_at":"2026-05-18T12:30:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:QGUAX5VXUWAGZ52LGBIMFVKIUF","target":"record","payload":{"canonical_record":{"source":{"id":"1611.04717","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-15T06:42:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"44c995d95d2ebf83168a334c26aeb1512795b28e79edc95fc42e88310f3b62eb","abstract_canon_sha256":"f532cae65df7164b0da2d43756a309389304277e965719605e35f92ad6994b9e"},"schema_version":"1.0"},"canonical_sha256":"81a80bf6b7a5806cf74b3050c2d548a17de12c1aaba8d70d5810a35fff3bda83","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:56.718149Z","signature_b64":"hMEAItPsdUZbjSVWKmLrKHhsNwbseL8fn7g6kEBFH7zhpVbi6wdhxLl5hELDkNFbdP99BrCCn8mGH2eqh5mSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81a80bf6b7a5806cf74b3050c2d548a17de12c1aaba8d70d5810a35fff3bda83","last_reissued_at":"2026-05-18T00:28:56.717488Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:56.717488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.04717","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:28:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jb4f0+VAcxi5oSwH0CjxI308N52PNzp6dP8RS/Cqxzgz2uLhTgAJzqQIrJavued8TtwkAWdEVFulRnq83DB1CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:24:02.607189Z"},"content_sha256":"f4b968641e04aef264b821c96657c8beb4f1d5757efa73e065498ba605422439","schema_version":"1.0","event_id":"sha256:f4b968641e04aef264b821c96657c8beb4f1d5757efa73e065498ba605422439"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:QGUAX5VXUWAGZ52LGBIMFVKIUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Adam Stooke, Davis Foote, Filip De Turck, Haoran Tang, John Schulman, Pieter Abbeel, Rein Houthooft, Xi Chen, Yan Duan","submitted_at":"2016-11-15T06:42:24Z","abstract_excerpt":"Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision processes (MDPs). It is generally thought that count-based methods cannot be applied in high-dimensional state spaces, since most states will only occur once. Recent deep RL exploration strategies are able to deal with high-dimensional continuous state spaces through complex heuristics, often relying on optimism in the face of uncertainty or intrinsic motivation. In this work, we describe a surprising finding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04717","kind":"arxiv","version":3},"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":"2026-05-18T00:28:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xiVuqo9+Z5TPQMx5QfNWC0E+gMghipUObbq9s9k3nwu0e4PDlIZjfH1ca8t/mL69ugfzoZ0kKwiXFwizbOZLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:24:02.607886Z"},"content_sha256":"1d55595e85de4fd495fe2df1bee4527d109b86ec94e2c7ef9fd12f0dd3e2ffd8","schema_version":"1.0","event_id":"sha256:1d55595e85de4fd495fe2df1bee4527d109b86ec94e2c7ef9fd12f0dd3e2ffd8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QGUAX5VXUWAGZ52LGBIMFVKIUF/bundle.json","state_url":"https://pith.science/pith/QGUAX5VXUWAGZ52LGBIMFVKIUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QGUAX5VXUWAGZ52LGBIMFVKIUF/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":"2026-05-30T12:24:02Z","links":{"resolver":"https://pith.science/pith/QGUAX5VXUWAGZ52LGBIMFVKIUF","bundle":"https://pith.science/pith/QGUAX5VXUWAGZ52LGBIMFVKIUF/bundle.json","state":"https://pith.science/pith/QGUAX5VXUWAGZ52LGBIMFVKIUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QGUAX5VXUWAGZ52LGBIMFVKIUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:QGUAX5VXUWAGZ52LGBIMFVKIUF","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":"f532cae65df7164b0da2d43756a309389304277e965719605e35f92ad6994b9e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-15T06:42:24Z","title_canon_sha256":"44c995d95d2ebf83168a334c26aeb1512795b28e79edc95fc42e88310f3b62eb"},"schema_version":"1.0","source":{"id":"1611.04717","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.04717","created_at":"2026-05-18T00:28:56Z"},{"alias_kind":"arxiv_version","alias_value":"1611.04717v3","created_at":"2026-05-18T00:28:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.04717","created_at":"2026-05-18T00:28:56Z"},{"alias_kind":"pith_short_12","alias_value":"QGUAX5VXUWAG","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"QGUAX5VXUWAGZ52L","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"QGUAX5VX","created_at":"2026-05-18T12:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:1d55595e85de4fd495fe2df1bee4527d109b86ec94e2c7ef9fd12f0dd3e2ffd8","target":"graph","created_at":"2026-05-18T00:28:56Z","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":"Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision processes (MDPs). It is generally thought that count-based methods cannot be applied in high-dimensional state spaces, since most states will only occur once. Recent deep RL exploration strategies are able to deal with high-dimensional continuous state spaces through complex heuristics, often relying on optimism in the face of uncertainty or intrinsic motivation. In this work, we describe a surprising finding","authors_text":"Adam Stooke, Davis Foote, Filip De Turck, Haoran Tang, John Schulman, Pieter Abbeel, Rein Houthooft, Xi Chen, Yan Duan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-15T06:42:24Z","title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.04717","kind":"arxiv","version":3},"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:f4b968641e04aef264b821c96657c8beb4f1d5757efa73e065498ba605422439","target":"record","created_at":"2026-05-18T00:28:56Z","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":"f532cae65df7164b0da2d43756a309389304277e965719605e35f92ad6994b9e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-15T06:42:24Z","title_canon_sha256":"44c995d95d2ebf83168a334c26aeb1512795b28e79edc95fc42e88310f3b62eb"},"schema_version":"1.0","source":{"id":"1611.04717","kind":"arxiv","version":3}},"canonical_sha256":"81a80bf6b7a5806cf74b3050c2d548a17de12c1aaba8d70d5810a35fff3bda83","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81a80bf6b7a5806cf74b3050c2d548a17de12c1aaba8d70d5810a35fff3bda83","first_computed_at":"2026-05-18T00:28:56.717488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:56.717488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hMEAItPsdUZbjSVWKmLrKHhsNwbseL8fn7g6kEBFH7zhpVbi6wdhxLl5hELDkNFbdP99BrCCn8mGH2eqh5mSAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:56.718149Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.04717","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f4b968641e04aef264b821c96657c8beb4f1d5757efa73e065498ba605422439","sha256:1d55595e85de4fd495fe2df1bee4527d109b86ec94e2c7ef9fd12f0dd3e2ffd8"],"state_sha256":"15a1d0b0e6a654a080ecffe44593fd0a0696d73cdbdf48a4dbadda549bb04659"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WrmsshvIxpgGMBL9iIJQ6NNXwjVDjcnyjpcoJCzJTcYQu+5yhXIUNkuM5z6ZXsepAwF6s2+KvEXs18E+I7l0DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T12:24:02.611602Z","bundle_sha256":"e15e545d1cc3bcb41c3ff92a665b6ba2c10b69847de18c19b1629694374e5242"}}