{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KPW6H4XHW764FRPNZFEC2JBK2Z","short_pith_number":"pith:KPW6H4XH","canonical_record":{"source":{"id":"2011.06709","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-13T01:01:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"135a29de65cb01359c13922368816c95e604a7170ee4c65e82a9d83cdae014c4","abstract_canon_sha256":"855569336c7527351cc57b7152318875e6544b0074d556b4d30e28dc3592d896"},"schema_version":"1.0"},"canonical_sha256":"53ede3f2e7b7fdc2c5edc9482d242ad678537903479bf0eedca11830f9796873","source":{"kind":"arxiv","id":"2011.06709","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.06709","created_at":"2026-07-05T01:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"2011.06709v2","created_at":"2026-07-05T01:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06709","created_at":"2026-07-05T01:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"KPW6H4XHW764","created_at":"2026-07-05T01:54:32Z"},{"alias_kind":"pith_short_16","alias_value":"KPW6H4XHW764FRPN","created_at":"2026-07-05T01:54:32Z"},{"alias_kind":"pith_short_8","alias_value":"KPW6H4XH","created_at":"2026-07-05T01:54:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KPW6H4XHW764FRPNZFEC2JBK2Z","target":"record","payload":{"canonical_record":{"source":{"id":"2011.06709","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-13T01:01:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"135a29de65cb01359c13922368816c95e604a7170ee4c65e82a9d83cdae014c4","abstract_canon_sha256":"855569336c7527351cc57b7152318875e6544b0074d556b4d30e28dc3592d896"},"schema_version":"1.0"},"canonical_sha256":"53ede3f2e7b7fdc2c5edc9482d242ad678537903479bf0eedca11830f9796873","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:54:32.323582Z","signature_b64":"UY95B370ncGIzdcnx92onPH0edrArOXSOiRUHl6vRtRGTkL5v26oNhi80MA3n/hRGqtHmgyTYm+uqtlC2RkMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53ede3f2e7b7fdc2c5edc9482d242ad678537903479bf0eedca11830f9796873","last_reissued_at":"2026-07-05T01:54:32.323124Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:54:32.323124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.06709","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":"2026-07-05T01:54:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LWLTQBEJHD0Yw7h/AUWJcElqT0Yj3216yUEwCM/gGFH6vJuy5GXwrTMY/Z29g/pN9YmDr9cMaHwOC9AdHynLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:03:31.316637Z"},"content_sha256":"94b87ff4296730a3497acb6a95dcd8486b88716966a8fa7610baa88b1c3de998","schema_version":"1.0","event_id":"sha256:94b87ff4296730a3497acb6a95dcd8486b88716966a8fa7610baa88b1c3de998"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KPW6H4XHW764FRPNZFEC2JBK2Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Active Reinforcement Learning: Observing Rewards at a Cost","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Krueger, Jan Leike, John Salvatier, Owain Evans","submitted_at":"2020-11-13T01:01:13Z","abstract_excerpt":"Active reinforcement learning (ARL) is a variant on reinforcement learning where the agent does not observe the reward unless it chooses to pay a query cost c > 0. The central question of ARL is how to quantify the long-term value of reward information. Even in multi-armed bandits, computing the value of this information is intractable and we have to rely on heuristics. We propose and evaluate several heuristic approaches for ARL in multi-armed bandits and (tabular) Markov decision processes, and discuss and illustrate some challenging aspects of the ARL problem."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06709","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/2011.06709/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":"2026-07-05T01:54:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jfm1/maYMOdGE3pjM6fhX9yWNctxe4KqXRrsJ9//HYU8vB/ojUwLUNTeSPNDTH4yoswjW6ZmB42rAR/05FxYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T19:03:31.317419Z"},"content_sha256":"262ce2759a444782c7d6181457da95c1686954f72d11e7ae674ea8047763a793","schema_version":"1.0","event_id":"sha256:262ce2759a444782c7d6181457da95c1686954f72d11e7ae674ea8047763a793"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPW6H4XHW764FRPNZFEC2JBK2Z/bundle.json","state_url":"https://pith.science/pith/KPW6H4XHW764FRPNZFEC2JBK2Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPW6H4XHW764FRPNZFEC2JBK2Z/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":"2026-08-12T19:03:31Z","links":{"resolver":"https://pith.science/pith/KPW6H4XHW764FRPNZFEC2JBK2Z","bundle":"https://pith.science/pith/KPW6H4XHW764FRPNZFEC2JBK2Z/bundle.json","state":"https://pith.science/pith/KPW6H4XHW764FRPNZFEC2JBK2Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPW6H4XHW764FRPNZFEC2JBK2Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KPW6H4XHW764FRPNZFEC2JBK2Z","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":"855569336c7527351cc57b7152318875e6544b0074d556b4d30e28dc3592d896","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-13T01:01:13Z","title_canon_sha256":"135a29de65cb01359c13922368816c95e604a7170ee4c65e82a9d83cdae014c4"},"schema_version":"1.0","source":{"id":"2011.06709","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.06709","created_at":"2026-07-05T01:54:32Z"},{"alias_kind":"arxiv_version","alias_value":"2011.06709v2","created_at":"2026-07-05T01:54:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06709","created_at":"2026-07-05T01:54:32Z"},{"alias_kind":"pith_short_12","alias_value":"KPW6H4XHW764","created_at":"2026-07-05T01:54:32Z"},{"alias_kind":"pith_short_16","alias_value":"KPW6H4XHW764FRPN","created_at":"2026-07-05T01:54:32Z"},{"alias_kind":"pith_short_8","alias_value":"KPW6H4XH","created_at":"2026-07-05T01:54:32Z"}],"graph_snapshots":[{"event_id":"sha256:262ce2759a444782c7d6181457da95c1686954f72d11e7ae674ea8047763a793","target":"graph","created_at":"2026-07-05T01:54:32Z","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/2011.06709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Active reinforcement learning (ARL) is a variant on reinforcement learning where the agent does not observe the reward unless it chooses to pay a query cost c > 0. The central question of ARL is how to quantify the long-term value of reward information. Even in multi-armed bandits, computing the value of this information is intractable and we have to rely on heuristics. We propose and evaluate several heuristic approaches for ARL in multi-armed bandits and (tabular) Markov decision processes, and discuss and illustrate some challenging aspects of the ARL problem.","authors_text":"David Krueger, Jan Leike, John Salvatier, Owain Evans","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-13T01:01:13Z","title":"Active Reinforcement Learning: Observing Rewards at a Cost"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06709","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":"sha256:94b87ff4296730a3497acb6a95dcd8486b88716966a8fa7610baa88b1c3de998","target":"record","created_at":"2026-07-05T01:54:32Z","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":"855569336c7527351cc57b7152318875e6544b0074d556b4d30e28dc3592d896","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-13T01:01:13Z","title_canon_sha256":"135a29de65cb01359c13922368816c95e604a7170ee4c65e82a9d83cdae014c4"},"schema_version":"1.0","source":{"id":"2011.06709","kind":"arxiv","version":2}},"canonical_sha256":"53ede3f2e7b7fdc2c5edc9482d242ad678537903479bf0eedca11830f9796873","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53ede3f2e7b7fdc2c5edc9482d242ad678537903479bf0eedca11830f9796873","first_computed_at":"2026-07-05T01:54:32.323124Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:54:32.323124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UY95B370ncGIzdcnx92onPH0edrArOXSOiRUHl6vRtRGTkL5v26oNhi80MA3n/hRGqtHmgyTYm+uqtlC2RkMAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:54:32.323582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.06709","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94b87ff4296730a3497acb6a95dcd8486b88716966a8fa7610baa88b1c3de998","sha256:262ce2759a444782c7d6181457da95c1686954f72d11e7ae674ea8047763a793"],"state_sha256":"f2a9b8392c17956f6485fb147c31f9c778ec7cc5a5b23dd8d1efeca116159ae7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DMV+Mqq2t/0dZDICJQ9eN3xv1p60/Vgxxxa6JoWfNJ5yQuQzjqiffF6b0VDIMMl0X34sTsHYK3H592VijbnmBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T19:03:31.323940Z","bundle_sha256":"b95a816f7fa6018a03e93edfc94361d9db2e2a0740be344428851e3f721f3f22"}}