{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:6FOO5OD6LNJDYOTPFEHHR7FM3W","short_pith_number":"pith:6FOO5OD6","canonical_record":{"source":{"id":"1507.00814","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-07-03T04:11:15Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"2dcb7de2513ba0d4df196ea513c8e1aa29d39476ab49bcd3518144e5033f36cd","abstract_canon_sha256":"76e607fd0c05b60890b71fb10f68615a98fb09768db5cbc095584180f58846c0"},"schema_version":"1.0"},"canonical_sha256":"f15ceeb87e5b523c3a6f290e78fcacdd93ad51fbad2f50ed6dcaf74f0eb128be","source":{"kind":"arxiv","id":"1507.00814","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.00814","created_at":"2026-05-18T01:26:25Z"},{"alias_kind":"arxiv_version","alias_value":"1507.00814v3","created_at":"2026-05-18T01:26:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.00814","created_at":"2026-05-18T01:26:25Z"},{"alias_kind":"pith_short_12","alias_value":"6FOO5OD6LNJD","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6FOO5OD6LNJDYOTP","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6FOO5OD6","created_at":"2026-05-18T12:29:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:6FOO5OD6LNJDYOTPFEHHR7FM3W","target":"record","payload":{"canonical_record":{"source":{"id":"1507.00814","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-07-03T04:11:15Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"2dcb7de2513ba0d4df196ea513c8e1aa29d39476ab49bcd3518144e5033f36cd","abstract_canon_sha256":"76e607fd0c05b60890b71fb10f68615a98fb09768db5cbc095584180f58846c0"},"schema_version":"1.0"},"canonical_sha256":"f15ceeb87e5b523c3a6f290e78fcacdd93ad51fbad2f50ed6dcaf74f0eb128be","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:25.162772Z","signature_b64":"lKPI/3jfsCwHY1FKW0oqzt/JvBZpOIuoqPtLMjV8owJK+fUx0utvnzQQPlBEiNfWO9NGNu/Nz7Glcpafq8NlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f15ceeb87e5b523c3a6f290e78fcacdd93ad51fbad2f50ed6dcaf74f0eb128be","last_reissued_at":"2026-05-18T01:26:25.162291Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:25.162291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.00814","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":"2026-05-18T01:26:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tPCJ3G0OEwuIQarvsAIPsTHbS1oH2VZKpXDDd2lZmJ03m5GW+CvOPredxSH3wznR+olXcofEZ44Apml6VsrkDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T09:53:23.672516Z"},"content_sha256":"c0d6c06d5205cdb941d298756737701ea0a2c4c7a9d2e2eee9ea90a285856f3d","schema_version":"1.0","event_id":"sha256:c0d6c06d5205cdb941d298756737701ea0a2c4c7a9d2e2eee9ea90a285856f3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:6FOO5OD6LNJDYOTPFEHHR7FM3W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Bradly C. Stadie, Pieter Abbeel, Sergey Levine","submitted_at":"2015-07-03T04:11:15Z","abstract_excerpt":"Achieving efficient and scalable exploration in complex domains poses a major challenge in reinforcement learning. While Bayesian and PAC-MDP approaches to the exploration problem offer strong formal guarantees, they are often impractical in higher dimensions due to their reliance on enumerating the state-action space. Hence, exploration in complex domains is often performed with simple epsilon-greedy methods. In this paper, we consider the challenging Atari games domain, which requires processing raw pixel inputs and delayed rewards. We evaluate several more sophisticated exploration strategi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.00814","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":"2026-05-18T01:26:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DwFqo3M9Lv8JM8azCU8wh2WTtEplopl+oxwXn6ZUXsSYf8hOBXD22nxhnvJuu1qT7HXZBkH5zLObcpVICUA5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T09:53:23.673193Z"},"content_sha256":"b6ce8cdac35fd3eb5151b06e3a8bcb503118f202e280241d565816ef62db0ec4","schema_version":"1.0","event_id":"sha256:b6ce8cdac35fd3eb5151b06e3a8bcb503118f202e280241d565816ef62db0ec4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6FOO5OD6LNJDYOTPFEHHR7FM3W/bundle.json","state_url":"https://pith.science/pith/6FOO5OD6LNJDYOTPFEHHR7FM3W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6FOO5OD6LNJDYOTPFEHHR7FM3W/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":"2026-06-10T09:53:23Z","links":{"resolver":"https://pith.science/pith/6FOO5OD6LNJDYOTPFEHHR7FM3W","bundle":"https://pith.science/pith/6FOO5OD6LNJDYOTPFEHHR7FM3W/bundle.json","state":"https://pith.science/pith/6FOO5OD6LNJDYOTPFEHHR7FM3W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6FOO5OD6LNJDYOTPFEHHR7FM3W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:6FOO5OD6LNJDYOTPFEHHR7FM3W","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":"76e607fd0c05b60890b71fb10f68615a98fb09768db5cbc095584180f58846c0","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-07-03T04:11:15Z","title_canon_sha256":"2dcb7de2513ba0d4df196ea513c8e1aa29d39476ab49bcd3518144e5033f36cd"},"schema_version":"1.0","source":{"id":"1507.00814","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.00814","created_at":"2026-05-18T01:26:25Z"},{"alias_kind":"arxiv_version","alias_value":"1507.00814v3","created_at":"2026-05-18T01:26:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.00814","created_at":"2026-05-18T01:26:25Z"},{"alias_kind":"pith_short_12","alias_value":"6FOO5OD6LNJD","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_16","alias_value":"6FOO5OD6LNJDYOTP","created_at":"2026-05-18T12:29:07Z"},{"alias_kind":"pith_short_8","alias_value":"6FOO5OD6","created_at":"2026-05-18T12:29:07Z"}],"graph_snapshots":[{"event_id":"sha256:b6ce8cdac35fd3eb5151b06e3a8bcb503118f202e280241d565816ef62db0ec4","target":"graph","created_at":"2026-05-18T01:26:25Z","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":"Achieving efficient and scalable exploration in complex domains poses a major challenge in reinforcement learning. While Bayesian and PAC-MDP approaches to the exploration problem offer strong formal guarantees, they are often impractical in higher dimensions due to their reliance on enumerating the state-action space. Hence, exploration in complex domains is often performed with simple epsilon-greedy methods. In this paper, we consider the challenging Atari games domain, which requires processing raw pixel inputs and delayed rewards. We evaluate several more sophisticated exploration strategi","authors_text":"Bradly C. Stadie, Pieter Abbeel, Sergey Levine","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-07-03T04:11:15Z","title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.00814","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:c0d6c06d5205cdb941d298756737701ea0a2c4c7a9d2e2eee9ea90a285856f3d","target":"record","created_at":"2026-05-18T01:26:25Z","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":"76e607fd0c05b60890b71fb10f68615a98fb09768db5cbc095584180f58846c0","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-07-03T04:11:15Z","title_canon_sha256":"2dcb7de2513ba0d4df196ea513c8e1aa29d39476ab49bcd3518144e5033f36cd"},"schema_version":"1.0","source":{"id":"1507.00814","kind":"arxiv","version":3}},"canonical_sha256":"f15ceeb87e5b523c3a6f290e78fcacdd93ad51fbad2f50ed6dcaf74f0eb128be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f15ceeb87e5b523c3a6f290e78fcacdd93ad51fbad2f50ed6dcaf74f0eb128be","first_computed_at":"2026-05-18T01:26:25.162291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:26:25.162291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lKPI/3jfsCwHY1FKW0oqzt/JvBZpOIuoqPtLMjV8owJK+fUx0utvnzQQPlBEiNfWO9NGNu/Nz7Glcpafq8NlDg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:26:25.162772Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.00814","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0d6c06d5205cdb941d298756737701ea0a2c4c7a9d2e2eee9ea90a285856f3d","sha256:b6ce8cdac35fd3eb5151b06e3a8bcb503118f202e280241d565816ef62db0ec4"],"state_sha256":"58a619b85e73615af35df81c418ab8219205f42b36489ef5fdc8806c325437af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xoo8SF+ypChv0kz0Dha4QeOF54zE1ewPt7y2e1psJR7inaOPoNjPcsvGKFafW12oBmWAA39M/DangTW3L0bxBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T09:53:23.677211Z","bundle_sha256":"1aa62c58b2e68956c00855e72447056f49684610a1225c5c49174df5add48fa8"}}