{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:R6BET6LIN64JQ7LVI3ULIORNDA","short_pith_number":"pith:R6BET6LI","canonical_record":{"source":{"id":"1611.07078","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-21T22:06:23Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"00a8b279b2e5664a59f6d3baa5c009d353b6c413eaad93986d6b1fbf023fc7ba","abstract_canon_sha256":"f12b2b2e44b7b3846db481abfd55c421524396a8a873b831e607d1149fcccb82"},"schema_version":"1.0"},"canonical_sha256":"8f8249f9686fb8987d7546e8b43a2d182b4c639656d82b7f4022b4e7ef5e1ef4","source":{"kind":"arxiv","id":"1611.07078","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.07078","created_at":"2026-05-18T00:37:54Z"},{"alias_kind":"arxiv_version","alias_value":"1611.07078v2","created_at":"2026-05-18T00:37:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.07078","created_at":"2026-05-18T00:37:54Z"},{"alias_kind":"pith_short_12","alias_value":"R6BET6LIN64J","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"R6BET6LIN64JQ7LV","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"R6BET6LI","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:R6BET6LIN64JQ7LVI3ULIORNDA","target":"record","payload":{"canonical_record":{"source":{"id":"1611.07078","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-21T22:06:23Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"00a8b279b2e5664a59f6d3baa5c009d353b6c413eaad93986d6b1fbf023fc7ba","abstract_canon_sha256":"f12b2b2e44b7b3846db481abfd55c421524396a8a873b831e607d1149fcccb82"},"schema_version":"1.0"},"canonical_sha256":"8f8249f9686fb8987d7546e8b43a2d182b4c639656d82b7f4022b4e7ef5e1ef4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:54.711616Z","signature_b64":"g/SJt4g0+F1xb2hFZOdt9XInjlpF1V6HrB8ifD0rgWhBK/MkWZauRcDZnNQ1KvCvz19gThwqWIxgajw4DvRkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f8249f9686fb8987d7546e8b43a2d182b4c639656d82b7f4022b4e7ef5e1ef4","last_reissued_at":"2026-05-18T00:37:54.711091Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:54.711091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.07078","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":"2026-05-18T00:37:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SSRKZsep6YZBPtIbXOvU/hzvowmYBb2JtjUKoTXsHG2F53klfO64LZzo75OsRNDQjCnIxkm/+Ssst2SmcgGnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T22:46:59.162335Z"},"content_sha256":"b5558a7e545dd06bb72110787c8697e4fe8861cfb64e480f04967e803487d352","schema_version":"1.0","event_id":"sha256:b5558a7e545dd06bb72110787c8697e4fe8861cfb64e480f04967e803487d352"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:R6BET6LIN64JQ7LVI3ULIORNDA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Felix Leibfried, Katja Hofmann, Nate Kushman","submitted_at":"2016-11-21T22:06:23Z","abstract_excerpt":"Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to act effectively across a wide range of environments such as Atari games, but require huge amounts of data. Model-based techniques are more data-efficient, but need to acquire explicit knowledge about the environment.\n  In this paper, we take a step towards using model-based techniques in environments with a high-dimensional visual state space by demonstrating"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.07078","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":""},"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":"2026-05-18T00:37:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rDiH52Zddoxhkm1yqb/MyNQMBc5kLOQC5VspBlNTTquAbbQ1kzhAL68zcM3FpR7p66hoi1x+Mf7bAgJ9X1EOAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T22:46:59.162993Z"},"content_sha256":"a5fc5306efbecbd54bb4e03b806a163879ea958e55b3d5e00f73e0bba23e1931","schema_version":"1.0","event_id":"sha256:a5fc5306efbecbd54bb4e03b806a163879ea958e55b3d5e00f73e0bba23e1931"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R6BET6LIN64JQ7LVI3ULIORNDA/bundle.json","state_url":"https://pith.science/pith/R6BET6LIN64JQ7LVI3ULIORNDA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R6BET6LIN64JQ7LVI3ULIORNDA/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":"2026-06-07T22:46:59Z","links":{"resolver":"https://pith.science/pith/R6BET6LIN64JQ7LVI3ULIORNDA","bundle":"https://pith.science/pith/R6BET6LIN64JQ7LVI3ULIORNDA/bundle.json","state":"https://pith.science/pith/R6BET6LIN64JQ7LVI3ULIORNDA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R6BET6LIN64JQ7LVI3ULIORNDA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:R6BET6LIN64JQ7LVI3ULIORNDA","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":"f12b2b2e44b7b3846db481abfd55c421524396a8a873b831e607d1149fcccb82","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-21T22:06:23Z","title_canon_sha256":"00a8b279b2e5664a59f6d3baa5c009d353b6c413eaad93986d6b1fbf023fc7ba"},"schema_version":"1.0","source":{"id":"1611.07078","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.07078","created_at":"2026-05-18T00:37:54Z"},{"alias_kind":"arxiv_version","alias_value":"1611.07078v2","created_at":"2026-05-18T00:37:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.07078","created_at":"2026-05-18T00:37:54Z"},{"alias_kind":"pith_short_12","alias_value":"R6BET6LIN64J","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"R6BET6LIN64JQ7LV","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"R6BET6LI","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:a5fc5306efbecbd54bb4e03b806a163879ea958e55b3d5e00f73e0bba23e1931","target":"graph","created_at":"2026-05-18T00:37:54Z","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"},"paper":{"abstract_excerpt":"Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to act effectively across a wide range of environments such as Atari games, but require huge amounts of data. Model-based techniques are more data-efficient, but need to acquire explicit knowledge about the environment.\n  In this paper, we take a step towards using model-based techniques in environments with a high-dimensional visual state space by demonstrating","authors_text":"Felix Leibfried, Katja Hofmann, Nate Kushman","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-21T22:06:23Z","title":"A Deep Learning Approach for Joint Video Frame and Reward Prediction in Atari Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.07078","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:b5558a7e545dd06bb72110787c8697e4fe8861cfb64e480f04967e803487d352","target":"record","created_at":"2026-05-18T00:37:54Z","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":"f12b2b2e44b7b3846db481abfd55c421524396a8a873b831e607d1149fcccb82","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-11-21T22:06:23Z","title_canon_sha256":"00a8b279b2e5664a59f6d3baa5c009d353b6c413eaad93986d6b1fbf023fc7ba"},"schema_version":"1.0","source":{"id":"1611.07078","kind":"arxiv","version":2}},"canonical_sha256":"8f8249f9686fb8987d7546e8b43a2d182b4c639656d82b7f4022b4e7ef5e1ef4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f8249f9686fb8987d7546e8b43a2d182b4c639656d82b7f4022b4e7ef5e1ef4","first_computed_at":"2026-05-18T00:37:54.711091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:37:54.711091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g/SJt4g0+F1xb2hFZOdt9XInjlpF1V6HrB8ifD0rgWhBK/MkWZauRcDZnNQ1KvCvz19gThwqWIxgajw4DvRkAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:37:54.711616Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.07078","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5558a7e545dd06bb72110787c8697e4fe8861cfb64e480f04967e803487d352","sha256:a5fc5306efbecbd54bb4e03b806a163879ea958e55b3d5e00f73e0bba23e1931"],"state_sha256":"61a23002ae5aa94fadafc80a06635c0f222b2603ab11ec1c8c2e0e5d017a2e53"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wKbI5ONJgMF0hDuXQRA3rJ0dD1ZwuUD0+iE+B3k9e2fvoV9HaSSRKUUTV2YnTTdthlb9JLWjPea+ocgI7GmfCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T22:46:59.166783Z","bundle_sha256":"18311e14e9bec6fab5060a674028143afcf114338623285518afb29d9b5c3468"}}