{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:F2LZEFTFOQ5JLJJA2RL6GIBNUD","short_pith_number":"pith:F2LZEFTF","canonical_record":{"source":{"id":"1512.01563","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-04T21:06:04Z","cross_cats_sorted":[],"title_canon_sha256":"31c6cca8acc36950e467538d7fb22708931aca23d766c46943b9009c0177b469","abstract_canon_sha256":"00d8213ca0bfe44b28a149036a5785bed6874a41cacb06e0798c3526180d7e7c"},"schema_version":"1.0"},"canonical_sha256":"2e97921665743a95a520d457e3202da0e17bd767815522d4b8639cdf84b746a7","source":{"kind":"arxiv","id":"1512.01563","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.01563","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"arxiv_version","alias_value":"1512.01563v2","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.01563","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"pith_short_12","alias_value":"F2LZEFTFOQ5J","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"F2LZEFTFOQ5JLJJA","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"F2LZEFTF","created_at":"2026-05-18T12:29:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:F2LZEFTFOQ5JLJJA2RL6GIBNUD","target":"record","payload":{"canonical_record":{"source":{"id":"1512.01563","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-04T21:06:04Z","cross_cats_sorted":[],"title_canon_sha256":"31c6cca8acc36950e467538d7fb22708931aca23d766c46943b9009c0177b469","abstract_canon_sha256":"00d8213ca0bfe44b28a149036a5785bed6874a41cacb06e0798c3526180d7e7c"},"schema_version":"1.0"},"canonical_sha256":"2e97921665743a95a520d457e3202da0e17bd767815522d4b8639cdf84b746a7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:29.408603Z","signature_b64":"wUDJkKU/yD8tHROK2F6v6KvomySizT9sjAZiA+cJutxFesJzmH55A7JZef8M8q2u+sK7pjF/sgFlZ+1ffoC1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e97921665743a95a520d457e3202da0e17bd767815522d4b8639cdf84b746a7","last_reissued_at":"2026-05-18T01:16:29.408092Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:29.408092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.01563","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":"2026-05-18T01:16:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tcuXSd9lEmngrkN5tb1QPM9lmGOISR2bYktbeFS2GMV2ZVscnVysaJDzkXoOSnQ7lVcPWzFhhRHUWOcz+X0pCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T18:21:41.870243Z"},"content_sha256":"ed1aa0b7421c604b4b699e209820304b4c1632384ae698809ddbbac56561798f","schema_version":"1.0","event_id":"sha256:ed1aa0b7421c604b4b699e209820304b4c1632384ae698809ddbbac56561798f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:F2LZEFTFOQ5JLJJA2RL6GIBNUD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"State of the Art Control of Atari Games Using Shallow Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Erik Talvitie, Marlos C. Machado, Michael Bowling, Yitao Liang","submitted_at":"2015-12-04T21:06:04Z","abstract_excerpt":"The recently introduced Deep Q-Networks (DQN) algorithm has gained attention as one of the first successful combinations of deep neural networks and reinforcement learning. Its promise was demonstrated in the Arcade Learning Environment (ALE), a challenging framework composed of dozens of Atari 2600 games used to evaluate general competency in AI. It achieved dramatically better results than earlier approaches, showing that its ability to learn good representations is quite robust and general. This paper attempts to understand the principles that underlie DQN's impressive performance and to be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.01563","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":"2026-05-18T01:16:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fKhz6C2rPfgrqF+uCgMRi2ejxjio/wXpc8ra3RyC2/jclPjD90jpFzIEIBT32WeRKU8j2EaRUFlzyzBt4x4bDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T18:21:41.870607Z"},"content_sha256":"1adb4f3b2b2cba43f23aa16b07e7c4c46e06737ed32a3404cab0c6571e09ba9b","schema_version":"1.0","event_id":"sha256:1adb4f3b2b2cba43f23aa16b07e7c4c46e06737ed32a3404cab0c6571e09ba9b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F2LZEFTFOQ5JLJJA2RL6GIBNUD/bundle.json","state_url":"https://pith.science/pith/F2LZEFTFOQ5JLJJA2RL6GIBNUD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F2LZEFTFOQ5JLJJA2RL6GIBNUD/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":"2026-06-03T18:21:41Z","links":{"resolver":"https://pith.science/pith/F2LZEFTFOQ5JLJJA2RL6GIBNUD","bundle":"https://pith.science/pith/F2LZEFTFOQ5JLJJA2RL6GIBNUD/bundle.json","state":"https://pith.science/pith/F2LZEFTFOQ5JLJJA2RL6GIBNUD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F2LZEFTFOQ5JLJJA2RL6GIBNUD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:F2LZEFTFOQ5JLJJA2RL6GIBNUD","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":"00d8213ca0bfe44b28a149036a5785bed6874a41cacb06e0798c3526180d7e7c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-04T21:06:04Z","title_canon_sha256":"31c6cca8acc36950e467538d7fb22708931aca23d766c46943b9009c0177b469"},"schema_version":"1.0","source":{"id":"1512.01563","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.01563","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"arxiv_version","alias_value":"1512.01563v2","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.01563","created_at":"2026-05-18T01:16:29Z"},{"alias_kind":"pith_short_12","alias_value":"F2LZEFTFOQ5J","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"F2LZEFTFOQ5JLJJA","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"F2LZEFTF","created_at":"2026-05-18T12:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:1adb4f3b2b2cba43f23aa16b07e7c4c46e06737ed32a3404cab0c6571e09ba9b","target":"graph","created_at":"2026-05-18T01:16:29Z","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":"The recently introduced Deep Q-Networks (DQN) algorithm has gained attention as one of the first successful combinations of deep neural networks and reinforcement learning. Its promise was demonstrated in the Arcade Learning Environment (ALE), a challenging framework composed of dozens of Atari 2600 games used to evaluate general competency in AI. It achieved dramatically better results than earlier approaches, showing that its ability to learn good representations is quite robust and general. This paper attempts to understand the principles that underlie DQN's impressive performance and to be","authors_text":"Erik Talvitie, Marlos C. Machado, Michael Bowling, Yitao Liang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-04T21:06:04Z","title":"State of the Art Control of Atari Games Using Shallow Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.01563","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:ed1aa0b7421c604b4b699e209820304b4c1632384ae698809ddbbac56561798f","target":"record","created_at":"2026-05-18T01:16:29Z","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":"00d8213ca0bfe44b28a149036a5785bed6874a41cacb06e0798c3526180d7e7c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-12-04T21:06:04Z","title_canon_sha256":"31c6cca8acc36950e467538d7fb22708931aca23d766c46943b9009c0177b469"},"schema_version":"1.0","source":{"id":"1512.01563","kind":"arxiv","version":2}},"canonical_sha256":"2e97921665743a95a520d457e3202da0e17bd767815522d4b8639cdf84b746a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e97921665743a95a520d457e3202da0e17bd767815522d4b8639cdf84b746a7","first_computed_at":"2026-05-18T01:16:29.408092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:16:29.408092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wUDJkKU/yD8tHROK2F6v6KvomySizT9sjAZiA+cJutxFesJzmH55A7JZef8M8q2u+sK7pjF/sgFlZ+1ffoC1AA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:16:29.408603Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.01563","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed1aa0b7421c604b4b699e209820304b4c1632384ae698809ddbbac56561798f","sha256:1adb4f3b2b2cba43f23aa16b07e7c4c46e06737ed32a3404cab0c6571e09ba9b"],"state_sha256":"2ed15b39d1c8100c46a0fc5932407607e878cf38598968622075a77f07de9924"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PjW9d/jK/oBL/NWaNgQiDKIbHD755JSQrJo7Hwaj61+bwGr+D8bueXw+aeMfqFBlDccfVDeTyas+tg7YuvgPBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T18:21:41.872667Z","bundle_sha256":"6f67dd1a7ee60f876b344884597317969ed06f09180a3e72beb418f3162e070e"}}