{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:C2DM46LRI57H4SOAV5SAM7TOGD","short_pith_number":"pith:C2DM46LR","canonical_record":{"source":{"id":"2003.10181","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-23T10:59:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5be1039133a2b38e8ff93983f51e36214a62c6ae0a520989aeee07d91421bd99","abstract_canon_sha256":"6d3edfc839ce752156de91ec92caff69d520977ace802418de265099d0cb8a7f"},"schema_version":"1.0"},"canonical_sha256":"1686ce7971477e7e49c0af64067e6e30d8effcab535a10c4ec978b668028e5f0","source":{"kind":"arxiv","id":"2003.10181","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.10181","created_at":"2026-07-05T00:51:43Z"},{"alias_kind":"arxiv_version","alias_value":"2003.10181v2","created_at":"2026-07-05T00:51:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.10181","created_at":"2026-07-05T00:51:43Z"},{"alias_kind":"pith_short_12","alias_value":"C2DM46LRI57H","created_at":"2026-07-05T00:51:43Z"},{"alias_kind":"pith_short_16","alias_value":"C2DM46LRI57H4SOA","created_at":"2026-07-05T00:51:43Z"},{"alias_kind":"pith_short_8","alias_value":"C2DM46LR","created_at":"2026-07-05T00:51:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:C2DM46LRI57H4SOAV5SAM7TOGD","target":"record","payload":{"canonical_record":{"source":{"id":"2003.10181","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-23T10:59:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5be1039133a2b38e8ff93983f51e36214a62c6ae0a520989aeee07d91421bd99","abstract_canon_sha256":"6d3edfc839ce752156de91ec92caff69d520977ace802418de265099d0cb8a7f"},"schema_version":"1.0"},"canonical_sha256":"1686ce7971477e7e49c0af64067e6e30d8effcab535a10c4ec978b668028e5f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:43.992328Z","signature_b64":"II+WrOgI7f+ekUPL+CUkbBuNKji/wGfa738NbEGCHTHI6SCp15TtEdMow+0rIxgByjU3V+93py02KFgLiCF8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1686ce7971477e7e49c0af64067e6e30d8effcab535a10c4ec978b668028e5f0","last_reissued_at":"2026-07-05T00:51:43.991987Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:43.991987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.10181","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":"2026-07-05T00:51:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GONCF+JT5Zn0Lt2MjTrflwj2/e/lcI+VPY82S4bTQMcMbo2BrqEoXZ71Z9RjC6Ug7pUIzO3kPq6W1NvZNN1aDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:48:09.566955Z"},"content_sha256":"34ef062a1cbf2e3d627ab131433bb6a7205721ee6d169ddb0102358f505766ff","schema_version":"1.0","event_id":"sha256:34ef062a1cbf2e3d627ab131433bb6a7205721ee6d169ddb0102358f505766ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:C2DM46LRI57H4SOAV5SAM7TOGD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Importance of using appropriate baselines for evaluation of data-efficiency in deep reinforcement learning for Atari","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kacper Kielak","submitted_at":"2020-03-23T10:59:04Z","abstract_excerpt":"Reinforcement learning (RL) has seen great advancements in the past few years. Nevertheless, the consensus among the RL community is that currently used methods, despite all their benefits, suffer from extreme data inefficiency, especially in the rich visual domains like Atari. To circumvent this problem, novel approaches were introduced that often claim to be much more efficient than popular variations of the state-of-the-art DQN algorithm. In this paper, however, we demonstrate that the newly proposed techniques simply used unfair baselines in their experiments. Namely, we show that the actu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.10181","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/2003.10181/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":"2026-07-05T00:51:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bGMLgObhYiyEl+0HcXrvKxqgkc+lSdtplVd+JRePKA0OoFSaJ0zVP62CZJd/ARB6dfJr0aIjU97VHL/Lp3cbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:48:09.567288Z"},"content_sha256":"4b2bdc618242995d1d01295982a4102416d887262d71267889c55f20ea60aaa5","schema_version":"1.0","event_id":"sha256:4b2bdc618242995d1d01295982a4102416d887262d71267889c55f20ea60aaa5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C2DM46LRI57H4SOAV5SAM7TOGD/bundle.json","state_url":"https://pith.science/pith/C2DM46LRI57H4SOAV5SAM7TOGD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C2DM46LRI57H4SOAV5SAM7TOGD/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":"2026-08-22T03:48:09Z","links":{"resolver":"https://pith.science/pith/C2DM46LRI57H4SOAV5SAM7TOGD","bundle":"https://pith.science/pith/C2DM46LRI57H4SOAV5SAM7TOGD/bundle.json","state":"https://pith.science/pith/C2DM46LRI57H4SOAV5SAM7TOGD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C2DM46LRI57H4SOAV5SAM7TOGD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:C2DM46LRI57H4SOAV5SAM7TOGD","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":"6d3edfc839ce752156de91ec92caff69d520977ace802418de265099d0cb8a7f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-23T10:59:04Z","title_canon_sha256":"5be1039133a2b38e8ff93983f51e36214a62c6ae0a520989aeee07d91421bd99"},"schema_version":"1.0","source":{"id":"2003.10181","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.10181","created_at":"2026-07-05T00:51:43Z"},{"alias_kind":"arxiv_version","alias_value":"2003.10181v2","created_at":"2026-07-05T00:51:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.10181","created_at":"2026-07-05T00:51:43Z"},{"alias_kind":"pith_short_12","alias_value":"C2DM46LRI57H","created_at":"2026-07-05T00:51:43Z"},{"alias_kind":"pith_short_16","alias_value":"C2DM46LRI57H4SOA","created_at":"2026-07-05T00:51:43Z"},{"alias_kind":"pith_short_8","alias_value":"C2DM46LR","created_at":"2026-07-05T00:51:43Z"}],"graph_snapshots":[{"event_id":"sha256:4b2bdc618242995d1d01295982a4102416d887262d71267889c55f20ea60aaa5","target":"graph","created_at":"2026-07-05T00:51:43Z","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/2003.10181/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has seen great advancements in the past few years. Nevertheless, the consensus among the RL community is that currently used methods, despite all their benefits, suffer from extreme data inefficiency, especially in the rich visual domains like Atari. To circumvent this problem, novel approaches were introduced that often claim to be much more efficient than popular variations of the state-of-the-art DQN algorithm. In this paper, however, we demonstrate that the newly proposed techniques simply used unfair baselines in their experiments. Namely, we show that the actu","authors_text":"Kacper Kielak","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-23T10:59:04Z","title":"Importance of using appropriate baselines for evaluation of data-efficiency in deep reinforcement learning for Atari"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.10181","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":"sha256:34ef062a1cbf2e3d627ab131433bb6a7205721ee6d169ddb0102358f505766ff","target":"record","created_at":"2026-07-05T00:51:43Z","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":"6d3edfc839ce752156de91ec92caff69d520977ace802418de265099d0cb8a7f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-23T10:59:04Z","title_canon_sha256":"5be1039133a2b38e8ff93983f51e36214a62c6ae0a520989aeee07d91421bd99"},"schema_version":"1.0","source":{"id":"2003.10181","kind":"arxiv","version":2}},"canonical_sha256":"1686ce7971477e7e49c0af64067e6e30d8effcab535a10c4ec978b668028e5f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1686ce7971477e7e49c0af64067e6e30d8effcab535a10c4ec978b668028e5f0","first_computed_at":"2026-07-05T00:51:43.991987Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:51:43.991987Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"II+WrOgI7f+ekUPL+CUkbBuNKji/wGfa738NbEGCHTHI6SCp15TtEdMow+0rIxgByjU3V+93py02KFgLiCF8Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:51:43.992328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.10181","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:34ef062a1cbf2e3d627ab131433bb6a7205721ee6d169ddb0102358f505766ff","sha256:4b2bdc618242995d1d01295982a4102416d887262d71267889c55f20ea60aaa5"],"state_sha256":"7323b68cddf32dda677b9023883f5385a3b3001057ffa6afb442c52e83593dae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L6GIz9A68x/lb1CHSzCMYTRXXgLRTBaaOz8UH5aDfwYZJwxdfwbPM3z9xlpU2/MqKzgSSQF+qtlgdk2qU5WpCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T03:48:09.570588Z","bundle_sha256":"b70848cb20f250044b51124af65f3cbdfd82f6f574d9b070a2a7da4dea61a7a1"}}