{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RWJSQJHRPSXMCZ4WM3XP2H5M7P","short_pith_number":"pith:RWJSQJHR","schema_version":"1.0","canonical_sha256":"8d932824f17caec1679666eefd1facfbc9f65dfdb9b373588e0a3797574c7989","source":{"kind":"arxiv","id":"2111.10247","version":1},"attestation_state":"computed","paper":{"title":"Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dominik Schmidt, Thomas Schmied","submitted_at":"2021-11-19T14:37:37Z","abstract_excerpt":"Across the Arcade Learning Environment, Rainbow achieves a level of performance competitive with humans and modern RL algorithms. However, attaining this level of performance requires large amounts of data and hardware resources, making research in this area computationally expensive and use in practical applications often infeasible. This paper's contribution is threefold: We (1) propose an improved version of Rainbow, seeking to drastically reduce Rainbow's data, training time, and compute requirements while maintaining its competitive performance; (2) we empirically demonstrate the effectiv"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2111.10247","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-19T14:37:37Z","cross_cats_sorted":[],"title_canon_sha256":"ec3e8d225c83421b544faa2078687b3c35e4d1cc65783b349cb02ab43188a92c","abstract_canon_sha256":"3fcf10a0fc3e16502455d5e5126521199a59ff6fbe6dc30adf4b4f7564955764"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:29.971041Z","signature_b64":"YbuokF+Witj1Sp3JVvVaFnaA+DSxzOwkAVaj7ghFDccWlrIi/WcoSKCVwts9UAez+d0ua8174ivSFT674G8vDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d932824f17caec1679666eefd1facfbc9f65dfdb9b373588e0a3797574c7989","last_reissued_at":"2026-07-05T03:33:29.970554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:29.970554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast and Data-Efficient Training of Rainbow: an Experimental Study on Atari","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dominik Schmidt, Thomas Schmied","submitted_at":"2021-11-19T14:37:37Z","abstract_excerpt":"Across the Arcade Learning Environment, Rainbow achieves a level of performance competitive with humans and modern RL algorithms. However, attaining this level of performance requires large amounts of data and hardware resources, making research in this area computationally expensive and use in practical applications often infeasible. This paper's contribution is threefold: We (1) propose an improved version of Rainbow, seeking to drastically reduce Rainbow's data, training time, and compute requirements while maintaining its competitive performance; (2) we empirically demonstrate the effectiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10247","kind":"arxiv","version":1},"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/2111.10247/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.10247","created_at":"2026-07-05T03:33:29.970631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.10247v1","created_at":"2026-07-05T03:33:29.970631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10247","created_at":"2026-07-05T03:33:29.970631+00:00"},{"alias_kind":"pith_short_12","alias_value":"RWJSQJHRPSXM","created_at":"2026-07-05T03:33:29.970631+00:00"},{"alias_kind":"pith_short_16","alias_value":"RWJSQJHRPSXMCZ4W","created_at":"2026-07-05T03:33:29.970631+00:00"},{"alias_kind":"pith_short_8","alias_value":"RWJSQJHR","created_at":"2026-07-05T03:33:29.970631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04970","citing_title":"DeGuV: Depth-Guided Visual Reinforcement Learning for Generalization and Interpretability in Manipulation","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RWJSQJHRPSXMCZ4WM3XP2H5M7P","json":"https://pith.science/pith/RWJSQJHRPSXMCZ4WM3XP2H5M7P.json","graph_json":"https://pith.science/api/pith-number/RWJSQJHRPSXMCZ4WM3XP2H5M7P/graph.json","events_json":"https://pith.science/api/pith-number/RWJSQJHRPSXMCZ4WM3XP2H5M7P/events.json","paper":"https://pith.science/paper/RWJSQJHR"},"agent_actions":{"view_html":"https://pith.science/pith/RWJSQJHRPSXMCZ4WM3XP2H5M7P","download_json":"https://pith.science/pith/RWJSQJHRPSXMCZ4WM3XP2H5M7P.json","view_paper":"https://pith.science/paper/RWJSQJHR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.10247&json=true","fetch_graph":"https://pith.science/api/pith-number/RWJSQJHRPSXMCZ4WM3XP2H5M7P/graph.json","fetch_events":"https://pith.science/api/pith-number/RWJSQJHRPSXMCZ4WM3XP2H5M7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RWJSQJHRPSXMCZ4WM3XP2H5M7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RWJSQJHRPSXMCZ4WM3XP2H5M7P/action/storage_attestation","attest_author":"https://pith.science/pith/RWJSQJHRPSXMCZ4WM3XP2H5M7P/action/author_attestation","sign_citation":"https://pith.science/pith/RWJSQJHRPSXMCZ4WM3XP2H5M7P/action/citation_signature","submit_replication":"https://pith.science/pith/RWJSQJHRPSXMCZ4WM3XP2H5M7P/action/replication_record"}},"created_at":"2026-07-05T03:33:29.970631+00:00","updated_at":"2026-07-05T03:33:29.970631+00:00"}