{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XMJLOIIXZGPUJNHXME5OUOVE6N","short_pith_number":"pith:XMJLOIIX","schema_version":"1.0","canonical_sha256":"bb12b72117c99f44b4f7613aea3aa4f376733a79368333b3d96268e2cb2584a4","source":{"kind":"arxiv","id":"2101.02722","version":1},"attestation_state":"computed","paper":{"title":"The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Austin Stone, Kurt Konolige, Oscar Ramirez, Rico Jonschkowski","submitted_at":"2021-01-07T19:03:34Z","abstract_excerpt":"Robots have to face challenging perceptual settings, including changes in viewpoint, lighting, and background. Current simulated reinforcement learning (RL) benchmarks such as DM Control provide visual input without such complexity, which limits the transfer of well-performing methods to the real world. In this paper, we extend DM Control with three kinds of visual distractions (variations in background, color, and camera pose) to produce a new challenging benchmark for vision-based control, and we analyze state of the art RL algorithms in these settings. Our experiments show that current RL m"},"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":"2101.02722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-01-07T19:03:34Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"a707d15d9899bd49bf87595b3a56e7ee1cfdefae917cd621f77ea410a8f72b3d","abstract_canon_sha256":"03025112618268744b74df6b88749598a1d716fb6d1a21d0216a42945513d7f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:29.859493Z","signature_b64":"YZCu8LmaNSh5PNfNi3T0JkSakcIA61fWJL2vMtVer0LuLF8u5hP8zJSTB9fNSf+3IAw2iQRWz6o4nGvoO+i1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb12b72117c99f44b4f7613aea3aa4f376733a79368333b3d96268e2cb2584a4","last_reissued_at":"2026-07-05T02:05:29.859006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:29.859006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Distracting Control Suite -- A Challenging Benchmark for Reinforcement Learning from Pixels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Austin Stone, Kurt Konolige, Oscar Ramirez, Rico Jonschkowski","submitted_at":"2021-01-07T19:03:34Z","abstract_excerpt":"Robots have to face challenging perceptual settings, including changes in viewpoint, lighting, and background. Current simulated reinforcement learning (RL) benchmarks such as DM Control provide visual input without such complexity, which limits the transfer of well-performing methods to the real world. In this paper, we extend DM Control with three kinds of visual distractions (variations in background, color, and camera pose) to produce a new challenging benchmark for vision-based control, and we analyze state of the art RL algorithms in these settings. Our experiments show that current RL m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.02722","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/2101.02722/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":"2101.02722","created_at":"2026-07-05T02:05:29.859068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.02722v1","created_at":"2026-07-05T02:05:29.859068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.02722","created_at":"2026-07-05T02:05:29.859068+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMJLOIIXZGPU","created_at":"2026-07-05T02:05:29.859068+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMJLOIIXZGPUJNHX","created_at":"2026-07-05T02:05:29.859068+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMJLOIIX","created_at":"2026-07-05T02:05:29.859068+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30544","citing_title":"Latent Actions from Factorized Transition Effects under Agent Ambiguity","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21800","citing_title":"stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20223","citing_title":"Why Latent Actions Fail, and How to Prevent It","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24661","citing_title":"Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04709","citing_title":"ELVIS: Ensemble-Calibrated Latent Imagination for Long-Horizon Visual MPC","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24661","citing_title":"Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMJLOIIXZGPUJNHXME5OUOVE6N","json":"https://pith.science/pith/XMJLOIIXZGPUJNHXME5OUOVE6N.json","graph_json":"https://pith.science/api/pith-number/XMJLOIIXZGPUJNHXME5OUOVE6N/graph.json","events_json":"https://pith.science/api/pith-number/XMJLOIIXZGPUJNHXME5OUOVE6N/events.json","paper":"https://pith.science/paper/XMJLOIIX"},"agent_actions":{"view_html":"https://pith.science/pith/XMJLOIIXZGPUJNHXME5OUOVE6N","download_json":"https://pith.science/pith/XMJLOIIXZGPUJNHXME5OUOVE6N.json","view_paper":"https://pith.science/paper/XMJLOIIX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.02722&json=true","fetch_graph":"https://pith.science/api/pith-number/XMJLOIIXZGPUJNHXME5OUOVE6N/graph.json","fetch_events":"https://pith.science/api/pith-number/XMJLOIIXZGPUJNHXME5OUOVE6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMJLOIIXZGPUJNHXME5OUOVE6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMJLOIIXZGPUJNHXME5OUOVE6N/action/storage_attestation","attest_author":"https://pith.science/pith/XMJLOIIXZGPUJNHXME5OUOVE6N/action/author_attestation","sign_citation":"https://pith.science/pith/XMJLOIIXZGPUJNHXME5OUOVE6N/action/citation_signature","submit_replication":"https://pith.science/pith/XMJLOIIXZGPUJNHXME5OUOVE6N/action/replication_record"}},"created_at":"2026-07-05T02:05:29.859068+00:00","updated_at":"2026-07-05T02:05:29.859068+00:00"}