{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IUSU7BX236XGQO6S2XA3DPA465","short_pith_number":"pith:IUSU7BX2","canonical_record":{"source":{"id":"1801.00690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-02T15:48:14Z","cross_cats_sorted":[],"title_canon_sha256":"11aa661c4e00a25af435dfbf79cbf609c7eb3068d3616fb0872f8cc672192052","abstract_canon_sha256":"09ca9a5aa7251c16ad0513268c06ebd7e89db5ac2fd395f5670995b8bfb1c5ae"},"schema_version":"1.0"},"canonical_sha256":"45254f86fadfae683bd2d5c1b1bc1cf74a89529d144fca0c213d25f8fa922efd","source":{"kind":"arxiv","id":"1801.00690","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.00690","created_at":"2026-07-04T22:27:08Z"},{"alias_kind":"arxiv_version","alias_value":"1801.00690v1","created_at":"2026-07-04T22:27:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00690","created_at":"2026-07-04T22:27:08Z"},{"alias_kind":"pith_short_12","alias_value":"IUSU7BX236XG","created_at":"2026-07-04T22:27:08Z"},{"alias_kind":"pith_short_16","alias_value":"IUSU7BX236XGQO6S","created_at":"2026-07-04T22:27:08Z"},{"alias_kind":"pith_short_8","alias_value":"IUSU7BX2","created_at":"2026-07-04T22:27:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IUSU7BX236XGQO6S2XA3DPA465","target":"record","payload":{"canonical_record":{"source":{"id":"1801.00690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-02T15:48:14Z","cross_cats_sorted":[],"title_canon_sha256":"11aa661c4e00a25af435dfbf79cbf609c7eb3068d3616fb0872f8cc672192052","abstract_canon_sha256":"09ca9a5aa7251c16ad0513268c06ebd7e89db5ac2fd395f5670995b8bfb1c5ae"},"schema_version":"1.0"},"canonical_sha256":"45254f86fadfae683bd2d5c1b1bc1cf74a89529d144fca0c213d25f8fa922efd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T22:27:08.426053Z","signature_b64":"yce4Z/bvxGblX88pHPcXSvbuL2Dz9FDU8FgBCTok5n6OGvJEf4KYkDEOALk1oBbAvUs8t6UYDtfh+LF4paCJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45254f86fadfae683bd2d5c1b1bc1cf74a89529d144fca0c213d25f8fa922efd","last_reissued_at":"2026-07-04T22:27:08.425426Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T22:27:08.425426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.00690","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T22:27:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NcwyqBK/vhXX1AIkA6al33856c/recZ0G+ta9wK5m+W/3b5fbpaDwER10Cw1E93uvr0Fdx5Kcya/YvXlCf1sBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:41:33.497814Z"},"content_sha256":"c94adfe49a031aff959a7362f01a81b2749333bef53127fe88a26e66080ab939","schema_version":"1.0","event_id":"sha256:c94adfe49a031aff959a7362f01a81b2749333bef53127fe88a26e66080ab939"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IUSU7BX236XGQO6S2XA3DPA465","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DeepMind Control Suite","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The DeepMind Control Suite offers a standardized set of continuous control tasks to benchmark reinforcement learning agents.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Abbas Abdolmaleki, Alistair Muldal, Andrew Lefrancq, David Budden, Diego de las Casas, Josh Merel, Martin Riedmiller, Timothy Lillicrap, Tom Erez, Yazhe Li, Yotam Doron, Yuval Tassa","submitted_at":"2018-01-02T15:48:14Z","abstract_excerpt":"The DeepMind Control Suite is a set of continuous control tasks with a standardised structure and interpretable rewards, intended to serve as performance benchmarks for reinforcement learning agents. The tasks are written in Python and powered by the MuJoCo physics engine, making them easy to use and modify. We include benchmarks for several learning algorithms. The Control Suite is publicly available at https://www.github.com/deepmind/dm_control . A video summary of all tasks is available at http://youtu.be/rAai4QzcYbs ."},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The DeepMind Control Suite is a set of continuous control tasks with a standardised structure and interpretable rewards, intended to serve as performance benchmarks for reinforcement learning agents.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen tasks and reward functions are sufficiently representative of real-world control problems and that performance on them will generalize to other domains.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The DeepMind Control Suite supplies a standardized collection of continuous control tasks with interpretable rewards for benchmarking reinforcement learning agents.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The DeepMind Control Suite offers a standardized set of continuous control tasks to benchmark reinforcement learning agents.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"35e364546e00c43de8e47c783972fb0ab04c430091fffc7d8091df1e5ab9431c"},"source":{"id":"1801.00690","kind":"arxiv","version":1},"verdict":{"id":"61aa29e9-f274-4932-b57f-82ac0b44b4f4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T07:40:16.913388Z","strongest_claim":"The DeepMind Control Suite is a set of continuous control tasks with a standardised structure and interpretable rewards, intended to serve as performance benchmarks for reinforcement learning agents.","one_line_summary":"The DeepMind Control Suite supplies a standardized collection of continuous control tasks with interpretable rewards for benchmarking reinforcement learning agents.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen tasks and reward functions are sufficiently representative of real-world control problems and that performance on them will generalize to other domains.","pith_extraction_headline":"The DeepMind Control Suite offers a standardized set of continuous control tasks to benchmark reinforcement learning agents."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1801.00690/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":13,"sample":[{"doi":"","year":null,"title":"Layer Normalization","work_id":"20a2d720-0046-4c7c-bcd6-327ec8143f69","ref_index":1,"cited_arxiv_id":"1607.06450","is_internal_anchor":true},{"doi":"10.1109/tsmc.1983.6313077","year":1983,"title":"doi: 10.1109/TSMC.1983.6313077","work_id":"5d5d0663-101c-45b7-a8b9-acfc8151271a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"A Distributional Perspective on Reinforcement Learning","work_id":"79879eb4-5aa1-4764-9aaa-505a0a1c0f7f","ref_index":3,"cited_arxiv_id":"1707.06887","is_internal_anchor":false},{"doi":"","year":2015,"title":"Simulation tools for model-based robotics: Comparison of bullet, havok, mujoco, ode and physx","work_id":"38cf2474-efac-4a24-9dac-7447fb98b1c4","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control","work_id":"79bc5b68-7f90-4779-aa0d-5e000bdf6421","ref_index":5,"cited_arxiv_id":"1708.04133","is_internal_anchor":false}],"resolved_work":13,"snapshot_sha256":"e5d3d9256b696963fdf555bcc4d70a5a914b595253ea8fb696d4e8fac5a9c342","internal_anchors":4},"formal_canon":{"evidence_count":1,"snapshot_sha256":"9d2968cd73d6b711ea9d4f0230d56d8b47099a9c81078f92f6d2894550110cf7"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"61aa29e9-f274-4932-b57f-82ac0b44b4f4"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-04T22:27:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eXsKtknKQHfD5UirM04+OtIAjSmEeNQdGEvV9jLoi+Hbq3sOrEJ07oZb0jHvMViuR7UyB7t2VEmcVv9pV3Y2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:41:33.499195Z"},"content_sha256":"d052fc361b851c0f4f62b3ff1db1062bc6377e30d2de39cd84c97486a3e885f7","schema_version":"1.0","event_id":"sha256:d052fc361b851c0f4f62b3ff1db1062bc6377e30d2de39cd84c97486a3e885f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IUSU7BX236XGQO6S2XA3DPA465/bundle.json","state_url":"https://pith.science/pith/IUSU7BX236XGQO6S2XA3DPA465/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IUSU7BX236XGQO6S2XA3DPA465/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":"2026-08-13T08:41:33Z","links":{"resolver":"https://pith.science/pith/IUSU7BX236XGQO6S2XA3DPA465","bundle":"https://pith.science/pith/IUSU7BX236XGQO6S2XA3DPA465/bundle.json","state":"https://pith.science/pith/IUSU7BX236XGQO6S2XA3DPA465/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IUSU7BX236XGQO6S2XA3DPA465/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IUSU7BX236XGQO6S2XA3DPA465","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":"09ca9a5aa7251c16ad0513268c06ebd7e89db5ac2fd395f5670995b8bfb1c5ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-02T15:48:14Z","title_canon_sha256":"11aa661c4e00a25af435dfbf79cbf609c7eb3068d3616fb0872f8cc672192052"},"schema_version":"1.0","source":{"id":"1801.00690","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.00690","created_at":"2026-07-04T22:27:08Z"},{"alias_kind":"arxiv_version","alias_value":"1801.00690v1","created_at":"2026-07-04T22:27:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.00690","created_at":"2026-07-04T22:27:08Z"},{"alias_kind":"pith_short_12","alias_value":"IUSU7BX236XG","created_at":"2026-07-04T22:27:08Z"},{"alias_kind":"pith_short_16","alias_value":"IUSU7BX236XGQO6S","created_at":"2026-07-04T22:27:08Z"},{"alias_kind":"pith_short_8","alias_value":"IUSU7BX2","created_at":"2026-07-04T22:27:08Z"}],"graph_snapshots":[{"event_id":"sha256:d052fc361b851c0f4f62b3ff1db1062bc6377e30d2de39cd84c97486a3e885f7","target":"graph","created_at":"2026-07-04T22:27:08Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The DeepMind Control Suite is a set of continuous control tasks with a standardised structure and interpretable rewards, intended to serve as performance benchmarks for reinforcement learning agents."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the chosen tasks and reward functions are sufficiently representative of real-world control problems and that performance on them will generalize to other domains."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"The DeepMind Control Suite supplies a standardized collection of continuous control tasks with interpretable rewards for benchmarking reinforcement learning agents."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"The DeepMind Control Suite offers a standardized set of continuous control tasks to benchmark reinforcement learning agents."}],"snapshot_sha256":"35e364546e00c43de8e47c783972fb0ab04c430091fffc7d8091df1e5ab9431c"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"9d2968cd73d6b711ea9d4f0230d56d8b47099a9c81078f92f6d2894550110cf7"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1801.00690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The DeepMind Control Suite is a set of continuous control tasks with a standardised structure and interpretable rewards, intended to serve as performance benchmarks for reinforcement learning agents. The tasks are written in Python and powered by the MuJoCo physics engine, making them easy to use and modify. We include benchmarks for several learning algorithms. The Control Suite is publicly available at https://www.github.com/deepmind/dm_control . A video summary of all tasks is available at http://youtu.be/rAai4QzcYbs .","authors_text":"Abbas Abdolmaleki, Alistair Muldal, Andrew Lefrancq, David Budden, Diego de las Casas, Josh Merel, Martin Riedmiller, Timothy Lillicrap, Tom Erez, Yazhe Li, Yotam Doron, Yuval Tassa","cross_cats":[],"headline":"The DeepMind Control Suite offers a standardized set of continuous control tasks to benchmark reinforcement learning agents.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-02T15:48:14Z","title":"DeepMind Control Suite"},"references":{"count":13,"internal_anchors":4,"resolved_work":13,"sample":[{"cited_arxiv_id":"1607.06450","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Layer Normalization","work_id":"20a2d720-0046-4c7c-bcd6-327ec8143f69","year":null},{"cited_arxiv_id":"","doi":"10.1109/tsmc.1983.6313077","is_internal_anchor":false,"ref_index":2,"title":"doi: 10.1109/TSMC.1983.6313077","work_id":"5d5d0663-101c-45b7-a8b9-acfc8151271a","year":1983},{"cited_arxiv_id":"1707.06887","doi":"","is_internal_anchor":false,"ref_index":3,"title":"A Distributional Perspective on Reinforcement Learning","work_id":"79879eb4-5aa1-4764-9aaa-505a0a1c0f7f","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Simulation tools for model-based robotics: Comparison of bullet, havok, mujoco, ode and physx","work_id":"38cf2474-efac-4a24-9dac-7447fb98b1c4","year":2015},{"cited_arxiv_id":"1708.04133","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control","work_id":"79bc5b68-7f90-4779-aa0d-5e000bdf6421","year":null}],"snapshot_sha256":"e5d3d9256b696963fdf555bcc4d70a5a914b595253ea8fb696d4e8fac5a9c342"},"source":{"id":"1801.00690","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-13T07:40:16.913388Z","id":"61aa29e9-f274-4932-b57f-82ac0b44b4f4","model_set":{"reader":"grok-4.3"},"one_line_summary":"The DeepMind Control Suite supplies a standardized collection of continuous control tasks with interpretable rewards for benchmarking reinforcement learning agents.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"The DeepMind Control Suite offers a standardized set of continuous control tasks to benchmark reinforcement learning agents.","strongest_claim":"The DeepMind Control Suite is a set of continuous control tasks with a standardised structure and interpretable rewards, intended to serve as performance benchmarks for reinforcement learning agents.","weakest_assumption":"That the chosen tasks and reward functions are sufficiently representative of real-world control problems and that performance on them will generalize to other domains."}},"verdict_id":"61aa29e9-f274-4932-b57f-82ac0b44b4f4"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c94adfe49a031aff959a7362f01a81b2749333bef53127fe88a26e66080ab939","target":"record","created_at":"2026-07-04T22:27:08Z","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":"09ca9a5aa7251c16ad0513268c06ebd7e89db5ac2fd395f5670995b8bfb1c5ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-02T15:48:14Z","title_canon_sha256":"11aa661c4e00a25af435dfbf79cbf609c7eb3068d3616fb0872f8cc672192052"},"schema_version":"1.0","source":{"id":"1801.00690","kind":"arxiv","version":1}},"canonical_sha256":"45254f86fadfae683bd2d5c1b1bc1cf74a89529d144fca0c213d25f8fa922efd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45254f86fadfae683bd2d5c1b1bc1cf74a89529d144fca0c213d25f8fa922efd","first_computed_at":"2026-07-04T22:27:08.425426Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T22:27:08.425426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yce4Z/bvxGblX88pHPcXSvbuL2Dz9FDU8FgBCTok5n6OGvJEf4KYkDEOALk1oBbAvUs8t6UYDtfh+LF4paCJBA==","signature_status":"signed_v1","signed_at":"2026-07-04T22:27:08.426053Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.00690","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c94adfe49a031aff959a7362f01a81b2749333bef53127fe88a26e66080ab939","sha256:d052fc361b851c0f4f62b3ff1db1062bc6377e30d2de39cd84c97486a3e885f7"],"state_sha256":"055f9bd09b0e97b7c6e2a2b9a94c3c1e1b9b25eeb6f88f8bd42861249970cd55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W1Z0iZMK2O/zeB7ivZUxV/1XReL0AcfJk7jKc5JfMLDxqVylItLtwsV71SfKEBazqsh0Lu9jFEqpMmQOfvj2AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T08:41:33.522176Z","bundle_sha256":"8182e480d41b216345fa217cf7f11c6d27e7240afb1d7ba06520b37711bdbbb7"}}