{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y7HVSMBNRYGPL7ADIRKTNLWM6F","short_pith_number":"pith:Y7HVSMBN","schema_version":"1.0","canonical_sha256":"c7cf59302d8e0cf5fc03445536aeccf144ad332dc731fd5a563fd378c6487775","source":{"kind":"arxiv","id":"2402.08191","version":2},"attestation_state":"computed","paper":{"title":"THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Dieter Fox, Ishika Singh, Jesse Thomason, Jiafei Duan, Ranjay Krishna, Wilbert Pumacay","submitted_at":"2024-02-13T03:25:33Z","abstract_excerpt":"To realize effective large-scale, real-world robotic applications, we must evaluate how well our robot policies adapt to changes in environmental conditions. Unfortunately, a majority of studies evaluate robot performance in environments closely resembling or even identical to the training setup. We present THE COLOSSEUM, a novel simulation benchmark, with 20 diverse manipulation tasks, that enables systematical evaluation of models across 14 axes of environmental perturbations. These perturbations include changes in color, texture, and size of objects, table-tops, and backgrounds; we also var"},"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":"2402.08191","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-02-13T03:25:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"857a6d1805c50db1102f53056d7e5a3770957e9e3d5e9e648aa20d895276427a","abstract_canon_sha256":"3b77fc790d8c0e73ad287ce238237e2ee790e997b40f5dee3ed2fa99e9873a63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:01.453404Z","signature_b64":"KLCkmI6An4PjlbMLsHu/PWeQ8E83ni9UATQ3tMNHJgyH/rD+TjakheUj9PhD2xT9HJCsAvF+cTEB4WiBCl1xBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7cf59302d8e0cf5fc03445536aeccf144ad332dc731fd5a563fd378c6487775","last_reissued_at":"2026-07-05T08:24:01.452864Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:01.452864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"THE COLOSSEUM: A Benchmark for Evaluating Generalization for Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Dieter Fox, Ishika Singh, Jesse Thomason, Jiafei Duan, Ranjay Krishna, Wilbert Pumacay","submitted_at":"2024-02-13T03:25:33Z","abstract_excerpt":"To realize effective large-scale, real-world robotic applications, we must evaluate how well our robot policies adapt to changes in environmental conditions. Unfortunately, a majority of studies evaluate robot performance in environments closely resembling or even identical to the training setup. We present THE COLOSSEUM, a novel simulation benchmark, with 20 diverse manipulation tasks, that enables systematical evaluation of models across 14 axes of environmental perturbations. These perturbations include changes in color, texture, and size of objects, table-tops, and backgrounds; we also var"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08191","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/2402.08191/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":"2402.08191","created_at":"2026-07-05T08:24:01.452944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.08191v2","created_at":"2026-07-05T08:24:01.452944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08191","created_at":"2026-07-05T08:24:01.452944+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7HVSMBNRYGP","created_at":"2026-07-05T08:24:01.452944+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7HVSMBNRYGPL7AD","created_at":"2026-07-05T08:24:01.452944+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7HVSMBN","created_at":"2026-07-05T08:24:01.452944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21572","citing_title":"Robot Critics that Sweat the Small Stuff","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09813","citing_title":"iMaC: Translating Actions into Motion and Contact Images for Embodied World Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02307","citing_title":"FATE-VLA:Failue-aware test generation for vision-language-action models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29898","citing_title":"Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27367","citing_title":"SpatialBench: Is Your Spatial Foundation Model an All-Round Player?","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30326","citing_title":"RoboWits: Unexpected Challenges for Robotic Creative Problem Solving","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2412.02818","citing_title":"RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00435","citing_title":"RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2603.15620","citing_title":"Towards Generalizable Robotic Manipulation in Dynamic Environments","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04974","citing_title":"From Video to Control: A Survey of Learning Manipulation Interfaces from Temporal Visual Data","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":233,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11114","citing_title":"SEVO: Semantic-Enhanced Virtual Observation for Robust VLA Manipulation via Active Illumination and Data-Centric Collection","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24661","citing_title":"Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06481","citing_title":"OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23001","citing_title":"Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24661","citing_title":"Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05226","citing_title":"RoboPlayground: Democratizing Robotic Evaluation through Structured Physical Domains","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06168","citing_title":"Action Images: End-to-End Policy Learning via Multiview Video Generation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04811","citing_title":"AnyUser: Translating Sketched User Intent into Domestic Robots","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y7HVSMBNRYGPL7ADIRKTNLWM6F","json":"https://pith.science/pith/Y7HVSMBNRYGPL7ADIRKTNLWM6F.json","graph_json":"https://pith.science/api/pith-number/Y7HVSMBNRYGPL7ADIRKTNLWM6F/graph.json","events_json":"https://pith.science/api/pith-number/Y7HVSMBNRYGPL7ADIRKTNLWM6F/events.json","paper":"https://pith.science/paper/Y7HVSMBN"},"agent_actions":{"view_html":"https://pith.science/pith/Y7HVSMBNRYGPL7ADIRKTNLWM6F","download_json":"https://pith.science/pith/Y7HVSMBNRYGPL7ADIRKTNLWM6F.json","view_paper":"https://pith.science/paper/Y7HVSMBN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.08191&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7HVSMBNRYGPL7ADIRKTNLWM6F/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7HVSMBNRYGPL7ADIRKTNLWM6F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7HVSMBNRYGPL7ADIRKTNLWM6F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7HVSMBNRYGPL7ADIRKTNLWM6F/action/storage_attestation","attest_author":"https://pith.science/pith/Y7HVSMBNRYGPL7ADIRKTNLWM6F/action/author_attestation","sign_citation":"https://pith.science/pith/Y7HVSMBNRYGPL7ADIRKTNLWM6F/action/citation_signature","submit_replication":"https://pith.science/pith/Y7HVSMBNRYGPL7ADIRKTNLWM6F/action/replication_record"}},"created_at":"2026-07-05T08:24:01.452944+00:00","updated_at":"2026-07-05T08:24:01.452944+00:00"}