{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NNELILUG4ZHFJZZ42BNWJJQSZ6","short_pith_number":"pith:NNELILUG","schema_version":"1.0","canonical_sha256":"6b48b42e86e64e54e73cd05b64a612cf91b5c6a401867f2e598bb52fc2ba5ee9","source":{"kind":"arxiv","id":"2012.02055","version":1},"attestation_state":"computed","paper":{"title":"Intervention Design for Effective Sim2Real Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Amy Zhang, David Meger, Joelle Pineau, Melissa Mozifian","submitted_at":"2020-12-03T16:38:54Z","abstract_excerpt":"The goal of this work is to address the recent success of domain randomization and data augmentation for the sim2real setting. We explain this success through the lens of causal inference, positioning domain randomization and data augmentation as interventions on the environment which encourage invariance to irrelevant features. Such interventions include visual perturbations that have no effect on reward and dynamics. This encourages the learning algorithm to be robust to these types of variations and learn to attend to the true causal mechanisms for solving the task. This connection leads to"},"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":"2012.02055","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-12-03T16:38:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5e54f4cb75b0f3b17a89cdb20c13d27f8dfd0c32cac40c34f4d99b68d42a5b3f","abstract_canon_sha256":"123bf94af1c9bce983cffad9c7dc4febb60bc999c638477ad30b710b5f6e87c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:52.822648Z","signature_b64":"RvIBMtXuprAmkissMOPQ9AssQSpwyZH/iBnzurAWHGQE05B6CyJiSZQYgvfbW+BZLtz58PQAhBGnE6uFbyV7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b48b42e86e64e54e73cd05b64a612cf91b5c6a401867f2e598bb52fc2ba5ee9","last_reissued_at":"2026-07-05T01:56:52.822293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:52.822293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Intervention Design for Effective Sim2Real Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Amy Zhang, David Meger, Joelle Pineau, Melissa Mozifian","submitted_at":"2020-12-03T16:38:54Z","abstract_excerpt":"The goal of this work is to address the recent success of domain randomization and data augmentation for the sim2real setting. We explain this success through the lens of causal inference, positioning domain randomization and data augmentation as interventions on the environment which encourage invariance to irrelevant features. Such interventions include visual perturbations that have no effect on reward and dynamics. This encourages the learning algorithm to be robust to these types of variations and learn to attend to the true causal mechanisms for solving the task. This connection leads to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02055","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/2012.02055/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":"2012.02055","created_at":"2026-07-05T01:56:52.822365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.02055v1","created_at":"2026-07-05T01:56:52.822365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02055","created_at":"2026-07-05T01:56:52.822365+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNELILUG4ZHF","created_at":"2026-07-05T01:56:52.822365+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNELILUG4ZHFJZZ4","created_at":"2026-07-05T01:56:52.822365+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNELILUG","created_at":"2026-07-05T01:56:52.822365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.15042","citing_title":"Enhancing Autonomous Driving Safety through World Model-Based Predictive Navigation and Adaptive Learning Algorithms for 5G Wireless Applications","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NNELILUG4ZHFJZZ42BNWJJQSZ6","json":"https://pith.science/pith/NNELILUG4ZHFJZZ42BNWJJQSZ6.json","graph_json":"https://pith.science/api/pith-number/NNELILUG4ZHFJZZ42BNWJJQSZ6/graph.json","events_json":"https://pith.science/api/pith-number/NNELILUG4ZHFJZZ42BNWJJQSZ6/events.json","paper":"https://pith.science/paper/NNELILUG"},"agent_actions":{"view_html":"https://pith.science/pith/NNELILUG4ZHFJZZ42BNWJJQSZ6","download_json":"https://pith.science/pith/NNELILUG4ZHFJZZ42BNWJJQSZ6.json","view_paper":"https://pith.science/paper/NNELILUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.02055&json=true","fetch_graph":"https://pith.science/api/pith-number/NNELILUG4ZHFJZZ42BNWJJQSZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/NNELILUG4ZHFJZZ42BNWJJQSZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNELILUG4ZHFJZZ42BNWJJQSZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNELILUG4ZHFJZZ42BNWJJQSZ6/action/storage_attestation","attest_author":"https://pith.science/pith/NNELILUG4ZHFJZZ42BNWJJQSZ6/action/author_attestation","sign_citation":"https://pith.science/pith/NNELILUG4ZHFJZZ42BNWJJQSZ6/action/citation_signature","submit_replication":"https://pith.science/pith/NNELILUG4ZHFJZZ42BNWJJQSZ6/action/replication_record"}},"created_at":"2026-07-05T01:56:52.822365+00:00","updated_at":"2026-07-05T01:56:52.822365+00:00"}