{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LEM6BGZHU53KKB3TOBFMK52SQ5","short_pith_number":"pith:LEM6BGZH","schema_version":"1.0","canonical_sha256":"5919e09b27a776a50773704ac5775287456897c793c3368bef67af0840ee617b","source":{"kind":"arxiv","id":"2511.04249","version":2},"attestation_state":"computed","paper":{"title":"Can Context Bridge the Reality Gap? Sim-to-Real Transfer of Context-Aware Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Erik Schaffernicht, Johannes A. Stork, Marco Iannotta, Todor Stoyanov, Yuxuan Yang","submitted_at":"2025-11-06T10:35:21Z","abstract_excerpt":"Sim-to-real transfer remains a major challenge in reinforcement learning (RL) for robotics, as policies trained in simulation often fail to generalize to the real world due to discrepancies in environment dynamics. Domain Randomization (DR) mitigates this issue by exposing the policy to a wide range of randomized dynamics during training, yet leading to a reduction in performance. While standard approaches typically train policies agnostic to these variations, we investigate whether sim-to-real transfer can be improved by conditioning the policy on an estimate of the dynamics parameters -- ref"},"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":"2511.04249","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-11-06T10:35:21Z","cross_cats_sorted":[],"title_canon_sha256":"663271d68f1abd1b74521d3661e7d34c4fb38d71fad67c4f74191efcb596c3f0","abstract_canon_sha256":"111280b47d52c76524239fb42620779e8aab56d004035cd0c105c47787b80b80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:21:34.045448Z","signature_b64":"4wWyup8Zsn1/35reQmS/caUM1vNAsELi2BR6+ln58h2TqCBdECpCp6egwM56Nt3r32Bc9zWtMiaAlWkJV8XIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5919e09b27a776a50773704ac5775287456897c793c3368bef67af0840ee617b","last_reissued_at":"2026-07-28T01:21:34.044530Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:21:34.044530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Context Bridge the Reality Gap? Sim-to-Real Transfer of Context-Aware Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Erik Schaffernicht, Johannes A. Stork, Marco Iannotta, Todor Stoyanov, Yuxuan Yang","submitted_at":"2025-11-06T10:35:21Z","abstract_excerpt":"Sim-to-real transfer remains a major challenge in reinforcement learning (RL) for robotics, as policies trained in simulation often fail to generalize to the real world due to discrepancies in environment dynamics. Domain Randomization (DR) mitigates this issue by exposing the policy to a wide range of randomized dynamics during training, yet leading to a reduction in performance. While standard approaches typically train policies agnostic to these variations, we investigate whether sim-to-real transfer can be improved by conditioning the policy on an estimate of the dynamics parameters -- ref"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.04249","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/2511.04249/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":"2511.04249","created_at":"2026-07-28T01:21:34.044949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.04249v2","created_at":"2026-07-28T01:21:34.044949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.04249","created_at":"2026-07-28T01:21:34.044949+00:00"},{"alias_kind":"pith_short_12","alias_value":"LEM6BGZHU53K","created_at":"2026-07-28T01:21:34.044949+00:00"},{"alias_kind":"pith_short_16","alias_value":"LEM6BGZHU53KKB3T","created_at":"2026-07-28T01:21:34.044949+00:00"},{"alias_kind":"pith_short_8","alias_value":"LEM6BGZH","created_at":"2026-07-28T01:21:34.044949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.04029","citing_title":"Position: Deployed Reinforcement Learning should be Continual","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02348","citing_title":"Contextual Intelligence The Next Leap for Reinforcement Learning","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LEM6BGZHU53KKB3TOBFMK52SQ5","json":"https://pith.science/pith/LEM6BGZHU53KKB3TOBFMK52SQ5.json","graph_json":"https://pith.science/api/pith-number/LEM6BGZHU53KKB3TOBFMK52SQ5/graph.json","events_json":"https://pith.science/api/pith-number/LEM6BGZHU53KKB3TOBFMK52SQ5/events.json","paper":"https://pith.science/paper/LEM6BGZH"},"agent_actions":{"view_html":"https://pith.science/pith/LEM6BGZHU53KKB3TOBFMK52SQ5","download_json":"https://pith.science/pith/LEM6BGZHU53KKB3TOBFMK52SQ5.json","view_paper":"https://pith.science/paper/LEM6BGZH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.04249&json=true","fetch_graph":"https://pith.science/api/pith-number/LEM6BGZHU53KKB3TOBFMK52SQ5/graph.json","fetch_events":"https://pith.science/api/pith-number/LEM6BGZHU53KKB3TOBFMK52SQ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LEM6BGZHU53KKB3TOBFMK52SQ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LEM6BGZHU53KKB3TOBFMK52SQ5/action/storage_attestation","attest_author":"https://pith.science/pith/LEM6BGZHU53KKB3TOBFMK52SQ5/action/author_attestation","sign_citation":"https://pith.science/pith/LEM6BGZHU53KKB3TOBFMK52SQ5/action/citation_signature","submit_replication":"https://pith.science/pith/LEM6BGZHU53KKB3TOBFMK52SQ5/action/replication_record"}},"created_at":"2026-07-28T01:21:34.044949+00:00","updated_at":"2026-07-28T01:21:34.044949+00:00"}