{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LRQOGM7O22WYGQ44RULBWKZJAX","short_pith_number":"pith:LRQOGM7O","schema_version":"1.0","canonical_sha256":"5c60e333eed6ad83439c8d161b2b2905fcba3a037787bf2948fb064b1df43260","source":{"kind":"arxiv","id":"2207.06572","version":4},"attestation_state":"computed","paper":{"title":"i-Sim2Real: Reinforcement Learning of Robotic Policies in Tight Human-Robot Interaction Loops","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alex Bewley, Anish Shankar, Avi Singh, David B. D'Ambrosio, Deepali Jain, Krzysztof Choromanski, Laura Graesser, Pannag R. Sanketi, Saminda Abeyruwan","submitted_at":"2022-07-14T00:26:45Z","abstract_excerpt":"Sim-to-real transfer is a powerful paradigm for robotic reinforcement learning. The ability to train policies in simulation enables safe exploration and large-scale data collection quickly at low cost. However, prior works in sim-to-real transfer of robotic policies typically do not involve any human-robot interaction because accurately simulating human behavior is an open problem. In this work, our goal is to leverage the power of simulation to train robotic policies that are proficient at interacting with humans upon deployment. But there is a chicken and egg problem -- how to gather example"},"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":"2207.06572","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-07-14T00:26:45Z","cross_cats_sorted":[],"title_canon_sha256":"e160139fb9b7e00c7b65f0df9df2ccda7db0c7c720c137114807336ebd297c7c","abstract_canon_sha256":"632c0000a869f815da3fe2bf1ea8e23e555b3ae91757455a88e2cf74e342132d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:05.295454Z","signature_b64":"Y8t0+U/5oxZf6nx7Wc2rs4q7txKUkCCJFWjZfEFqa+0pwPRn7LCFilXuEkjRbnzzj4bEQQJt5gKsPIbf0lO3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c60e333eed6ad83439c8d161b2b2905fcba3a037787bf2948fb064b1df43260","last_reissued_at":"2026-07-05T05:18:05.295090Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:05.295090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"i-Sim2Real: Reinforcement Learning of Robotic Policies in Tight Human-Robot Interaction Loops","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alex Bewley, Anish Shankar, Avi Singh, David B. D'Ambrosio, Deepali Jain, Krzysztof Choromanski, Laura Graesser, Pannag R. Sanketi, Saminda Abeyruwan","submitted_at":"2022-07-14T00:26:45Z","abstract_excerpt":"Sim-to-real transfer is a powerful paradigm for robotic reinforcement learning. The ability to train policies in simulation enables safe exploration and large-scale data collection quickly at low cost. However, prior works in sim-to-real transfer of robotic policies typically do not involve any human-robot interaction because accurately simulating human behavior is an open problem. In this work, our goal is to leverage the power of simulation to train robotic policies that are proficient at interacting with humans upon deployment. But there is a chicken and egg problem -- how to gather example"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.06572","kind":"arxiv","version":4},"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/2207.06572/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":"2207.06572","created_at":"2026-07-05T05:18:05.295146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.06572v4","created_at":"2026-07-05T05:18:05.295146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.06572","created_at":"2026-07-05T05:18:05.295146+00:00"},{"alias_kind":"pith_short_12","alias_value":"LRQOGM7O22WY","created_at":"2026-07-05T05:18:05.295146+00:00"},{"alias_kind":"pith_short_16","alias_value":"LRQOGM7O22WYGQ44","created_at":"2026-07-05T05:18:05.295146+00:00"},{"alias_kind":"pith_short_8","alias_value":"LRQOGM7O","created_at":"2026-07-05T05:18:05.295146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LRQOGM7O22WYGQ44RULBWKZJAX","json":"https://pith.science/pith/LRQOGM7O22WYGQ44RULBWKZJAX.json","graph_json":"https://pith.science/api/pith-number/LRQOGM7O22WYGQ44RULBWKZJAX/graph.json","events_json":"https://pith.science/api/pith-number/LRQOGM7O22WYGQ44RULBWKZJAX/events.json","paper":"https://pith.science/paper/LRQOGM7O"},"agent_actions":{"view_html":"https://pith.science/pith/LRQOGM7O22WYGQ44RULBWKZJAX","download_json":"https://pith.science/pith/LRQOGM7O22WYGQ44RULBWKZJAX.json","view_paper":"https://pith.science/paper/LRQOGM7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.06572&json=true","fetch_graph":"https://pith.science/api/pith-number/LRQOGM7O22WYGQ44RULBWKZJAX/graph.json","fetch_events":"https://pith.science/api/pith-number/LRQOGM7O22WYGQ44RULBWKZJAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LRQOGM7O22WYGQ44RULBWKZJAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LRQOGM7O22WYGQ44RULBWKZJAX/action/storage_attestation","attest_author":"https://pith.science/pith/LRQOGM7O22WYGQ44RULBWKZJAX/action/author_attestation","sign_citation":"https://pith.science/pith/LRQOGM7O22WYGQ44RULBWKZJAX/action/citation_signature","submit_replication":"https://pith.science/pith/LRQOGM7O22WYGQ44RULBWKZJAX/action/replication_record"}},"created_at":"2026-07-05T05:18:05.295146+00:00","updated_at":"2026-07-05T05:18:05.295146+00:00"}