{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OQKFQIVKLKJCF5YY7SMO3ACOMY","short_pith_number":"pith:OQKFQIVK","schema_version":"1.0","canonical_sha256":"74145822aa5a9222f718fc98ed804e6629aba14aa6cda1c706a3b5cd1ae20883","source":{"kind":"arxiv","id":"2302.13137","version":3},"attestation_state":"computed","paper":{"title":"A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Alap Kshirsagar, Alois Knoll, Guang Chen, Jan Peters, Shangding Gu, Yali Du","submitted_at":"2023-02-25T18:29:32Z","abstract_excerpt":"Deployment of Reinforcement Learning (RL) algorithms for robotics applications in the real world requires ensuring the safety of the robot and its environment. Safe Robot RL (SRRL) is a crucial step towards achieving human-robot coexistence. In this paper, we envision a human-centered SRRL framework consisting of three stages: safe exploration, safety value alignment, and safe collaboration. We examine the research gaps in these areas and propose to leverage interactive behaviors for SRRL. Interactive behaviors enable bi-directional information transfer between humans and robots, such as conve"},"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":"2302.13137","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-02-25T18:29:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"56c9fbb3d0518e0adc575474afcea3b886706d4ccc8ac30395dbed8244892edb","abstract_canon_sha256":"0e71948bbd94027a55b57ce2f1babc79e3c8088e07cb8a402a487e6fd0fc6a85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:24.414515Z","signature_b64":"0kPeMbTPsLBsBJ5rv5WDFw2nIzADuuFCeJsOrVMkvSlQCgNxLptRJlNmgN5A6tPpArdM0jHtzBHFIQIf2lCYCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74145822aa5a9222f718fc98ed804e6629aba14aa6cda1c706a3b5cd1ae20883","last_reissued_at":"2026-07-05T07:01:24.414065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:24.414065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Alap Kshirsagar, Alois Knoll, Guang Chen, Jan Peters, Shangding Gu, Yali Du","submitted_at":"2023-02-25T18:29:32Z","abstract_excerpt":"Deployment of Reinforcement Learning (RL) algorithms for robotics applications in the real world requires ensuring the safety of the robot and its environment. Safe Robot RL (SRRL) is a crucial step towards achieving human-robot coexistence. In this paper, we envision a human-centered SRRL framework consisting of three stages: safe exploration, safety value alignment, and safe collaboration. We examine the research gaps in these areas and propose to leverage interactive behaviors for SRRL. Interactive behaviors enable bi-directional information transfer between humans and robots, such as conve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13137","kind":"arxiv","version":3},"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/2302.13137/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":"2302.13137","created_at":"2026-07-05T07:01:24.414130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.13137v3","created_at":"2026-07-05T07:01:24.414130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13137","created_at":"2026-07-05T07:01:24.414130+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQKFQIVKLKJC","created_at":"2026-07-05T07:01:24.414130+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQKFQIVKLKJCF5YY","created_at":"2026-07-05T07:01:24.414130+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQKFQIVK","created_at":"2026-07-05T07:01:24.414130+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/OQKFQIVKLKJCF5YY7SMO3ACOMY","json":"https://pith.science/pith/OQKFQIVKLKJCF5YY7SMO3ACOMY.json","graph_json":"https://pith.science/api/pith-number/OQKFQIVKLKJCF5YY7SMO3ACOMY/graph.json","events_json":"https://pith.science/api/pith-number/OQKFQIVKLKJCF5YY7SMO3ACOMY/events.json","paper":"https://pith.science/paper/OQKFQIVK"},"agent_actions":{"view_html":"https://pith.science/pith/OQKFQIVKLKJCF5YY7SMO3ACOMY","download_json":"https://pith.science/pith/OQKFQIVKLKJCF5YY7SMO3ACOMY.json","view_paper":"https://pith.science/paper/OQKFQIVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.13137&json=true","fetch_graph":"https://pith.science/api/pith-number/OQKFQIVKLKJCF5YY7SMO3ACOMY/graph.json","fetch_events":"https://pith.science/api/pith-number/OQKFQIVKLKJCF5YY7SMO3ACOMY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQKFQIVKLKJCF5YY7SMO3ACOMY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQKFQIVKLKJCF5YY7SMO3ACOMY/action/storage_attestation","attest_author":"https://pith.science/pith/OQKFQIVKLKJCF5YY7SMO3ACOMY/action/author_attestation","sign_citation":"https://pith.science/pith/OQKFQIVKLKJCF5YY7SMO3ACOMY/action/citation_signature","submit_replication":"https://pith.science/pith/OQKFQIVKLKJCF5YY7SMO3ACOMY/action/replication_record"}},"created_at":"2026-07-05T07:01:24.414130+00:00","updated_at":"2026-07-05T07:01:24.414130+00:00"}