{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:H6WLOJKNIUJQUZMJRMHVHRF5BE","short_pith_number":"pith:H6WLOJKN","schema_version":"1.0","canonical_sha256":"3facb7254d45130a65898b0f53c4bd0932800e56aac2269115d403daeb357002","source":{"kind":"arxiv","id":"1705.05394","version":1},"attestation_state":"computed","paper":{"title":"Probabilistically Safe Policy Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"David Held, Fred Shentu, Michael Zhang, Pieter Abbeel, Zoe McCarthy","submitted_at":"2017-05-15T18:02:17Z","abstract_excerpt":"Although learning-based methods have great potential for robotics, one concern is that a robot that updates its parameters might cause large amounts of damage before it learns the optimal policy. We formalize the idea of safe learning in a probabilistic sense by defining an optimization problem: we desire to maximize the expected return while keeping the expected damage below a given safety limit. We study this optimization for the case of a robot manipulator with safety-based torque limits. We would like to ensure that the damage constraint is maintained at every step of the optimization and "},"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":"1705.05394","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-05-15T18:02:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8f2c689efc2db98a0f739968fa183b57a6cadedd1553ea043f9551919c9a84e9","abstract_canon_sha256":"4d4a3918459e7cf7cf709e02c83c820fa1842b7ad9c346fbe9fafda55f6716e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:22.822350Z","signature_b64":"dyauR1p+0u2optXCiG3+DOudnToGMoq11sEsOi6GG4HOMn1Uil75uHmlNLkWO98hK8Cg1ayTAnCyTce5m0+rBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3facb7254d45130a65898b0f53c4bd0932800e56aac2269115d403daeb357002","last_reissued_at":"2026-05-18T00:44:22.821796Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:22.821796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistically Safe Policy Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"David Held, Fred Shentu, Michael Zhang, Pieter Abbeel, Zoe McCarthy","submitted_at":"2017-05-15T18:02:17Z","abstract_excerpt":"Although learning-based methods have great potential for robotics, one concern is that a robot that updates its parameters might cause large amounts of damage before it learns the optimal policy. We formalize the idea of safe learning in a probabilistic sense by defining an optimization problem: we desire to maximize the expected return while keeping the expected damage below a given safety limit. We study this optimization for the case of a robot manipulator with safety-based torque limits. We would like to ensure that the damage constraint is maintained at every step of the optimization and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.05394","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":""},"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":"1705.05394","created_at":"2026-05-18T00:44:22.821875+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.05394v1","created_at":"2026-05-18T00:44:22.821875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.05394","created_at":"2026-05-18T00:44:22.821875+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6WLOJKNIUJQ","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6WLOJKNIUJQUZMJ","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6WLOJKN","created_at":"2026-05-18T12:31:18.294218+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/H6WLOJKNIUJQUZMJRMHVHRF5BE","json":"https://pith.science/pith/H6WLOJKNIUJQUZMJRMHVHRF5BE.json","graph_json":"https://pith.science/api/pith-number/H6WLOJKNIUJQUZMJRMHVHRF5BE/graph.json","events_json":"https://pith.science/api/pith-number/H6WLOJKNIUJQUZMJRMHVHRF5BE/events.json","paper":"https://pith.science/paper/H6WLOJKN"},"agent_actions":{"view_html":"https://pith.science/pith/H6WLOJKNIUJQUZMJRMHVHRF5BE","download_json":"https://pith.science/pith/H6WLOJKNIUJQUZMJRMHVHRF5BE.json","view_paper":"https://pith.science/paper/H6WLOJKN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.05394&json=true","fetch_graph":"https://pith.science/api/pith-number/H6WLOJKNIUJQUZMJRMHVHRF5BE/graph.json","fetch_events":"https://pith.science/api/pith-number/H6WLOJKNIUJQUZMJRMHVHRF5BE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6WLOJKNIUJQUZMJRMHVHRF5BE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6WLOJKNIUJQUZMJRMHVHRF5BE/action/storage_attestation","attest_author":"https://pith.science/pith/H6WLOJKNIUJQUZMJRMHVHRF5BE/action/author_attestation","sign_citation":"https://pith.science/pith/H6WLOJKNIUJQUZMJRMHVHRF5BE/action/citation_signature","submit_replication":"https://pith.science/pith/H6WLOJKNIUJQUZMJRMHVHRF5BE/action/replication_record"}},"created_at":"2026-05-18T00:44:22.821875+00:00","updated_at":"2026-05-18T00:44:22.821875+00:00"}