{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:IBCXW4AEQUUXSWGGCVYDLCH7Q6","short_pith_number":"pith:IBCXW4AE","schema_version":"1.0","canonical_sha256":"40457b700485297958c615703588ff878e4de84073254a8e691e918cd815103d","source":{"kind":"arxiv","id":"1703.10284","version":2},"attestation_state":"computed","paper":{"title":"Enter the Matrix: Safely Interruptible Autonomous Systems via Virtualization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Brent Harrison, Mark O. Riedl","submitted_at":"2017-03-30T01:35:01Z","abstract_excerpt":"Autonomous systems that operate around humans will likely always rely on kill switches that stop their execution and allow them to be remote-controlled for the safety of humans or to prevent damage to the system. It is theoretically possible for an autonomous system with sufficient sensor and effector capability that learn online using reinforcement learning to discover that the kill switch deprives it of long-term reward and thus learn to disable the switch or otherwise prevent a human operator from using the switch. This is referred to as the big red button problem. We present a technique th"},"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":"1703.10284","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-30T01:35:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"94c80171d3a1b52a4d788af4d37e818d93db00c3eeb01bd70fd6dd6c223ac46d","abstract_canon_sha256":"8dc77c4016415da634434047113da202adc75c4801ff17f3185ed15e29ebf532"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:53.886934Z","signature_b64":"DAx7g2g8vzicpyKOU0AkDtC9rOqServcSd2gKHdmmSkR0MRtiyZbjHhwILOHfZux7SGwk0gjfMq6hZbTDdI/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40457b700485297958c615703588ff878e4de84073254a8e691e918cd815103d","last_reissued_at":"2026-05-17T23:59:53.886262Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:53.886262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enter the Matrix: Safely Interruptible Autonomous Systems via Virtualization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Brent Harrison, Mark O. Riedl","submitted_at":"2017-03-30T01:35:01Z","abstract_excerpt":"Autonomous systems that operate around humans will likely always rely on kill switches that stop their execution and allow them to be remote-controlled for the safety of humans or to prevent damage to the system. It is theoretically possible for an autonomous system with sufficient sensor and effector capability that learn online using reinforcement learning to discover that the kill switch deprives it of long-term reward and thus learn to disable the switch or otherwise prevent a human operator from using the switch. This is referred to as the big red button problem. We present a technique th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.10284","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":""},"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":"1703.10284","created_at":"2026-05-17T23:59:53.886385+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.10284v2","created_at":"2026-05-17T23:59:53.886385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.10284","created_at":"2026-05-17T23:59:53.886385+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBCXW4AEQUUX","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBCXW4AEQUUXSWGG","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBCXW4AE","created_at":"2026-05-18T12:31:21.493067+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/IBCXW4AEQUUXSWGGCVYDLCH7Q6","json":"https://pith.science/pith/IBCXW4AEQUUXSWGGCVYDLCH7Q6.json","graph_json":"https://pith.science/api/pith-number/IBCXW4AEQUUXSWGGCVYDLCH7Q6/graph.json","events_json":"https://pith.science/api/pith-number/IBCXW4AEQUUXSWGGCVYDLCH7Q6/events.json","paper":"https://pith.science/paper/IBCXW4AE"},"agent_actions":{"view_html":"https://pith.science/pith/IBCXW4AEQUUXSWGGCVYDLCH7Q6","download_json":"https://pith.science/pith/IBCXW4AEQUUXSWGGCVYDLCH7Q6.json","view_paper":"https://pith.science/paper/IBCXW4AE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.10284&json=true","fetch_graph":"https://pith.science/api/pith-number/IBCXW4AEQUUXSWGGCVYDLCH7Q6/graph.json","fetch_events":"https://pith.science/api/pith-number/IBCXW4AEQUUXSWGGCVYDLCH7Q6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBCXW4AEQUUXSWGGCVYDLCH7Q6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBCXW4AEQUUXSWGGCVYDLCH7Q6/action/storage_attestation","attest_author":"https://pith.science/pith/IBCXW4AEQUUXSWGGCVYDLCH7Q6/action/author_attestation","sign_citation":"https://pith.science/pith/IBCXW4AEQUUXSWGGCVYDLCH7Q6/action/citation_signature","submit_replication":"https://pith.science/pith/IBCXW4AEQUUXSWGGCVYDLCH7Q6/action/replication_record"}},"created_at":"2026-05-17T23:59:53.886385+00:00","updated_at":"2026-05-17T23:59:53.886385+00:00"}