{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PQRT2OS3QQITGRR7A4EZWAZYLJ","short_pith_number":"pith:PQRT2OS3","schema_version":"1.0","canonical_sha256":"7c233d3a5b841133463f07099b03385a4dd00467d8eae3351d467908fe1bd27a","source":{"kind":"arxiv","id":"2109.02323","version":1},"attestation_state":"computed","paper":{"title":"Safe Reinforcement Learning using Formal Verification for Tissue Retraction in Autonomous Robotic-Assisted Surgery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alessandro Farinelli, Alicia Casals, Ameya Pore, Davide Corsi, Diego Dall'Alba, Enrico Marchesini, Paolo Fiorini","submitted_at":"2021-09-06T09:49:00Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) is a viable solution for automating repetitive surgical subtasks due to its ability to learn complex behaviours in a dynamic environment. This task automation could lead to reduced surgeon's cognitive workload, increased precision in critical aspects of the surgery, and fewer patient-related complications. However, current DRL methods do not guarantee any safety criteria as they maximise cumulative rewards without considering the risks associated with the actions performed. Due to this limitation, the application of DRL in the safety-critical paradigm of robot"},"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":"2109.02323","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-09-06T09:49:00Z","cross_cats_sorted":[],"title_canon_sha256":"2f4d4804ad2f62ae701029495c11c21a68c5a8d012455ad1dc52e0c41f2793f7","abstract_canon_sha256":"7c8f0be26becd6b682305fc93bfbda5b8e7f2a21cd29d7eaec56b6ed315d1242"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:41.193018Z","signature_b64":"8XeGWs3vK7xrRDBRFA3Lt7S+jhMKueLIU81aWRDz1y2+W/elHZBks7J8Zu8H5adlRhvhFOBJNXWMh0PxswiRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c233d3a5b841133463f07099b03385a4dd00467d8eae3351d467908fe1bd27a","last_reissued_at":"2026-07-05T03:11:41.192533Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:41.192533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Reinforcement Learning using Formal Verification for Tissue Retraction in Autonomous Robotic-Assisted Surgery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alessandro Farinelli, Alicia Casals, Ameya Pore, Davide Corsi, Diego Dall'Alba, Enrico Marchesini, Paolo Fiorini","submitted_at":"2021-09-06T09:49:00Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) is a viable solution for automating repetitive surgical subtasks due to its ability to learn complex behaviours in a dynamic environment. This task automation could lead to reduced surgeon's cognitive workload, increased precision in critical aspects of the surgery, and fewer patient-related complications. However, current DRL methods do not guarantee any safety criteria as they maximise cumulative rewards without considering the risks associated with the actions performed. Due to this limitation, the application of DRL in the safety-critical paradigm of robot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02323","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2109.02323/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":"2109.02323","created_at":"2026-07-05T03:11:41.192592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.02323v1","created_at":"2026-07-05T03:11:41.192592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02323","created_at":"2026-07-05T03:11:41.192592+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQRT2OS3QQIT","created_at":"2026-07-05T03:11:41.192592+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQRT2OS3QQITGRR7","created_at":"2026-07-05T03:11:41.192592+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQRT2OS3","created_at":"2026-07-05T03:11:41.192592+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/PQRT2OS3QQITGRR7A4EZWAZYLJ","json":"https://pith.science/pith/PQRT2OS3QQITGRR7A4EZWAZYLJ.json","graph_json":"https://pith.science/api/pith-number/PQRT2OS3QQITGRR7A4EZWAZYLJ/graph.json","events_json":"https://pith.science/api/pith-number/PQRT2OS3QQITGRR7A4EZWAZYLJ/events.json","paper":"https://pith.science/paper/PQRT2OS3"},"agent_actions":{"view_html":"https://pith.science/pith/PQRT2OS3QQITGRR7A4EZWAZYLJ","download_json":"https://pith.science/pith/PQRT2OS3QQITGRR7A4EZWAZYLJ.json","view_paper":"https://pith.science/paper/PQRT2OS3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.02323&json=true","fetch_graph":"https://pith.science/api/pith-number/PQRT2OS3QQITGRR7A4EZWAZYLJ/graph.json","fetch_events":"https://pith.science/api/pith-number/PQRT2OS3QQITGRR7A4EZWAZYLJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQRT2OS3QQITGRR7A4EZWAZYLJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQRT2OS3QQITGRR7A4EZWAZYLJ/action/storage_attestation","attest_author":"https://pith.science/pith/PQRT2OS3QQITGRR7A4EZWAZYLJ/action/author_attestation","sign_citation":"https://pith.science/pith/PQRT2OS3QQITGRR7A4EZWAZYLJ/action/citation_signature","submit_replication":"https://pith.science/pith/PQRT2OS3QQITGRR7A4EZWAZYLJ/action/replication_record"}},"created_at":"2026-07-05T03:11:41.192592+00:00","updated_at":"2026-07-05T03:11:41.192592+00:00"}