{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:A3UE3MO7745RE7GJ76EXLDTLI7","short_pith_number":"pith:A3UE3MO7","canonical_record":{"source":{"id":"2310.08841","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-13T03:39:15Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"0bee0a9d1d923f3989fab4b59e6f84eccf993e3574d77e6c035a7b970208726b","abstract_canon_sha256":"682726d36a52efff340d157ca055a6588488082d759456631d33754ee300009e"},"schema_version":"1.0"},"canonical_sha256":"06e84db1dfff3b127cc9ff89758e6b47de69be2608b084435c8c0d8770d29a7a","source":{"kind":"arxiv","id":"2310.08841","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08841","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08841v1","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08841","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_12","alias_value":"A3UE3MO7745R","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_16","alias_value":"A3UE3MO7745RE7GJ","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_8","alias_value":"A3UE3MO7","created_at":"2026-07-05T07:00:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:A3UE3MO7745RE7GJ76EXLDTLI7","target":"record","payload":{"canonical_record":{"source":{"id":"2310.08841","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-13T03:39:15Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"0bee0a9d1d923f3989fab4b59e6f84eccf993e3574d77e6c035a7b970208726b","abstract_canon_sha256":"682726d36a52efff340d157ca055a6588488082d759456631d33754ee300009e"},"schema_version":"1.0"},"canonical_sha256":"06e84db1dfff3b127cc9ff89758e6b47de69be2608b084435c8c0d8770d29a7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:35.688776Z","signature_b64":"OOJHrX6P4fIfmJ34gboIsSl//pDXuU1seeWxnb3KpL6qP7+HefB3uJvD4R8REMbTfHm4XfCOe+zyoxB/DkZhAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06e84db1dfff3b127cc9ff89758e6b47de69be2608b084435c8c0d8770d29a7a","last_reissued_at":"2026-07-05T07:00:35.688306Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:35.688306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.08841","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:00:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8tCqlvswWZ1TWy/jr+iLFyBaQMQOIA/F/IBlKtzoNOsgfAyMp52oPKyUTtfXGVqPoVBXxXWldqJySFqLkkJHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:40:18.035652Z"},"content_sha256":"efcc94eeb23903dc875073e43f48da1ceb3cadb2cc4df871f8607045482e6289","schema_version":"1.0","event_id":"sha256:efcc94eeb23903dc875073e43f48da1ceb3cadb2cc4df871f8607045482e6289"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:A3UE3MO7745RE7GJ76EXLDTLI7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Optimal Transport for Enhanced Offline Reinforcement Learning in Surgical Robotic Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.AI","authors_text":"Abbas Khosravi, Maryam Zare, Parham M. Kebria","submitted_at":"2023-10-13T03:39:15Z","abstract_excerpt":"Most Reinforcement Learning (RL) methods are traditionally studied in an active learning setting, where agents directly interact with their environments, observe action outcomes, and learn through trial and error. However, allowing partially trained agents to interact with real physical systems poses significant challenges, including high costs, safety risks, and the need for constant supervision. Offline RL addresses these cost and safety concerns by leveraging existing datasets and reducing the need for resource-intensive real-time interactions. Nevertheless, a substantial challenge lies in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08841","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/2310.08841/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:00:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KJQp0joKbyF8NjcwpK4vbi1PN6nbnQIdlkUMOI4ea/3+Ji3S1PbeHS3fzhZ5KTcwiNtCY1PgcbGE7VglmjgfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:40:18.036192Z"},"content_sha256":"b080f316c32f293bea1d90341ebd02231143f5b7ea05e95588588a5d75c88887","schema_version":"1.0","event_id":"sha256:b080f316c32f293bea1d90341ebd02231143f5b7ea05e95588588a5d75c88887"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A3UE3MO7745RE7GJ76EXLDTLI7/bundle.json","state_url":"https://pith.science/pith/A3UE3MO7745RE7GJ76EXLDTLI7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A3UE3MO7745RE7GJ76EXLDTLI7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T12:40:18Z","links":{"resolver":"https://pith.science/pith/A3UE3MO7745RE7GJ76EXLDTLI7","bundle":"https://pith.science/pith/A3UE3MO7745RE7GJ76EXLDTLI7/bundle.json","state":"https://pith.science/pith/A3UE3MO7745RE7GJ76EXLDTLI7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A3UE3MO7745RE7GJ76EXLDTLI7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:A3UE3MO7745RE7GJ76EXLDTLI7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"682726d36a52efff340d157ca055a6588488082d759456631d33754ee300009e","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-13T03:39:15Z","title_canon_sha256":"0bee0a9d1d923f3989fab4b59e6f84eccf993e3574d77e6c035a7b970208726b"},"schema_version":"1.0","source":{"id":"2310.08841","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08841","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08841v1","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08841","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_12","alias_value":"A3UE3MO7745R","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_16","alias_value":"A3UE3MO7745RE7GJ","created_at":"2026-07-05T07:00:35Z"},{"alias_kind":"pith_short_8","alias_value":"A3UE3MO7","created_at":"2026-07-05T07:00:35Z"}],"graph_snapshots":[{"event_id":"sha256:b080f316c32f293bea1d90341ebd02231143f5b7ea05e95588588a5d75c88887","target":"graph","created_at":"2026-07-05T07:00:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2310.08841/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most Reinforcement Learning (RL) methods are traditionally studied in an active learning setting, where agents directly interact with their environments, observe action outcomes, and learn through trial and error. However, allowing partially trained agents to interact with real physical systems poses significant challenges, including high costs, safety risks, and the need for constant supervision. Offline RL addresses these cost and safety concerns by leveraging existing datasets and reducing the need for resource-intensive real-time interactions. Nevertheless, a substantial challenge lies in ","authors_text":"Abbas Khosravi, Maryam Zare, Parham M. Kebria","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-13T03:39:15Z","title":"Leveraging Optimal Transport for Enhanced Offline Reinforcement Learning in Surgical Robotic Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08841","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:efcc94eeb23903dc875073e43f48da1ceb3cadb2cc4df871f8607045482e6289","target":"record","created_at":"2026-07-05T07:00:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"682726d36a52efff340d157ca055a6588488082d759456631d33754ee300009e","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-13T03:39:15Z","title_canon_sha256":"0bee0a9d1d923f3989fab4b59e6f84eccf993e3574d77e6c035a7b970208726b"},"schema_version":"1.0","source":{"id":"2310.08841","kind":"arxiv","version":1}},"canonical_sha256":"06e84db1dfff3b127cc9ff89758e6b47de69be2608b084435c8c0d8770d29a7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06e84db1dfff3b127cc9ff89758e6b47de69be2608b084435c8c0d8770d29a7a","first_computed_at":"2026-07-05T07:00:35.688306Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:00:35.688306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OOJHrX6P4fIfmJ34gboIsSl//pDXuU1seeWxnb3KpL6qP7+HefB3uJvD4R8REMbTfHm4XfCOe+zyoxB/DkZhAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:00:35.688776Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08841","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efcc94eeb23903dc875073e43f48da1ceb3cadb2cc4df871f8607045482e6289","sha256:b080f316c32f293bea1d90341ebd02231143f5b7ea05e95588588a5d75c88887"],"state_sha256":"a9fa9bd5fb719a8ae4690ca4d27e6ec49c287909ca8fa8e3b0a2f0d22e007648"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"80y7hq62i3wjk/nXpzXnqV4dJi35u8MdRuGRLoBeJFR4LCmctELNtob2KRR5Y9w/ii8OV3EdXjsNV/P9+vjnDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T12:40:18.042064Z","bundle_sha256":"4455b177f443e1c8474e3b009e7a0a77fd4200d7fc576587fa8fc089223c1f9d"}}