{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IZBNEGQ4IPV35U2WTYHKKJNGAY","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":"fef706662cccff8334d4f704ac8d906349de6e4e23947bb4c9fb4ca15d391983","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-04-13T20:55:15Z","title_canon_sha256":"404f96b9a201fe4aeaced87be133dcafa181fddda6169194963301393e5477e0"},"schema_version":"1.0","source":{"id":"2404.09080","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.09080","created_at":"2026-07-05T09:31:45Z"},{"alias_kind":"arxiv_version","alias_value":"2404.09080v2","created_at":"2026-07-05T09:31:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.09080","created_at":"2026-07-05T09:31:45Z"},{"alias_kind":"pith_short_12","alias_value":"IZBNEGQ4IPV3","created_at":"2026-07-05T09:31:45Z"},{"alias_kind":"pith_short_16","alias_value":"IZBNEGQ4IPV35U2W","created_at":"2026-07-05T09:31:45Z"},{"alias_kind":"pith_short_8","alias_value":"IZBNEGQ4","created_at":"2026-07-05T09:31:45Z"}],"graph_snapshots":[{"event_id":"sha256:cb04d0d3d1463349ccc2e2455e415f39c32d028b4572abc3a9849b4ec481505e","target":"graph","created_at":"2026-07-05T09:31:45Z","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/2404.09080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Integrating learning-based techniques, especially reinforcement learning, into robotics is promising for solving complex problems in unstructured environments. However, most existing approaches are trained in well-tuned simulators and subsequently deployed on real robots without online fine-tuning. In this setting, extensive engineering is required to mitigate the sim-to-real gap, which can be challenging for complex systems. Instead, learning with real-world interaction data offers a promising alternative: it not only eliminates the need for a fine-tuned simulator but also applies to a broade","authors_text":"Davide Tateo, Haitham Bou-Ammar, Jan Peters, Puze Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-04-13T20:55:15Z","title":"Safe Reinforcement Learning on the Constraint Manifold: Theory and Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.09080","kind":"arxiv","version":2},"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:cf989898fcecc6d8b1206d580a0105d77ec2156ddfe02dd71b4f326b60955e3b","target":"record","created_at":"2026-07-05T09:31:45Z","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":"fef706662cccff8334d4f704ac8d906349de6e4e23947bb4c9fb4ca15d391983","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-04-13T20:55:15Z","title_canon_sha256":"404f96b9a201fe4aeaced87be133dcafa181fddda6169194963301393e5477e0"},"schema_version":"1.0","source":{"id":"2404.09080","kind":"arxiv","version":2}},"canonical_sha256":"4642d21a1c43ebbed3569e0ea525a606137d75e4c9a729064621a079dd8ee362","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4642d21a1c43ebbed3569e0ea525a606137d75e4c9a729064621a079dd8ee362","first_computed_at":"2026-07-05T09:31:45.201119Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:45.201119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bh8/KfBgSjYnTIQMmpOU9tE9f9hvWtGnXs8H4EjFo7jqW16/idy965lOjdypmvS0u6R+G/UM8YYaXtGCzZLAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:45.201610Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.09080","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf989898fcecc6d8b1206d580a0105d77ec2156ddfe02dd71b4f326b60955e3b","sha256:cb04d0d3d1463349ccc2e2455e415f39c32d028b4572abc3a9849b4ec481505e"],"state_sha256":"3dfc0736a25db0989a96a4c7c2f18007eb9505bdeac6ca1bf5899f2b5d885202"}