{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WUZOWDXP6AC2PTHKP2YTZRGKP2","short_pith_number":"pith:WUZOWDXP","schema_version":"1.0","canonical_sha256":"b532eb0eeff005a7ccea7eb13cc4ca7e909f9bb2bad92ec898717308cf8db464","source":{"kind":"arxiv","id":"2307.15690","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Offline Reinforcement Learning on Real-Robot Hardware","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Bernhard Sch\\\"olkopf, Felix Widmaier, Georg Martius, Manuel W\\\"uthrich, Nico G\\\"urtler, Pavel Kolev, Sebastian Blaes, Stefan Bauer","submitted_at":"2023-07-28T17:29:49Z","abstract_excerpt":"Learning policies from previously recorded data is a promising direction for real-world robotics tasks, as online learning is often infeasible. Dexterous manipulation in particular remains an open problem in its general form. The combination of offline reinforcement learning with large diverse datasets, however, has the potential to lead to a breakthrough in this challenging domain analogously to the rapid progress made in supervised learning in recent years. To coordinate the efforts of the research community toward tackling this problem, we propose a benchmark including: i) a large collectio"},"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":"2307.15690","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-28T17:29:49Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"ce3883b7d3ec2d0d7587398b6d3330343deecf50bd5de954d003c77e938e7b20","abstract_canon_sha256":"8fd1d7d54d6bb8c707e857d6341896f3c013252dd60ab2ea77acbc124429047a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:38.402822Z","signature_b64":"tQ6d64/fWXIxP187ijSBOd83QQ27aM0+l3L/QT9/BhLetsSUzhvvTBQVym0fKSFp6gz2HwrOtKpAjNUDwWrnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b532eb0eeff005a7ccea7eb13cc4ca7e909f9bb2bad92ec898717308cf8db464","last_reissued_at":"2026-07-05T06:35:38.402331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:38.402331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Offline Reinforcement Learning on Real-Robot Hardware","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Bernhard Sch\\\"olkopf, Felix Widmaier, Georg Martius, Manuel W\\\"uthrich, Nico G\\\"urtler, Pavel Kolev, Sebastian Blaes, Stefan Bauer","submitted_at":"2023-07-28T17:29:49Z","abstract_excerpt":"Learning policies from previously recorded data is a promising direction for real-world robotics tasks, as online learning is often infeasible. Dexterous manipulation in particular remains an open problem in its general form. The combination of offline reinforcement learning with large diverse datasets, however, has the potential to lead to a breakthrough in this challenging domain analogously to the rapid progress made in supervised learning in recent years. To coordinate the efforts of the research community toward tackling this problem, we propose a benchmark including: i) a large collectio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15690","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/2307.15690/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":"2307.15690","created_at":"2026-07-05T06:35:38.402395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.15690v1","created_at":"2026-07-05T06:35:38.402395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15690","created_at":"2026-07-05T06:35:38.402395+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUZOWDXP6AC2","created_at":"2026-07-05T06:35:38.402395+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUZOWDXP6AC2PTHK","created_at":"2026-07-05T06:35:38.402395+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUZOWDXP","created_at":"2026-07-05T06:35:38.402395+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.02523","citing_title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WUZOWDXP6AC2PTHKP2YTZRGKP2","json":"https://pith.science/pith/WUZOWDXP6AC2PTHKP2YTZRGKP2.json","graph_json":"https://pith.science/api/pith-number/WUZOWDXP6AC2PTHKP2YTZRGKP2/graph.json","events_json":"https://pith.science/api/pith-number/WUZOWDXP6AC2PTHKP2YTZRGKP2/events.json","paper":"https://pith.science/paper/WUZOWDXP"},"agent_actions":{"view_html":"https://pith.science/pith/WUZOWDXP6AC2PTHKP2YTZRGKP2","download_json":"https://pith.science/pith/WUZOWDXP6AC2PTHKP2YTZRGKP2.json","view_paper":"https://pith.science/paper/WUZOWDXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.15690&json=true","fetch_graph":"https://pith.science/api/pith-number/WUZOWDXP6AC2PTHKP2YTZRGKP2/graph.json","fetch_events":"https://pith.science/api/pith-number/WUZOWDXP6AC2PTHKP2YTZRGKP2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUZOWDXP6AC2PTHKP2YTZRGKP2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUZOWDXP6AC2PTHKP2YTZRGKP2/action/storage_attestation","attest_author":"https://pith.science/pith/WUZOWDXP6AC2PTHKP2YTZRGKP2/action/author_attestation","sign_citation":"https://pith.science/pith/WUZOWDXP6AC2PTHKP2YTZRGKP2/action/citation_signature","submit_replication":"https://pith.science/pith/WUZOWDXP6AC2PTHKP2YTZRGKP2/action/replication_record"}},"created_at":"2026-07-05T06:35:38.402395+00:00","updated_at":"2026-07-05T06:35:38.402395+00:00"}