{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S4PUWTM7PI2WBNAGPM3Z6BC7HA","short_pith_number":"pith:S4PUWTM7","schema_version":"1.0","canonical_sha256":"971f4b4d9f7a3560b4067b379f045f3819131467e5bd3c3669b3e6189fa20482","source":{"kind":"arxiv","id":"2401.16013","version":4},"attestation_state":"computed","paper":{"title":"SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Abhishek Gupta, Archit Sharma, Charles Xu, Chelsea Finn, Jacob Berg, Jianlan Luo, Sergey Levine, Stefan Schaal, You Liang Tan, Zheyuan Hu","submitted_at":"2024-01-29T10:01:10Z","abstract_excerpt":"In recent years, significant progress has been made in the field of robotic reinforcement learning (RL), enabling methods that handle complex image observations, train in the real world, and incorporate auxiliary data, such as demonstrations and prior experience. However, despite these advances, robotic RL remains hard to use. It is acknowledged among practitioners that the particular implementation details of these algorithms are often just as important (if not more so) for performance as the choice of algorithm. We posit that a significant challenge to widespread adoption of robotic RL, as w"},"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":"2401.16013","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-01-29T10:01:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d877660ed01eea48eb1840fa1388f4a7c8bf144b076cceae65fe0a911b749faf","abstract_canon_sha256":"233a884f4629a36c972fea4df41f95d729ec79981d2067a6033680b109c2757c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:31.289609Z","signature_b64":"OwHAJMGQ98ysavBUV+A/0pBSxTY4RBDbUKE25IQD005J1QNco5Dn+Kt/ugEgeLtwX5FmS2Ep/jijQ3cbGu8aAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"971f4b4d9f7a3560b4067b379f045f3819131467e5bd3c3669b3e6189fa20482","last_reissued_at":"2026-07-05T10:35:31.288944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:31.288944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Abhishek Gupta, Archit Sharma, Charles Xu, Chelsea Finn, Jacob Berg, Jianlan Luo, Sergey Levine, Stefan Schaal, You Liang Tan, Zheyuan Hu","submitted_at":"2024-01-29T10:01:10Z","abstract_excerpt":"In recent years, significant progress has been made in the field of robotic reinforcement learning (RL), enabling methods that handle complex image observations, train in the real world, and incorporate auxiliary data, such as demonstrations and prior experience. However, despite these advances, robotic RL remains hard to use. It is acknowledged among practitioners that the particular implementation details of these algorithms are often just as important (if not more so) for performance as the choice of algorithm. We posit that a significant challenge to widespread adoption of robotic RL, as w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16013","kind":"arxiv","version":4},"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/2401.16013/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":"2401.16013","created_at":"2026-07-05T10:35:31.289027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.16013v4","created_at":"2026-07-05T10:35:31.289027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16013","created_at":"2026-07-05T10:35:31.289027+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4PUWTM7PI2W","created_at":"2026-07-05T10:35:31.289027+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4PUWTM7PI2WBNAG","created_at":"2026-07-05T10:35:31.289027+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4PUWTM7","created_at":"2026-07-05T10:35:31.289027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13675","citing_title":"Improving Robotic Generalist Policies via Flow Reversal Steering","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25477","citing_title":"EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2409.00588","citing_title":"Diffusion Policy Policy Optimization","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S4PUWTM7PI2WBNAGPM3Z6BC7HA","json":"https://pith.science/pith/S4PUWTM7PI2WBNAGPM3Z6BC7HA.json","graph_json":"https://pith.science/api/pith-number/S4PUWTM7PI2WBNAGPM3Z6BC7HA/graph.json","events_json":"https://pith.science/api/pith-number/S4PUWTM7PI2WBNAGPM3Z6BC7HA/events.json","paper":"https://pith.science/paper/S4PUWTM7"},"agent_actions":{"view_html":"https://pith.science/pith/S4PUWTM7PI2WBNAGPM3Z6BC7HA","download_json":"https://pith.science/pith/S4PUWTM7PI2WBNAGPM3Z6BC7HA.json","view_paper":"https://pith.science/paper/S4PUWTM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.16013&json=true","fetch_graph":"https://pith.science/api/pith-number/S4PUWTM7PI2WBNAGPM3Z6BC7HA/graph.json","fetch_events":"https://pith.science/api/pith-number/S4PUWTM7PI2WBNAGPM3Z6BC7HA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4PUWTM7PI2WBNAGPM3Z6BC7HA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4PUWTM7PI2WBNAGPM3Z6BC7HA/action/storage_attestation","attest_author":"https://pith.science/pith/S4PUWTM7PI2WBNAGPM3Z6BC7HA/action/author_attestation","sign_citation":"https://pith.science/pith/S4PUWTM7PI2WBNAGPM3Z6BC7HA/action/citation_signature","submit_replication":"https://pith.science/pith/S4PUWTM7PI2WBNAGPM3Z6BC7HA/action/replication_record"}},"created_at":"2026-07-05T10:35:31.289027+00:00","updated_at":"2026-07-05T10:35:31.289027+00:00"}