{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PT3QB7WYIRO3HIB5VNJ3D4PLC7","short_pith_number":"pith:PT3QB7WY","schema_version":"1.0","canonical_sha256":"7cf700fed8445db3a03dab53b1f1eb17d404e7dbe7d6a8f88c2d3a6bc15ea0bb","source":{"kind":"arxiv","id":"2506.04147","version":4},"attestation_state":"computed","paper":{"title":"SLAC: Simulation-Pretrained Latent Action Space for Whole-Body Real-World RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jiaheng Hu, Peter Stone, Roberto Mart\\'in-Mart\\'in","submitted_at":"2025-06-04T16:41:55Z","abstract_excerpt":"Building capable household and industrial robots requires mastering the control of versatile, high-degree-of-freedom (DoF) systems such as mobile manipulators. While reinforcement learning (RL) holds promise for autonomously acquiring robot control policies, scaling it to high-DoF embodiments remains challenging. Direct RL in the real world demands both safe exploration and high sample efficiency, which are difficult to achieve in practice. Sim-to-real RL, on the other hand, is often brittle due to the reality gap. This paper introduces SLAC, a method that renders real-world RL feasible for co"},"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":"2506.04147","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-04T16:41:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bf1041b9748d3be9e897356d34411438252386956820ed059f12ef090274dc01","abstract_canon_sha256":"9c1791c7d4f85ee0508ae2bc3dd31ed5cd079e651e8815c261bde6354ddc85f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:47.897136Z","signature_b64":"VDiGG4/EBpfq4+rnL+TRKHsrU1aWqXAdz0F3IFHyBOoo/xeEMF4TdFhUNtEvjHXq41qsxno1dcik2nanhqOMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cf700fed8445db3a03dab53b1f1eb17d404e7dbe7d6a8f88c2d3a6bc15ea0bb","last_reissued_at":"2026-07-05T11:54:47.896647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:47.896647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SLAC: Simulation-Pretrained Latent Action Space for Whole-Body Real-World RL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Jiaheng Hu, Peter Stone, Roberto Mart\\'in-Mart\\'in","submitted_at":"2025-06-04T16:41:55Z","abstract_excerpt":"Building capable household and industrial robots requires mastering the control of versatile, high-degree-of-freedom (DoF) systems such as mobile manipulators. While reinforcement learning (RL) holds promise for autonomously acquiring robot control policies, scaling it to high-DoF embodiments remains challenging. Direct RL in the real world demands both safe exploration and high sample efficiency, which are difficult to achieve in practice. Sim-to-real RL, on the other hand, is often brittle due to the reality gap. This paper introduces SLAC, a method that renders real-world RL feasible for co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04147","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/2506.04147/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":"2506.04147","created_at":"2026-07-05T11:54:47.896709+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04147v4","created_at":"2026-07-05T11:54:47.896709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04147","created_at":"2026-07-05T11:54:47.896709+00:00"},{"alias_kind":"pith_short_12","alias_value":"PT3QB7WYIRO3","created_at":"2026-07-05T11:54:47.896709+00:00"},{"alias_kind":"pith_short_16","alias_value":"PT3QB7WYIRO3HIB5","created_at":"2026-07-05T11:54:47.896709+00:00"},{"alias_kind":"pith_short_8","alias_value":"PT3QB7WY","created_at":"2026-07-05T11:54:47.896709+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.26575","citing_title":"IDEA: Insensitive to Dynamics Mismatch via Effect Alignment for Sim-to-Real Transfer in Multi-Agent Control","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10267","citing_title":"What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2512.06571","citing_title":"Learning Agile Striker Skills for Humanoid Soccer Robots from Noisy Sensory Input","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01518","citing_title":"VOFA: Visual Object Goal Pushing with Force-Adaptive Control for Humanoids","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PT3QB7WYIRO3HIB5VNJ3D4PLC7","json":"https://pith.science/pith/PT3QB7WYIRO3HIB5VNJ3D4PLC7.json","graph_json":"https://pith.science/api/pith-number/PT3QB7WYIRO3HIB5VNJ3D4PLC7/graph.json","events_json":"https://pith.science/api/pith-number/PT3QB7WYIRO3HIB5VNJ3D4PLC7/events.json","paper":"https://pith.science/paper/PT3QB7WY"},"agent_actions":{"view_html":"https://pith.science/pith/PT3QB7WYIRO3HIB5VNJ3D4PLC7","download_json":"https://pith.science/pith/PT3QB7WYIRO3HIB5VNJ3D4PLC7.json","view_paper":"https://pith.science/paper/PT3QB7WY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04147&json=true","fetch_graph":"https://pith.science/api/pith-number/PT3QB7WYIRO3HIB5VNJ3D4PLC7/graph.json","fetch_events":"https://pith.science/api/pith-number/PT3QB7WYIRO3HIB5VNJ3D4PLC7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PT3QB7WYIRO3HIB5VNJ3D4PLC7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PT3QB7WYIRO3HIB5VNJ3D4PLC7/action/storage_attestation","attest_author":"https://pith.science/pith/PT3QB7WYIRO3HIB5VNJ3D4PLC7/action/author_attestation","sign_citation":"https://pith.science/pith/PT3QB7WYIRO3HIB5VNJ3D4PLC7/action/citation_signature","submit_replication":"https://pith.science/pith/PT3QB7WYIRO3HIB5VNJ3D4PLC7/action/replication_record"}},"created_at":"2026-07-05T11:54:47.896709+00:00","updated_at":"2026-07-05T11:54:47.896709+00:00"}