{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RX6MALDHSU2YUYIFGIXBCUYFPC","short_pith_number":"pith:RX6MALDH","schema_version":"1.0","canonical_sha256":"8dfcc02c6795358a6105322e115305789f0744f9a32f956fa84f3dc7bed087b8","source":{"kind":"arxiv","id":"2508.12252","version":2},"attestation_state":"computed","paper":{"title":"Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for Humanoids","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"C. Karen Liu, Haochen Shi, Kaizhe Hu, Shuran Song, Weizhuo Wang, Yao He","submitted_at":"2025-08-17T06:17:06Z","abstract_excerpt":"Simulation-based reinforcement learning (RL) has significantly advanced humanoid locomotion tasks, yet direct real-world RL from scratch or adapting from pretrained policies remains rare, limiting the full potential of humanoid robots. Real-world learning, despite being crucial for overcoming the sim-to-real gap, faces substantial challenges related to safety, reward design, and learning efficiency. To address these limitations, we propose Robot-Trains-Robot (RTR), a novel framework where a robotic arm teacher actively supports and guides a humanoid robot student. The RTR system provides prote"},"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":"2508.12252","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-17T06:17:06Z","cross_cats_sorted":[],"title_canon_sha256":"59dcad8507109e7a7eb714ab1be23d38f1b6a19d2013a37c7cc287fba8b916d5","abstract_canon_sha256":"e0d8cfc3b5c44e73434d4e930fed4516721ce0a7430ccdea6d5c739d692f7f38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:19.951009Z","signature_b64":"L2GWxo8RDUBuUgyZgDQOF7SL9kqiSlgCN5TzAfu4W9Dks/couO+WdAdvhBD2kQSP43M/k7ZK8YJaiIU0Yu5gBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dfcc02c6795358a6105322e115305789f0744f9a32f956fa84f3dc7bed087b8","last_reissued_at":"2026-07-05T11:59:19.950579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:19.950579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for Humanoids","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"C. Karen Liu, Haochen Shi, Kaizhe Hu, Shuran Song, Weizhuo Wang, Yao He","submitted_at":"2025-08-17T06:17:06Z","abstract_excerpt":"Simulation-based reinforcement learning (RL) has significantly advanced humanoid locomotion tasks, yet direct real-world RL from scratch or adapting from pretrained policies remains rare, limiting the full potential of humanoid robots. Real-world learning, despite being crucial for overcoming the sim-to-real gap, faces substantial challenges related to safety, reward design, and learning efficiency. To address these limitations, we propose Robot-Trains-Robot (RTR), a novel framework where a robotic arm teacher actively supports and guides a humanoid robot student. The RTR system provides prote"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12252","kind":"arxiv","version":2},"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/2508.12252/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":"2508.12252","created_at":"2026-07-05T11:59:19.950637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12252v2","created_at":"2026-07-05T11:59:19.950637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12252","created_at":"2026-07-05T11:59:19.950637+00:00"},{"alias_kind":"pith_short_12","alias_value":"RX6MALDHSU2Y","created_at":"2026-07-05T11:59:19.950637+00:00"},{"alias_kind":"pith_short_16","alias_value":"RX6MALDHSU2YUYIF","created_at":"2026-07-05T11:59:19.950637+00:00"},{"alias_kind":"pith_short_8","alias_value":"RX6MALDH","created_at":"2026-07-05T11:59:19.950637+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01651","citing_title":"One Demonstration Is Enough for Real-World Robotic Reinforcement Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02280","citing_title":"Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy Adaptation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28476","citing_title":"FADA: Few-Shot Domain Adaptation via Dynamics Alignment for Humanoid Control","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RX6MALDHSU2YUYIFGIXBCUYFPC","json":"https://pith.science/pith/RX6MALDHSU2YUYIFGIXBCUYFPC.json","graph_json":"https://pith.science/api/pith-number/RX6MALDHSU2YUYIFGIXBCUYFPC/graph.json","events_json":"https://pith.science/api/pith-number/RX6MALDHSU2YUYIFGIXBCUYFPC/events.json","paper":"https://pith.science/paper/RX6MALDH"},"agent_actions":{"view_html":"https://pith.science/pith/RX6MALDHSU2YUYIFGIXBCUYFPC","download_json":"https://pith.science/pith/RX6MALDHSU2YUYIFGIXBCUYFPC.json","view_paper":"https://pith.science/paper/RX6MALDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12252&json=true","fetch_graph":"https://pith.science/api/pith-number/RX6MALDHSU2YUYIFGIXBCUYFPC/graph.json","fetch_events":"https://pith.science/api/pith-number/RX6MALDHSU2YUYIFGIXBCUYFPC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RX6MALDHSU2YUYIFGIXBCUYFPC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RX6MALDHSU2YUYIFGIXBCUYFPC/action/storage_attestation","attest_author":"https://pith.science/pith/RX6MALDHSU2YUYIFGIXBCUYFPC/action/author_attestation","sign_citation":"https://pith.science/pith/RX6MALDHSU2YUYIFGIXBCUYFPC/action/citation_signature","submit_replication":"https://pith.science/pith/RX6MALDHSU2YUYIFGIXBCUYFPC/action/replication_record"}},"created_at":"2026-07-05T11:59:19.950637+00:00","updated_at":"2026-07-05T11:59:19.950637+00:00"}