{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RX6MALDHSU2YUYIFGIXBCUYFPC","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":"e0d8cfc3b5c44e73434d4e930fed4516721ce0a7430ccdea6d5c739d692f7f38","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-17T06:17:06Z","title_canon_sha256":"59dcad8507109e7a7eb714ab1be23d38f1b6a19d2013a37c7cc287fba8b916d5"},"schema_version":"1.0","source":{"id":"2508.12252","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12252","created_at":"2026-07-05T11:59:19Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12252v2","created_at":"2026-07-05T11:59:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12252","created_at":"2026-07-05T11:59:19Z"},{"alias_kind":"pith_short_12","alias_value":"RX6MALDHSU2Y","created_at":"2026-07-05T11:59:19Z"},{"alias_kind":"pith_short_16","alias_value":"RX6MALDHSU2YUYIF","created_at":"2026-07-05T11:59:19Z"},{"alias_kind":"pith_short_8","alias_value":"RX6MALDH","created_at":"2026-07-05T11:59:19Z"}],"graph_snapshots":[{"event_id":"sha256:85bca64e63452c655b64a6696039671d768e1273d456dc9c304414091b859257","target":"graph","created_at":"2026-07-05T11:59:19Z","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/2508.12252/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"C. Karen Liu, Haochen Shi, Kaizhe Hu, Shuran Song, Weizhuo Wang, Yao He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-17T06:17:06Z","title":"Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for Humanoids"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12252","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":"sha256:70d329dabaf158242eadfc3d4719c0ae13e23a8721729ffa82ac5ce155feb813","target":"record","created_at":"2026-07-05T11:59:19Z","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":"e0d8cfc3b5c44e73434d4e930fed4516721ce0a7430ccdea6d5c739d692f7f38","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-17T06:17:06Z","title_canon_sha256":"59dcad8507109e7a7eb714ab1be23d38f1b6a19d2013a37c7cc287fba8b916d5"},"schema_version":"1.0","source":{"id":"2508.12252","kind":"arxiv","version":2}},"canonical_sha256":"8dfcc02c6795358a6105322e115305789f0744f9a32f956fa84f3dc7bed087b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8dfcc02c6795358a6105322e115305789f0744f9a32f956fa84f3dc7bed087b8","first_computed_at":"2026-07-05T11:59:19.950579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:19.950579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L2GWxo8RDUBuUgyZgDQOF7SL9kqiSlgCN5TzAfu4W9Dks/couO+WdAdvhBD2kQSP43M/k7ZK8YJaiIU0Yu5gBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:19.951009Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.12252","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70d329dabaf158242eadfc3d4719c0ae13e23a8721729ffa82ac5ce155feb813","sha256:85bca64e63452c655b64a6696039671d768e1273d456dc9c304414091b859257"],"state_sha256":"4aa7d9fb71a9e2892928b3adc3f1f092c19f8d9392b0daf820e7dca825c5b158"}