{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6A7U5GQ2LRGJUFQYBFBDQT65NB","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":"228d34b2cc3ab8c5602f06982f3f39448c28116bb1f517dd0f83306769297fc3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-04-30T00:36:26Z","title_canon_sha256":"a3286ca8569e18616957097ba9de7f309b81758d14cb008154d5e11c93459f76"},"schema_version":"1.0","source":{"id":"2404.19173","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.19173","created_at":"2026-07-05T09:00:59Z"},{"alias_kind":"arxiv_version","alias_value":"2404.19173v2","created_at":"2026-07-05T09:00:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.19173","created_at":"2026-07-05T09:00:59Z"},{"alias_kind":"pith_short_12","alias_value":"6A7U5GQ2LRGJ","created_at":"2026-07-05T09:00:59Z"},{"alias_kind":"pith_short_16","alias_value":"6A7U5GQ2LRGJUFQY","created_at":"2026-07-05T09:00:59Z"},{"alias_kind":"pith_short_8","alias_value":"6A7U5GQ2","created_at":"2026-07-05T09:00:59Z"}],"graph_snapshots":[{"event_id":"sha256:3d5487ae366adcc0d7ebcf537fdefd9e1ea1f0b636ddce88b38627c276cfc4aa","target":"graph","created_at":"2026-07-05T09:00:59Z","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/2404.19173/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A necessary capability for humanoid robots is the ability to stand and walk while rejecting natural disturbances. Recent progress has been made using sim-to-real reinforcement learning (RL) to train such locomotion controllers, with approaches differing mainly in their reward functions. However, prior works lack a clear method to systematically test new reward functions and compare controller performance through repeatable experiments. This limits our understanding of the trade-offs between approaches and hinders progress. To address this, we propose a low-cost, quantitative benchmarking metho","authors_text":"Aayam Shrestha, Alan Fern, Bart van Marum, Helei Duan, Jeremy Dao, Pranay Dugar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-04-30T00:36:26Z","title":"Revisiting Reward Design and Evaluation for Robust Humanoid Standing and Walking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.19173","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":"sha256:2dc94a52f3d3d194dc45b2808f87116b6c13296d4af3ded8aa15beff70baa5a9","target":"record","created_at":"2026-07-05T09:00:59Z","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":"228d34b2cc3ab8c5602f06982f3f39448c28116bb1f517dd0f83306769297fc3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-04-30T00:36:26Z","title_canon_sha256":"a3286ca8569e18616957097ba9de7f309b81758d14cb008154d5e11c93459f76"},"schema_version":"1.0","source":{"id":"2404.19173","kind":"arxiv","version":2}},"canonical_sha256":"f03f4e9a1a5c4c9a16180942384fdd687537fa051b99af9a5bd3073e2e6ae186","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f03f4e9a1a5c4c9a16180942384fdd687537fa051b99af9a5bd3073e2e6ae186","first_computed_at":"2026-07-05T09:00:59.817274Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:59.817274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pXTFWFKVoZH3ZDgNOvn2h2l14dBweRKlhkfkluJS7p/Q9NmTu2Udns/sP9FWNr3La4nGryFSnRaxBMog9s4aAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:59.817822Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.19173","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2dc94a52f3d3d194dc45b2808f87116b6c13296d4af3ded8aa15beff70baa5a9","sha256:3d5487ae366adcc0d7ebcf537fdefd9e1ea1f0b636ddce88b38627c276cfc4aa"],"state_sha256":"d64d944425b15cb8c2fca961ec399243bfe583cc7b455d14a56e7f5cbf1a1934"}