{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y33JFOVLN2QPKO3M2NXAVZ4TBX","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":"fb36ef648bc6c4cf35d80bae03b2d966038607703d65f8a2c857494e60458d76","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-24T10:04:11Z","title_canon_sha256":"7641ffe5f70016dcbfc0d336806994d14d44336593c43a559dc527b76c8545ff"},"schema_version":"1.0","source":{"id":"2605.24975","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24975","created_at":"2026-05-26T01:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24975v1","created_at":"2026-05-26T01:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24975","created_at":"2026-05-26T01:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"Y33JFOVLN2QP","created_at":"2026-05-26T01:04:08Z"},{"alias_kind":"pith_short_16","alias_value":"Y33JFOVLN2QPKO3M","created_at":"2026-05-26T01:04:08Z"},{"alias_kind":"pith_short_8","alias_value":"Y33JFOVL","created_at":"2026-05-26T01:04:08Z"}],"graph_snapshots":[{"event_id":"sha256:9fe981740f08f3bc2f5dd50f4a8b2bc3920e5afc4b369ddb13b00894b3377914","target":"graph","created_at":"2026-05-26T01:04:08Z","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/2605.24975/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Proximal Policy Optimization (PPO) has become the de facto standard for training legged robots, thanks to its robustness and scalability in massively parallel simulation environments like IsaacLab. However, its on-policy nature makes it inherently sample-inefficient, preventing its use for continuous adaptation and fine-tuning on real hardware. Soft Actor-Critic (SAC), by contrast, is an off-policy algorithm that can reuse past experience, making it a natural candidate for sim-to-real transfer workflows where the same algorithm can be used both in simulation and for online learning on the real","authors_text":"Chenhao Li, Gianluca Sabatini, Marco Hutter","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-24T10:04:11Z","title":"Bridging the Gap: Enabling Soft Actor Critic for High Performance Legged Locomotion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24975","kind":"arxiv","version":1},"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":"sha256:69ffaeda762730033f1d5e5652babbd7ef2c09c7a02bd07b56d75414cdfb1bd9","target":"record","created_at":"2026-05-26T01:04:08Z","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":"fb36ef648bc6c4cf35d80bae03b2d966038607703d65f8a2c857494e60458d76","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-24T10:04:11Z","title_canon_sha256":"7641ffe5f70016dcbfc0d336806994d14d44336593c43a559dc527b76c8545ff"},"schema_version":"1.0","source":{"id":"2605.24975","kind":"arxiv","version":1}},"canonical_sha256":"c6f692baab6ea0f53b6cd36e0ae7930dc0ec59682e9d7e41f161274b3094bee4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6f692baab6ea0f53b6cd36e0ae7930dc0ec59682e9d7e41f161274b3094bee4","first_computed_at":"2026-05-26T01:04:08.914845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:04:08.914845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cWN6UXWapKiTkenOyMkSgf+osAMcqU5ys46Hj/TL+x+xh0RINb7gBT7n0w7/sRtKNi88wSeW7/WQSkO/9YjKAw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:04:08.915307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24975","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69ffaeda762730033f1d5e5652babbd7ef2c09c7a02bd07b56d75414cdfb1bd9","sha256:9fe981740f08f3bc2f5dd50f4a8b2bc3920e5afc4b369ddb13b00894b3377914"],"state_sha256":"41c2a9f96a9faca1da321f3e96c5d9a797618a58b0e16e44f76f5f480fd5d7aa"}