{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MAO2B6ZEQQ6BFMMNZZTIYJE2WL","short_pith_number":"pith:MAO2B6ZE","canonical_record":{"source":{"id":"2507.01243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-01T23:31:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fb9ec934656c6b355536aaf427ff0aa12daa231fecec5aa986d73ad03952a4ae","abstract_canon_sha256":"878c33c73429c34fe377c3def7886a23ed61848f47c7d39e36b8ae6a539dc1d2"},"schema_version":"1.0"},"canonical_sha256":"601da0fb24843c12b18dce668c249ab2f72fdb5cbf2e0c159aa33536bebb2826","source":{"kind":"arxiv","id":"2507.01243","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01243","created_at":"2026-07-05T11:30:27Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01243v1","created_at":"2026-07-05T11:30:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01243","created_at":"2026-07-05T11:30:27Z"},{"alias_kind":"pith_short_12","alias_value":"MAO2B6ZEQQ6B","created_at":"2026-07-05T11:30:27Z"},{"alias_kind":"pith_short_16","alias_value":"MAO2B6ZEQQ6BFMMN","created_at":"2026-07-05T11:30:27Z"},{"alias_kind":"pith_short_8","alias_value":"MAO2B6ZE","created_at":"2026-07-05T11:30:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MAO2B6ZEQQ6BFMMNZZTIYJE2WL","target":"record","payload":{"canonical_record":{"source":{"id":"2507.01243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-01T23:31:36Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fb9ec934656c6b355536aaf427ff0aa12daa231fecec5aa986d73ad03952a4ae","abstract_canon_sha256":"878c33c73429c34fe377c3def7886a23ed61848f47c7d39e36b8ae6a539dc1d2"},"schema_version":"1.0"},"canonical_sha256":"601da0fb24843c12b18dce668c249ab2f72fdb5cbf2e0c159aa33536bebb2826","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:27.280464Z","signature_b64":"jttKMV1XX1vc1w2zjuaJDV9Q3plKX2ealZ0cLWAxfapSkPsmliUJyHz2VpWkVOSkC4+Yf2yZcS8Bs6YYNVh8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"601da0fb24843c12b18dce668c249ab2f72fdb5cbf2e0c159aa33536bebb2826","last_reissued_at":"2026-07-05T11:30:27.279925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:27.279925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.01243","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:30:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4hZtSdXbwmh+s7GwPL5sgDayjTqMg4lCC73aBzj8yrfLa9fCr34v1Rb37XnmUTp0lJumjUoZOqzkM33JNrW2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:37:42.385911Z"},"content_sha256":"9539ef5cbb9da9dda79f5fe5ba7716304cd416bc79396d9a190dd97535da5c57","schema_version":"1.0","event_id":"sha256:9539ef5cbb9da9dda79f5fe5ba7716304cd416bc79396d9a190dd97535da5c57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MAO2B6ZEQQ6BFMMNZZTIYJE2WL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Jump-Start Reinforcement Learning with Self-Evolving Priors for Extreme Monopedal Locomotion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Guojian Zhan, Shengbo Eben Li, Shiqi Liu, Tao Zhang, Yao Lyu, Ziang Zheng","submitted_at":"2025-07-01T23:31:36Z","abstract_excerpt":"Reinforcement learning (RL) has shown great potential in enabling quadruped robots to perform agile locomotion. However, directly training policies to simultaneously handle dual extreme challenges, i.e., extreme underactuation and extreme terrains, as in monopedal hopping tasks, remains highly challenging due to unstable early-stage interactions and unreliable reward feedback. To address this, we propose JumpER (jump-start reinforcement learning via self-evolving priors), an RL training framework that structures policy learning into multiple stages of increasing complexity. By dynamically gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01243","kind":"arxiv","version":1},"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/2507.01243/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:30:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EpiGJbYCto01Go7hO7DmHa3DXh0i+AXWbTALcHZWxP0/Ey0lFTg5+zuk5WPUpP0BsvenIWPSL/U8IUzpV+xhCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:37:42.386688Z"},"content_sha256":"6f418a6a71ba4b0165f5675b3a8d9fd02f977a549c5a7cdb775086b3f6c34820","schema_version":"1.0","event_id":"sha256:6f418a6a71ba4b0165f5675b3a8d9fd02f977a549c5a7cdb775086b3f6c34820"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MAO2B6ZEQQ6BFMMNZZTIYJE2WL/bundle.json","state_url":"https://pith.science/pith/MAO2B6ZEQQ6BFMMNZZTIYJE2WL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MAO2B6ZEQQ6BFMMNZZTIYJE2WL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T17:37:42Z","links":{"resolver":"https://pith.science/pith/MAO2B6ZEQQ6BFMMNZZTIYJE2WL","bundle":"https://pith.science/pith/MAO2B6ZEQQ6BFMMNZZTIYJE2WL/bundle.json","state":"https://pith.science/pith/MAO2B6ZEQQ6BFMMNZZTIYJE2WL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MAO2B6ZEQQ6BFMMNZZTIYJE2WL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MAO2B6ZEQQ6BFMMNZZTIYJE2WL","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":"878c33c73429c34fe377c3def7886a23ed61848f47c7d39e36b8ae6a539dc1d2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-01T23:31:36Z","title_canon_sha256":"fb9ec934656c6b355536aaf427ff0aa12daa231fecec5aa986d73ad03952a4ae"},"schema_version":"1.0","source":{"id":"2507.01243","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01243","created_at":"2026-07-05T11:30:27Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01243v1","created_at":"2026-07-05T11:30:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01243","created_at":"2026-07-05T11:30:27Z"},{"alias_kind":"pith_short_12","alias_value":"MAO2B6ZEQQ6B","created_at":"2026-07-05T11:30:27Z"},{"alias_kind":"pith_short_16","alias_value":"MAO2B6ZEQQ6BFMMN","created_at":"2026-07-05T11:30:27Z"},{"alias_kind":"pith_short_8","alias_value":"MAO2B6ZE","created_at":"2026-07-05T11:30:27Z"}],"graph_snapshots":[{"event_id":"sha256:6f418a6a71ba4b0165f5675b3a8d9fd02f977a549c5a7cdb775086b3f6c34820","target":"graph","created_at":"2026-07-05T11:30:27Z","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/2507.01243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has shown great potential in enabling quadruped robots to perform agile locomotion. However, directly training policies to simultaneously handle dual extreme challenges, i.e., extreme underactuation and extreme terrains, as in monopedal hopping tasks, remains highly challenging due to unstable early-stage interactions and unreliable reward feedback. To address this, we propose JumpER (jump-start reinforcement learning via self-evolving priors), an RL training framework that structures policy learning into multiple stages of increasing complexity. By dynamically gene","authors_text":"Guojian Zhan, Shengbo Eben Li, Shiqi Liu, Tao Zhang, Yao Lyu, Ziang Zheng","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-01T23:31:36Z","title":"Jump-Start Reinforcement Learning with Self-Evolving Priors for Extreme Monopedal Locomotion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01243","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":"sha256:9539ef5cbb9da9dda79f5fe5ba7716304cd416bc79396d9a190dd97535da5c57","target":"record","created_at":"2026-07-05T11:30:27Z","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":"878c33c73429c34fe377c3def7886a23ed61848f47c7d39e36b8ae6a539dc1d2","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-01T23:31:36Z","title_canon_sha256":"fb9ec934656c6b355536aaf427ff0aa12daa231fecec5aa986d73ad03952a4ae"},"schema_version":"1.0","source":{"id":"2507.01243","kind":"arxiv","version":1}},"canonical_sha256":"601da0fb24843c12b18dce668c249ab2f72fdb5cbf2e0c159aa33536bebb2826","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"601da0fb24843c12b18dce668c249ab2f72fdb5cbf2e0c159aa33536bebb2826","first_computed_at":"2026-07-05T11:30:27.279925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:27.279925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jttKMV1XX1vc1w2zjuaJDV9Q3plKX2ealZ0cLWAxfapSkPsmliUJyHz2VpWkVOSkC4+Yf2yZcS8Bs6YYNVh8Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:27.280464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01243","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9539ef5cbb9da9dda79f5fe5ba7716304cd416bc79396d9a190dd97535da5c57","sha256:6f418a6a71ba4b0165f5675b3a8d9fd02f977a549c5a7cdb775086b3f6c34820"],"state_sha256":"13121abeef653d6adce2ea2e1c5bdcf85da0e71c6778784f975a9dbd46f11329"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0b7qF7NV+LA55JuXftsX1zZjzcZ4152C++Nkwsib7j/gpq0pN8A21XNYta3ApxIx2y8b6PLSUKl8UwjOqJlfDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:37:42.391970Z","bundle_sha256":"e49428f41262c5535adb8099d0868cc3d12f22867b13b37eb03d16b338ceac6b"}}