{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CFKK743LBRZMJHR5BUO2J6NTQ7","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":"72328337a5af4a7c3d0dbbcde2f709f24c0bf3f8522011e79ea587071442ec16","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-07T04:21:12Z","title_canon_sha256":"56e680640a7ff9cf39485314c79826e432fa2796d03690d5562320579b011a39"},"schema_version":"1.0","source":{"id":"2403.04205","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.04205","created_at":"2026-07-05T09:08:47Z"},{"alias_kind":"arxiv_version","alias_value":"2403.04205v3","created_at":"2026-07-05T09:08:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04205","created_at":"2026-07-05T09:08:47Z"},{"alias_kind":"pith_short_12","alias_value":"CFKK743LBRZM","created_at":"2026-07-05T09:08:47Z"},{"alias_kind":"pith_short_16","alias_value":"CFKK743LBRZMJHR5","created_at":"2026-07-05T09:08:47Z"},{"alias_kind":"pith_short_8","alias_value":"CFKK743L","created_at":"2026-07-05T09:08:47Z"}],"graph_snapshots":[{"event_id":"sha256:0d778080884a92610e2db70b74f13a7743fbf475cdf47170b703c87f3b93d474","target":"graph","created_at":"2026-07-05T09:08:47Z","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/2403.04205/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The efficacy of reinforcement learning for robot control relies on the tailored integration of task-specific priors and heuristics for effective exploration, which challenges their straightforward application to complex tasks and necessitates a unified approach. In this work, we define a general class for priors called oracles that generate state references when queried in a closed-loop manner during training. By bounding the permissible state around the oracle's ansatz, we propose a task-agnostic oracle-guided policy optimization. To enhance modularity, we introduce task-vital modes, showing ","authors_text":"Lokesh Krishna, Nikhil Sobanbabu, Quan Nguyen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-07T04:21:12Z","title":"OGMP: Oracle Guided Multi-mode Policies for Agile and Versatile Robot Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04205","kind":"arxiv","version":3},"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:a985ea14d1bda0eb1c757a8b6574cf06a464964887627f80f1a0c91b3d8ecdc2","target":"record","created_at":"2026-07-05T09:08:47Z","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":"72328337a5af4a7c3d0dbbcde2f709f24c0bf3f8522011e79ea587071442ec16","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-07T04:21:12Z","title_canon_sha256":"56e680640a7ff9cf39485314c79826e432fa2796d03690d5562320579b011a39"},"schema_version":"1.0","source":{"id":"2403.04205","kind":"arxiv","version":3}},"canonical_sha256":"1154aff36b0c72c49e3d0d1da4f9b387eaff3959f937a5666f9776f71632464c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1154aff36b0c72c49e3d0d1da4f9b387eaff3959f937a5666f9776f71632464c","first_computed_at":"2026-07-05T09:08:47.396500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:47.396500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j1zi1E3O8g5LwS3dP4XDecC0+Z5ckjVPPAtf+LmZEf6SlPDtmoN0oQNfzOSQh/xcNvhKeXVLLVX9JD9ldZcpAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:47.397220Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.04205","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a985ea14d1bda0eb1c757a8b6574cf06a464964887627f80f1a0c91b3d8ecdc2","sha256:0d778080884a92610e2db70b74f13a7743fbf475cdf47170b703c87f3b93d474"],"state_sha256":"c7986d887b1cb48e590314f23d8e1c72e23951e5f66be2b2de788b6b6d2584ae"}