{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CFKK743LBRZMJHR5BUO2J6NTQ7","short_pith_number":"pith:CFKK743L","canonical_record":{"source":{"id":"2403.04205","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-07T04:21:12Z","cross_cats_sorted":[],"title_canon_sha256":"56e680640a7ff9cf39485314c79826e432fa2796d03690d5562320579b011a39","abstract_canon_sha256":"72328337a5af4a7c3d0dbbcde2f709f24c0bf3f8522011e79ea587071442ec16"},"schema_version":"1.0"},"canonical_sha256":"1154aff36b0c72c49e3d0d1da4f9b387eaff3959f937a5666f9776f71632464c","source":{"kind":"arxiv","id":"2403.04205","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CFKK743LBRZMJHR5BUO2J6NTQ7","target":"record","payload":{"canonical_record":{"source":{"id":"2403.04205","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-07T04:21:12Z","cross_cats_sorted":[],"title_canon_sha256":"56e680640a7ff9cf39485314c79826e432fa2796d03690d5562320579b011a39","abstract_canon_sha256":"72328337a5af4a7c3d0dbbcde2f709f24c0bf3f8522011e79ea587071442ec16"},"schema_version":"1.0"},"canonical_sha256":"1154aff36b0c72c49e3d0d1da4f9b387eaff3959f937a5666f9776f71632464c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:47.397220Z","signature_b64":"j1zi1E3O8g5LwS3dP4XDecC0+Z5ckjVPPAtf+LmZEf6SlPDtmoN0oQNfzOSQh/xcNvhKeXVLLVX9JD9ldZcpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1154aff36b0c72c49e3d0d1da4f9b387eaff3959f937a5666f9776f71632464c","last_reissued_at":"2026-07-05T09:08:47.396500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:47.396500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.04205","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:08:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZvYfQgxCbqbGiU0XUo+FwSPD+Z/lJp+3KNx69yfLlBTNuMeIpcyTMQisQPghPEDVzXZmDziiYonn6OFHd3CuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:08:40.872968Z"},"content_sha256":"a985ea14d1bda0eb1c757a8b6574cf06a464964887627f80f1a0c91b3d8ecdc2","schema_version":"1.0","event_id":"sha256:a985ea14d1bda0eb1c757a8b6574cf06a464964887627f80f1a0c91b3d8ecdc2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CFKK743LBRZMJHR5BUO2J6NTQ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OGMP: Oracle Guided Multi-mode Policies for Agile and Versatile Robot Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Lokesh Krishna, Nikhil Sobanbabu, Quan Nguyen","submitted_at":"2024-03-07T04:21:12Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04205","kind":"arxiv","version":3},"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/2403.04205/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":"2026-07-05T09:08:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"72pFxqRaf8HTeo2XT0B7fNYv3dvWSXfrIUnwo6TD65HBXoDYq0g28vnDpL7wBUTn2lrvWzeUfN1tJ0TPzwjTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:08:40.873353Z"},"content_sha256":"0d778080884a92610e2db70b74f13a7743fbf475cdf47170b703c87f3b93d474","schema_version":"1.0","event_id":"sha256:0d778080884a92610e2db70b74f13a7743fbf475cdf47170b703c87f3b93d474"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CFKK743LBRZMJHR5BUO2J6NTQ7/bundle.json","state_url":"https://pith.science/pith/CFKK743LBRZMJHR5BUO2J6NTQ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CFKK743LBRZMJHR5BUO2J6NTQ7/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":"2026-07-07T14:08:40Z","links":{"resolver":"https://pith.science/pith/CFKK743LBRZMJHR5BUO2J6NTQ7","bundle":"https://pith.science/pith/CFKK743LBRZMJHR5BUO2J6NTQ7/bundle.json","state":"https://pith.science/pith/CFKK743LBRZMJHR5BUO2J6NTQ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CFKK743LBRZMJHR5BUO2J6NTQ7/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WMo24xU9yEE+8/YfTKAbmD9Lg690uzk3pHEvcvuS2+H3u7ZAJ99UFYqA0tWJKCGnIQxnCBB2ntbc3Qbtj8z3Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:08:40.875249Z","bundle_sha256":"19d42bbcf216aa764bc6143a43bf40e4a8e87f098c3742f268cedccafc247db0"}}