{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:WXJ2ULMEQTS7Y3C7AM2WHPBGGF","short_pith_number":"pith:WXJ2ULME","canonical_record":{"source":{"id":"2106.07125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-06-14T01:18:09Z","cross_cats_sorted":[],"title_canon_sha256":"1272e0ad667b20bfd4fce427c15aae0a12bcf920c27843f95e70e4da0f70ea84","abstract_canon_sha256":"9c7cacda53e3c965c75cf46216f8b4c24f1c6c54ad00d7433fc3dcdc09e6c493"},"schema_version":"1.0"},"canonical_sha256":"b5d3aa2d8484e5fc6c5f033563bc26315bdd92f4285575ce3fa142d3b3134601","source":{"kind":"arxiv","id":"2106.07125","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.07125","created_at":"2026-07-05T02:48:44Z"},{"alias_kind":"arxiv_version","alias_value":"2106.07125v1","created_at":"2026-07-05T02:48:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07125","created_at":"2026-07-05T02:48:44Z"},{"alias_kind":"pith_short_12","alias_value":"WXJ2ULMEQTS7","created_at":"2026-07-05T02:48:44Z"},{"alias_kind":"pith_short_16","alias_value":"WXJ2ULMEQTS7Y3C7","created_at":"2026-07-05T02:48:44Z"},{"alias_kind":"pith_short_8","alias_value":"WXJ2ULME","created_at":"2026-07-05T02:48:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:WXJ2ULMEQTS7Y3C7AM2WHPBGGF","target":"record","payload":{"canonical_record":{"source":{"id":"2106.07125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-06-14T01:18:09Z","cross_cats_sorted":[],"title_canon_sha256":"1272e0ad667b20bfd4fce427c15aae0a12bcf920c27843f95e70e4da0f70ea84","abstract_canon_sha256":"9c7cacda53e3c965c75cf46216f8b4c24f1c6c54ad00d7433fc3dcdc09e6c493"},"schema_version":"1.0"},"canonical_sha256":"b5d3aa2d8484e5fc6c5f033563bc26315bdd92f4285575ce3fa142d3b3134601","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:44.808024Z","signature_b64":"CkFZPkQUfgjfJpmdQPWr+tc3GNG7PRtMfL2Il1icYiP3sEjR6rfi8j1OhZrDaVHVqtLT+vo0Q/lZuE/96n7YDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5d3aa2d8484e5fc6c5f033563bc26315bdd92f4285575ce3fa142d3b3134601","last_reissued_at":"2026-07-05T02:48:44.807672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:44.807672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.07125","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":"2026-07-05T02:48:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cQ0SLrhTmcpd8qfDLp6BcJi85yXDaigJIFcnkccDOZEb0bleUnRuLnurRH9LQqFqIKPVk+m5ha0aAcmo4/1IDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:56:42.980066Z"},"content_sha256":"0b43455061f3d304472fb9f41c7cf2da5d4693ac86c63f3aafed4b38e1baa09d","schema_version":"1.0","event_id":"sha256:0b43455061f3d304472fb9f41c7cf2da5d4693ac86c63f3aafed4b38e1baa09d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:WXJ2ULMEQTS7Y3C7AM2WHPBGGF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational Policy Search using Sparse Gaussian Process Priors for Learning Multimodal Optimal Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Hikaru Sasaki, Takamitsu Matsubara","submitted_at":"2021-06-14T01:18:09Z","abstract_excerpt":"Policy search reinforcement learning has been drawing much attention as a method of learning a robot control policy. In particular, policy search using such non-parametric policies as Gaussian process regression can learn optimal actions with high-dimensional and redundant sensors as input. However, previous methods implicitly assume that the optimal action becomes unique for each state. This assumption can severely limit such practical applications as robot manipulations since designing a reward function that appears in only one optimal action for complex tasks is difficult. The previous meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07125","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/2106.07125/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":"2026-07-05T02:48:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N7xB0ktyhxxSQa1+lox7gjasqooDkbZsxyfAukb5HXOSRpGMA3jhKvnCg74TmHoerqrU21LQbT9WlNUnXjRZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:56:42.980530Z"},"content_sha256":"c7ae3be7dee567a3ce27866725ae9e2862e3fd9b018db4271207bc6f4ff266d0","schema_version":"1.0","event_id":"sha256:c7ae3be7dee567a3ce27866725ae9e2862e3fd9b018db4271207bc6f4ff266d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WXJ2ULMEQTS7Y3C7AM2WHPBGGF/bundle.json","state_url":"https://pith.science/pith/WXJ2ULMEQTS7Y3C7AM2WHPBGGF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WXJ2ULMEQTS7Y3C7AM2WHPBGGF/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":"2026-07-09T03:56:42Z","links":{"resolver":"https://pith.science/pith/WXJ2ULMEQTS7Y3C7AM2WHPBGGF","bundle":"https://pith.science/pith/WXJ2ULMEQTS7Y3C7AM2WHPBGGF/bundle.json","state":"https://pith.science/pith/WXJ2ULMEQTS7Y3C7AM2WHPBGGF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WXJ2ULMEQTS7Y3C7AM2WHPBGGF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WXJ2ULMEQTS7Y3C7AM2WHPBGGF","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":"9c7cacda53e3c965c75cf46216f8b4c24f1c6c54ad00d7433fc3dcdc09e6c493","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-06-14T01:18:09Z","title_canon_sha256":"1272e0ad667b20bfd4fce427c15aae0a12bcf920c27843f95e70e4da0f70ea84"},"schema_version":"1.0","source":{"id":"2106.07125","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.07125","created_at":"2026-07-05T02:48:44Z"},{"alias_kind":"arxiv_version","alias_value":"2106.07125v1","created_at":"2026-07-05T02:48:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.07125","created_at":"2026-07-05T02:48:44Z"},{"alias_kind":"pith_short_12","alias_value":"WXJ2ULMEQTS7","created_at":"2026-07-05T02:48:44Z"},{"alias_kind":"pith_short_16","alias_value":"WXJ2ULMEQTS7Y3C7","created_at":"2026-07-05T02:48:44Z"},{"alias_kind":"pith_short_8","alias_value":"WXJ2ULME","created_at":"2026-07-05T02:48:44Z"}],"graph_snapshots":[{"event_id":"sha256:c7ae3be7dee567a3ce27866725ae9e2862e3fd9b018db4271207bc6f4ff266d0","target":"graph","created_at":"2026-07-05T02:48:44Z","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/2106.07125/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy search reinforcement learning has been drawing much attention as a method of learning a robot control policy. In particular, policy search using such non-parametric policies as Gaussian process regression can learn optimal actions with high-dimensional and redundant sensors as input. However, previous methods implicitly assume that the optimal action becomes unique for each state. This assumption can severely limit such practical applications as robot manipulations since designing a reward function that appears in only one optimal action for complex tasks is difficult. The previous meth","authors_text":"Hikaru Sasaki, Takamitsu Matsubara","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-06-14T01:18:09Z","title":"Variational Policy Search using Sparse Gaussian Process Priors for Learning Multimodal Optimal Actions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.07125","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":"sha256:0b43455061f3d304472fb9f41c7cf2da5d4693ac86c63f3aafed4b38e1baa09d","target":"record","created_at":"2026-07-05T02:48:44Z","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":"9c7cacda53e3c965c75cf46216f8b4c24f1c6c54ad00d7433fc3dcdc09e6c493","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-06-14T01:18:09Z","title_canon_sha256":"1272e0ad667b20bfd4fce427c15aae0a12bcf920c27843f95e70e4da0f70ea84"},"schema_version":"1.0","source":{"id":"2106.07125","kind":"arxiv","version":1}},"canonical_sha256":"b5d3aa2d8484e5fc6c5f033563bc26315bdd92f4285575ce3fa142d3b3134601","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5d3aa2d8484e5fc6c5f033563bc26315bdd92f4285575ce3fa142d3b3134601","first_computed_at":"2026-07-05T02:48:44.807672Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:44.807672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CkFZPkQUfgjfJpmdQPWr+tc3GNG7PRtMfL2Il1icYiP3sEjR6rfi8j1OhZrDaVHVqtLT+vo0Q/lZuE/96n7YDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:44.808024Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.07125","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b43455061f3d304472fb9f41c7cf2da5d4693ac86c63f3aafed4b38e1baa09d","sha256:c7ae3be7dee567a3ce27866725ae9e2862e3fd9b018db4271207bc6f4ff266d0"],"state_sha256":"f6b35f10570b41150c72e60e0851b3daca9e3dac1f5250b02a798f55085b6294"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/WB/3/EQxqYMm0ISmSKOf3kJcBN2OmdQBVuEkNTLXkloD9c+Jr8nu0V2IvujiWMRjbheq8BNE9m69PUCgKW4BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:56:42.982535Z","bundle_sha256":"02921321a394b709b3ad2cacaa707a70e9f90748378d57fca5cfc48edab7a0a1"}}