{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:FA3TH2VJRXDPIWT3V5GLVW22H2","short_pith_number":"pith:FA3TH2VJ","canonical_record":{"source":{"id":"2011.05927","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T17:35:25Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"title_canon_sha256":"1a35c71e5c6d0be7154c005314e742478d73ba80ed3b3cd8a6273feb18b4c275","abstract_canon_sha256":"c669b70fda69e2e306ae52ec8f2b3fd806ab588600142b90f8544c40454c28f1"},"schema_version":"1.0"},"canonical_sha256":"283733eaa98dc6f45a7baf4cbadb5a3ea015447eec521f20d17fdf08e59d5932","source":{"kind":"arxiv","id":"2011.05927","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.05927","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2011.05927v3","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05927","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"FA3TH2VJRXDP","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"FA3TH2VJRXDPIWT3","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"FA3TH2VJ","created_at":"2026-07-05T04:08:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:FA3TH2VJRXDPIWT3V5GLVW22H2","target":"record","payload":{"canonical_record":{"source":{"id":"2011.05927","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T17:35:25Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"title_canon_sha256":"1a35c71e5c6d0be7154c005314e742478d73ba80ed3b3cd8a6273feb18b4c275","abstract_canon_sha256":"c669b70fda69e2e306ae52ec8f2b3fd806ab588600142b90f8544c40454c28f1"},"schema_version":"1.0"},"canonical_sha256":"283733eaa98dc6f45a7baf4cbadb5a3ea015447eec521f20d17fdf08e59d5932","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:56.045489Z","signature_b64":"k+1pemA46hhZxdrveoqJ9d6kOQB7iucBZy4gssc3aJ2fL3p4BfxYLgWYSKxRwRtyg6L2R5eZ8S6epl8MySR/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"283733eaa98dc6f45a7baf4cbadb5a3ea015447eec521f20d17fdf08e59d5932","last_reissued_at":"2026-07-05T04:08:56.045130Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:56.045130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.05927","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":"2026-07-05T04:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qkbDnwbFuI1U0g7tRubfGuR6FR3XbGu22GAa8dQHaSUczgYNz5ortl0F2CJyawD/cD/Z+dz0o/poIQ4IF7QhCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T14:56:28.278131Z"},"content_sha256":"9d315cbbcc7e5a257be576bf856c78f5a466b8a61ade1d6b1319d709405099df","schema_version":"1.0","event_id":"sha256:9d315cbbcc7e5a257be576bf856c78f5a466b8a61ade1d6b1319d709405099df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:FA3TH2VJRXDPIWT3V5GLVW22H2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Using Hamiltonian Monte Carlo Sampling for Reinforcement Learning Problems in High-dimension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Amit Chakraborty, Biswadip Dey, Naomi Ehrich Leonard, Udari Madhushani","submitted_at":"2020-11-11T17:35:25Z","abstract_excerpt":"Value function based reinforcement learning (RL) algorithms, for example, $Q$-learning, learn optimal policies from datasets of actions, rewards, and state transitions. However, when the underlying state transition dynamics are stochastic and evolve on a high-dimensional space, generating independent and identically distributed (IID) data samples for creating these datasets poses a significant challenge due to the intractability of the associated normalizing integral. In these scenarios, Hamiltonian Monte Carlo (HMC) sampling offers a computationally tractable way to generate data for training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05927","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/2011.05927/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":"2026-07-05T04:08:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cNahrXc2Lo7nVUT74N5JyVUxhxKuz6D2fy/lyDeTtdfHXRFe2km+3bmwODx+YIrcPtvrZcl4penFpUNSc6fcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T14:56:28.278777Z"},"content_sha256":"0ff05d27556d88498767ec6a0504caa60de93a6c8713e919a9898965ca3e7dff","schema_version":"1.0","event_id":"sha256:0ff05d27556d88498767ec6a0504caa60de93a6c8713e919a9898965ca3e7dff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FA3TH2VJRXDPIWT3V5GLVW22H2/bundle.json","state_url":"https://pith.science/pith/FA3TH2VJRXDPIWT3V5GLVW22H2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FA3TH2VJRXDPIWT3V5GLVW22H2/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":"2026-07-12T14:56:28Z","links":{"resolver":"https://pith.science/pith/FA3TH2VJRXDPIWT3V5GLVW22H2","bundle":"https://pith.science/pith/FA3TH2VJRXDPIWT3V5GLVW22H2/bundle.json","state":"https://pith.science/pith/FA3TH2VJRXDPIWT3V5GLVW22H2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FA3TH2VJRXDPIWT3V5GLVW22H2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FA3TH2VJRXDPIWT3V5GLVW22H2","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":"c669b70fda69e2e306ae52ec8f2b3fd806ab588600142b90f8544c40454c28f1","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T17:35:25Z","title_canon_sha256":"1a35c71e5c6d0be7154c005314e742478d73ba80ed3b3cd8a6273feb18b4c275"},"schema_version":"1.0","source":{"id":"2011.05927","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.05927","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"arxiv_version","alias_value":"2011.05927v3","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.05927","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"pith_short_12","alias_value":"FA3TH2VJRXDP","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"pith_short_16","alias_value":"FA3TH2VJRXDPIWT3","created_at":"2026-07-05T04:08:56Z"},{"alias_kind":"pith_short_8","alias_value":"FA3TH2VJ","created_at":"2026-07-05T04:08:56Z"}],"graph_snapshots":[{"event_id":"sha256:0ff05d27556d88498767ec6a0504caa60de93a6c8713e919a9898965ca3e7dff","target":"graph","created_at":"2026-07-05T04:08:56Z","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/2011.05927/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Value function based reinforcement learning (RL) algorithms, for example, $Q$-learning, learn optimal policies from datasets of actions, rewards, and state transitions. However, when the underlying state transition dynamics are stochastic and evolve on a high-dimensional space, generating independent and identically distributed (IID) data samples for creating these datasets poses a significant challenge due to the intractability of the associated normalizing integral. In these scenarios, Hamiltonian Monte Carlo (HMC) sampling offers a computationally tractable way to generate data for training","authors_text":"Amit Chakraborty, Biswadip Dey, Naomi Ehrich Leonard, Udari Madhushani","cross_cats":["cs.SY","eess.SY","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T17:35:25Z","title":"On Using Hamiltonian Monte Carlo Sampling for Reinforcement Learning Problems in High-dimension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.05927","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":"sha256:9d315cbbcc7e5a257be576bf856c78f5a466b8a61ade1d6b1319d709405099df","target":"record","created_at":"2026-07-05T04:08:56Z","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":"c669b70fda69e2e306ae52ec8f2b3fd806ab588600142b90f8544c40454c28f1","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-11T17:35:25Z","title_canon_sha256":"1a35c71e5c6d0be7154c005314e742478d73ba80ed3b3cd8a6273feb18b4c275"},"schema_version":"1.0","source":{"id":"2011.05927","kind":"arxiv","version":3}},"canonical_sha256":"283733eaa98dc6f45a7baf4cbadb5a3ea015447eec521f20d17fdf08e59d5932","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"283733eaa98dc6f45a7baf4cbadb5a3ea015447eec521f20d17fdf08e59d5932","first_computed_at":"2026-07-05T04:08:56.045130Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:56.045130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k+1pemA46hhZxdrveoqJ9d6kOQB7iucBZy4gssc3aJ2fL3p4BfxYLgWYSKxRwRtyg6L2R5eZ8S6epl8MySR/CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:56.045489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.05927","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d315cbbcc7e5a257be576bf856c78f5a466b8a61ade1d6b1319d709405099df","sha256:0ff05d27556d88498767ec6a0504caa60de93a6c8713e919a9898965ca3e7dff"],"state_sha256":"4133b270052a766d4c469522b64c5b4654d114535fc030e92e6feea859cf7ac4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OWHZCRIDDcAWtYnYYLC3f1Q5Vd8Vvdu2Hws0R0GDIEGsfqPTW4JWU7Xn0Fuy6ZHbDC7po9VZ0TYUe5riZbvxBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T14:56:28.283949Z","bundle_sha256":"de30a1a617be87e3a76e867e3eace10be72f120eb00179dfdb22c3e7ac43fb0e"}}