{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QIXROM3I52NQRXEJZKCE2KPHOI","short_pith_number":"pith:QIXROM3I","canonical_record":{"source":{"id":"1806.06931","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-13T03:47:12Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d7b2ca1f602d53b5369e82efb44706c981ac31b3a339e83307fbf34899d55a05","abstract_canon_sha256":"9d2893ce92bd3bd983dd2fe39e03f3cdf6ab71418d9844f9bbc12cf7583621be"},"schema_version":"1.0"},"canonical_sha256":"822f173368ee9b08dc89ca844d29e7723a89e7c1f64e5206bcb0bff506315ad0","source":{"kind":"arxiv","id":"1806.06931","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06931","created_at":"2026-05-18T00:12:58Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06931v1","created_at":"2026-05-18T00:12:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06931","created_at":"2026-05-18T00:12:58Z"},{"alias_kind":"pith_short_12","alias_value":"QIXROM3I52NQ","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QIXROM3I52NQRXEJ","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QIXROM3I","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QIXROM3I52NQRXEJZKCE2KPHOI","target":"record","payload":{"canonical_record":{"source":{"id":"1806.06931","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-13T03:47:12Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d7b2ca1f602d53b5369e82efb44706c981ac31b3a339e83307fbf34899d55a05","abstract_canon_sha256":"9d2893ce92bd3bd983dd2fe39e03f3cdf6ab71418d9844f9bbc12cf7583621be"},"schema_version":"1.0"},"canonical_sha256":"822f173368ee9b08dc89ca844d29e7723a89e7c1f64e5206bcb0bff506315ad0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:58.031459Z","signature_b64":"YsiHeqDZS8CXS2vptycDaEg0UqsuLXLDjgBG4zahXyHXS12tKhwK6ouVvN33Sdvns/ill0b0z5Rww45NPmg+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"822f173368ee9b08dc89ca844d29e7723a89e7c1f64e5206bcb0bff506315ad0","last_reissued_at":"2026-05-18T00:12:58.030813Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:58.030813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.06931","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":"2026-05-18T00:12:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ao6rp+xIWRWi7lt1F6dBbEEVlV42p68z4Ya4kNn2ckHr0xjSZ6BgqO0a6QZM6UZJdjJ8CKe0EhquNDfLfsTfDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T19:39:35.431594Z"},"content_sha256":"ca5bc61672b21c93f052dedc8c2cf1c7a1fbc0d0ea5dec99844fbc3f8bc2f6e7","schema_version":"1.0","event_id":"sha256:ca5bc61672b21c93f052dedc8c2cf1c7a1fbc0d0ea5dec99844fbc3f8bc2f6e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QIXROM3I52NQRXEJZKCE2KPHOI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir-massoud Farahmand, Daniel Nikovski, Martha White, Piyush Grover, Saleh Nabi, Yangchen Pan","submitted_at":"2018-06-13T03:47:12Z","abstract_excerpt":"Recent work has shown that reinforcement learning (RL) is a promising approach to control dynamical systems described by partial differential equations (PDE). This paper shows how to use RL to tackle more general PDE control problems that have continuous high-dimensional action spaces with spatial relationship among action dimensions. In particular, we propose the concept of action descriptors, which encode regularities among spatially-extended action dimensions and enable the agent to control high-dimensional action PDEs. We provide theoretical evidence suggesting that this approach can be mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06931","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":""},"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":"2026-05-18T00:12:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4XSUgjIecfhS6A8jeRgLgWLQLYVHyvYF15zKtOD9ZIdWNTJmPBqkcvZ8LMsbjXFspJIWx/NP6T8M+p4k28XrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T19:39:35.432074Z"},"content_sha256":"02ea90b42f84678468dda493e61fb1ad5ff9ae8bfee01c304e1ecef8b9f9e4e4","schema_version":"1.0","event_id":"sha256:02ea90b42f84678468dda493e61fb1ad5ff9ae8bfee01c304e1ecef8b9f9e4e4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QIXROM3I52NQRXEJZKCE2KPHOI/bundle.json","state_url":"https://pith.science/pith/QIXROM3I52NQRXEJZKCE2KPHOI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QIXROM3I52NQRXEJZKCE2KPHOI/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":"2026-05-21T19:39:35Z","links":{"resolver":"https://pith.science/pith/QIXROM3I52NQRXEJZKCE2KPHOI","bundle":"https://pith.science/pith/QIXROM3I52NQRXEJZKCE2KPHOI/bundle.json","state":"https://pith.science/pith/QIXROM3I52NQRXEJZKCE2KPHOI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QIXROM3I52NQRXEJZKCE2KPHOI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QIXROM3I52NQRXEJZKCE2KPHOI","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":"9d2893ce92bd3bd983dd2fe39e03f3cdf6ab71418d9844f9bbc12cf7583621be","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-13T03:47:12Z","title_canon_sha256":"d7b2ca1f602d53b5369e82efb44706c981ac31b3a339e83307fbf34899d55a05"},"schema_version":"1.0","source":{"id":"1806.06931","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06931","created_at":"2026-05-18T00:12:58Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06931v1","created_at":"2026-05-18T00:12:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06931","created_at":"2026-05-18T00:12:58Z"},{"alias_kind":"pith_short_12","alias_value":"QIXROM3I52NQ","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QIXROM3I52NQRXEJ","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QIXROM3I","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:02ea90b42f84678468dda493e61fb1ad5ff9ae8bfee01c304e1ecef8b9f9e4e4","target":"graph","created_at":"2026-05-18T00:12:58Z","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"},"paper":{"abstract_excerpt":"Recent work has shown that reinforcement learning (RL) is a promising approach to control dynamical systems described by partial differential equations (PDE). This paper shows how to use RL to tackle more general PDE control problems that have continuous high-dimensional action spaces with spatial relationship among action dimensions. In particular, we propose the concept of action descriptors, which encode regularities among spatially-extended action dimensions and enable the agent to control high-dimensional action PDEs. We provide theoretical evidence suggesting that this approach can be mo","authors_text":"Amir-massoud Farahmand, Daniel Nikovski, Martha White, Piyush Grover, Saleh Nabi, Yangchen Pan","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-13T03:47:12Z","title":"Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06931","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:ca5bc61672b21c93f052dedc8c2cf1c7a1fbc0d0ea5dec99844fbc3f8bc2f6e7","target":"record","created_at":"2026-05-18T00:12:58Z","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":"9d2893ce92bd3bd983dd2fe39e03f3cdf6ab71418d9844f9bbc12cf7583621be","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-13T03:47:12Z","title_canon_sha256":"d7b2ca1f602d53b5369e82efb44706c981ac31b3a339e83307fbf34899d55a05"},"schema_version":"1.0","source":{"id":"1806.06931","kind":"arxiv","version":1}},"canonical_sha256":"822f173368ee9b08dc89ca844d29e7723a89e7c1f64e5206bcb0bff506315ad0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"822f173368ee9b08dc89ca844d29e7723a89e7c1f64e5206bcb0bff506315ad0","first_computed_at":"2026-05-18T00:12:58.030813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:58.030813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YsiHeqDZS8CXS2vptycDaEg0UqsuLXLDjgBG4zahXyHXS12tKhwK6ouVvN33Sdvns/ill0b0z5Rww45NPmg+BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:58.031459Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.06931","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca5bc61672b21c93f052dedc8c2cf1c7a1fbc0d0ea5dec99844fbc3f8bc2f6e7","sha256:02ea90b42f84678468dda493e61fb1ad5ff9ae8bfee01c304e1ecef8b9f9e4e4"],"state_sha256":"00d1ee871157395213b29aa2ed44b18f109d98940f6470421e98097756003d3f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4sez9Ec5Vr8FQqDHiqLYseWb0Zqt0Nx7yuQTeLyORuFQ2IhPTFDyjvA8lIj2pLSY61JFcV9lep2rbPkxgYzJDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T19:39:35.434705Z","bundle_sha256":"a409c9f6e7a7fb48e81ad0ca69693b71cdd9fcbf526c0b2a414bbdc2c10f0e76"}}