{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:T6UWNQTS4PCASEAHGIHWKNLAIJ","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":"b21a87e1908fa1cf8adb2238d92e4502b4ed301b32a6486b244db7f200a7fcf1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T16:48:57Z","title_canon_sha256":"a7e944a2b500a30bb9356f2daff688ec6289eef021f691ad2eab9490c99503e9"},"schema_version":"1.0","source":{"id":"2112.07535","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07535","created_at":"2026-07-05T04:12:17Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07535v2","created_at":"2026-07-05T04:12:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07535","created_at":"2026-07-05T04:12:17Z"},{"alias_kind":"pith_short_12","alias_value":"T6UWNQTS4PCA","created_at":"2026-07-05T04:12:17Z"},{"alias_kind":"pith_short_16","alias_value":"T6UWNQTS4PCASEAH","created_at":"2026-07-05T04:12:17Z"},{"alias_kind":"pith_short_8","alias_value":"T6UWNQTS","created_at":"2026-07-05T04:12:17Z"}],"graph_snapshots":[{"event_id":"sha256:15cdf1558c50ad8a21fe1ab2439996369ea8da5bc82083e5e58aa8fd67b3d5ce","target":"graph","created_at":"2026-07-05T04:12:17Z","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/2112.07535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of reinforcement learning (RL) in scientific applications, such as materials design and automated chemistry, is increasing. A major challenge, however, lies in fact that measuring the state of the system is often costly and time consuming in scientific applications, whereas policy learning with RL requires a measurement after each time step. In this work, we make the measurement costs explicit in the form of a costed reward and propose a framework that enables off-the-shelf deep RL algorithms to learn a policy for both selecting actions and determining whether or not to measure the cur","authors_text":"Andriy Drozdyuk, Colin Bellinger, Isaac Tamblyn, Mark Crowley","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T16:48:57Z","title":"Scientific Discovery and the Cost of Measurement -- Balancing Information and Cost in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07535","kind":"arxiv","version":2},"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":"sha256:73d7556d8b734bf63e9dcbec332f355c8408f40f02fcd394e01033406823d4c7","target":"record","created_at":"2026-07-05T04:12:17Z","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":"b21a87e1908fa1cf8adb2238d92e4502b4ed301b32a6486b244db7f200a7fcf1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-14T16:48:57Z","title_canon_sha256":"a7e944a2b500a30bb9356f2daff688ec6289eef021f691ad2eab9490c99503e9"},"schema_version":"1.0","source":{"id":"2112.07535","kind":"arxiv","version":2}},"canonical_sha256":"9fa966c272e3c4091007320f65356042465f6c7a533ee8bcd7ef8b515704c923","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fa966c272e3c4091007320f65356042465f6c7a533ee8bcd7ef8b515704c923","first_computed_at":"2026-07-05T04:12:17.338390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:12:17.338390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LiC+FCTT7i2IGFZf+owCkGV9WwA9abb1iZCJ50xuN1yAGESQJoW8EK2tTSpPw/4ft/wlu959vT4rvZQSSSAdCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:12:17.338869Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.07535","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73d7556d8b734bf63e9dcbec332f355c8408f40f02fcd394e01033406823d4c7","sha256:15cdf1558c50ad8a21fe1ab2439996369ea8da5bc82083e5e58aa8fd67b3d5ce"],"state_sha256":"5c9382cec9e38000753b21b147c37d2272ef38e7eda16e09cf69501077d37157"}