{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SNLEYIHSEV5PNNXONRIRMMGURU","short_pith_number":"pith:SNLEYIHS","canonical_record":{"source":{"id":"2303.08271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-03-14T23:22:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8289aab8c9dc3de6e7562cdc741a6727bcadb56139e3926a514f93e72ca21c87","abstract_canon_sha256":"9ac43537c949e480a74f15ed57d51dc107d76be19be81a30d30d0dea91062b44"},"schema_version":"1.0"},"canonical_sha256":"93564c20f2257af6b6ee6c511630d48d2eff2182fd34253312c2e6cc2a6369ee","source":{"kind":"arxiv","id":"2303.08271","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.08271","created_at":"2026-07-05T05:51:30Z"},{"alias_kind":"arxiv_version","alias_value":"2303.08271v1","created_at":"2026-07-05T05:51:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08271","created_at":"2026-07-05T05:51:30Z"},{"alias_kind":"pith_short_12","alias_value":"SNLEYIHSEV5P","created_at":"2026-07-05T05:51:30Z"},{"alias_kind":"pith_short_16","alias_value":"SNLEYIHSEV5PNNXO","created_at":"2026-07-05T05:51:30Z"},{"alias_kind":"pith_short_8","alias_value":"SNLEYIHS","created_at":"2026-07-05T05:51:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SNLEYIHSEV5PNNXONRIRMMGURU","target":"record","payload":{"canonical_record":{"source":{"id":"2303.08271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-03-14T23:22:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8289aab8c9dc3de6e7562cdc741a6727bcadb56139e3926a514f93e72ca21c87","abstract_canon_sha256":"9ac43537c949e480a74f15ed57d51dc107d76be19be81a30d30d0dea91062b44"},"schema_version":"1.0"},"canonical_sha256":"93564c20f2257af6b6ee6c511630d48d2eff2182fd34253312c2e6cc2a6369ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:30.826808Z","signature_b64":"7w5e63zEaY7D8KNYGDbjbnWemqiIoJpTqBHrukexL/2kYjg4vcvnRJtuERVCmoPizw/djql6jy5tcWWjZ2deCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93564c20f2257af6b6ee6c511630d48d2eff2182fd34253312c2e6cc2a6369ee","last_reissued_at":"2026-07-05T05:51:30.826403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:30.826403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.08271","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":"2026-07-05T05:51:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XKe+bn7iTus32VzP7Y3xZSy8mdwnSG/gP+hnsSHNqIHdwS2HjPJKL6w7d7xZir/6V7VochFoWhi6BH8ZAbiYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T16:29:13.621248Z"},"content_sha256":"ec162a783fa086e856bbd010d642f18660976e88483b8b1fd8008cc8f02c7017","schema_version":"1.0","event_id":"sha256:ec162a783fa086e856bbd010d642f18660976e88483b8b1fd8008cc8f02c7017"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SNLEYIHSEV5PNNXONRIRMMGURU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Merlijn Krale, Nils Jansen, Thiago D. Sim\\~ao","submitted_at":"2023-03-14T23:22:32Z","abstract_excerpt":"We study Markov decision processes (MDPs), where agents have direct control over when and how they gather information, as formalized by action-contingent noiselessly observable MDPs (ACNO-MPDs). In these models, actions consist of two components: a control action that affects the environment, and a measurement action that affects what the agent can observe. To solve ACNO-MDPs, we introduce the act-then-measure (ATM) heuristic, which assumes that we can ignore future state uncertainty when choosing control actions. We show how following this heuristic may lead to shorter policy computation time"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08271","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/2303.08271/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":"2026-07-05T05:51:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mqD/dqktUm0Q582qvvNKoRD3on07P4yuATEr9LalPJVqDQhq0kKRM0FnjbDP2kzGgu+D+/Swp4tZx5BVYAd7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T16:29:13.621594Z"},"content_sha256":"8be7f22f8d1a163b931e801fd853ae561c30ec705a14dc79132e7a6d662db17e","schema_version":"1.0","event_id":"sha256:8be7f22f8d1a163b931e801fd853ae561c30ec705a14dc79132e7a6d662db17e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SNLEYIHSEV5PNNXONRIRMMGURU/bundle.json","state_url":"https://pith.science/pith/SNLEYIHSEV5PNNXONRIRMMGURU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SNLEYIHSEV5PNNXONRIRMMGURU/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":"2026-08-11T16:29:13Z","links":{"resolver":"https://pith.science/pith/SNLEYIHSEV5PNNXONRIRMMGURU","bundle":"https://pith.science/pith/SNLEYIHSEV5PNNXONRIRMMGURU/bundle.json","state":"https://pith.science/pith/SNLEYIHSEV5PNNXONRIRMMGURU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SNLEYIHSEV5PNNXONRIRMMGURU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SNLEYIHSEV5PNNXONRIRMMGURU","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":"9ac43537c949e480a74f15ed57d51dc107d76be19be81a30d30d0dea91062b44","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-03-14T23:22:32Z","title_canon_sha256":"8289aab8c9dc3de6e7562cdc741a6727bcadb56139e3926a514f93e72ca21c87"},"schema_version":"1.0","source":{"id":"2303.08271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.08271","created_at":"2026-07-05T05:51:30Z"},{"alias_kind":"arxiv_version","alias_value":"2303.08271v1","created_at":"2026-07-05T05:51:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08271","created_at":"2026-07-05T05:51:30Z"},{"alias_kind":"pith_short_12","alias_value":"SNLEYIHSEV5P","created_at":"2026-07-05T05:51:30Z"},{"alias_kind":"pith_short_16","alias_value":"SNLEYIHSEV5PNNXO","created_at":"2026-07-05T05:51:30Z"},{"alias_kind":"pith_short_8","alias_value":"SNLEYIHS","created_at":"2026-07-05T05:51:30Z"}],"graph_snapshots":[{"event_id":"sha256:8be7f22f8d1a163b931e801fd853ae561c30ec705a14dc79132e7a6d662db17e","target":"graph","created_at":"2026-07-05T05:51:30Z","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/2303.08271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study Markov decision processes (MDPs), where agents have direct control over when and how they gather information, as formalized by action-contingent noiselessly observable MDPs (ACNO-MPDs). In these models, actions consist of two components: a control action that affects the environment, and a measurement action that affects what the agent can observe. To solve ACNO-MDPs, we introduce the act-then-measure (ATM) heuristic, which assumes that we can ignore future state uncertainty when choosing control actions. We show how following this heuristic may lead to shorter policy computation time","authors_text":"Merlijn Krale, Nils Jansen, Thiago D. Sim\\~ao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-03-14T23:22:32Z","title":"Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08271","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:ec162a783fa086e856bbd010d642f18660976e88483b8b1fd8008cc8f02c7017","target":"record","created_at":"2026-07-05T05:51:30Z","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":"9ac43537c949e480a74f15ed57d51dc107d76be19be81a30d30d0dea91062b44","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-03-14T23:22:32Z","title_canon_sha256":"8289aab8c9dc3de6e7562cdc741a6727bcadb56139e3926a514f93e72ca21c87"},"schema_version":"1.0","source":{"id":"2303.08271","kind":"arxiv","version":1}},"canonical_sha256":"93564c20f2257af6b6ee6c511630d48d2eff2182fd34253312c2e6cc2a6369ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93564c20f2257af6b6ee6c511630d48d2eff2182fd34253312c2e6cc2a6369ee","first_computed_at":"2026-07-05T05:51:30.826403Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:51:30.826403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7w5e63zEaY7D8KNYGDbjbnWemqiIoJpTqBHrukexL/2kYjg4vcvnRJtuERVCmoPizw/djql6jy5tcWWjZ2deCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:51:30.826808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.08271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec162a783fa086e856bbd010d642f18660976e88483b8b1fd8008cc8f02c7017","sha256:8be7f22f8d1a163b931e801fd853ae561c30ec705a14dc79132e7a6d662db17e"],"state_sha256":"3245d8a737c5d480c78de649de1eac5a650fe27217df609d48804ee6cb490746"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"545fUtjpOOhwrBIgPAbhddjQs978Hdo0O3RbxfsC/3aJVsnwRiifiYBxOuwgoRUchAmx4yYL7hb24PldQAkpDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T16:29:13.623906Z","bundle_sha256":"47e20a43ceb885c640c735b011441d091d75e4e3434b956f19af6d88e6270894"}}