{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IQXX7PPSD4SZ7OGZQRXVCQEPNG","short_pith_number":"pith:IQXX7PPS","canonical_record":{"source":{"id":"2605.28675","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T16:08:56Z","cross_cats_sorted":[],"title_canon_sha256":"542c5197a9e1f48a0c2fcd5b7d3dfdef648531b2ba7cde3baad76987a16b5a53","abstract_canon_sha256":"43d6d86b709022c2a241fb54385e69488249a42b733920c64b54293837c15d83"},"schema_version":"1.0"},"canonical_sha256":"442f7fbdf21f259fb8d9846f51408f69b976376c7a7f125d8bd1e0ce14e7c504","source":{"kind":"arxiv","id":"2605.28675","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28675","created_at":"2026-05-28T02:04:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28675v1","created_at":"2026-05-28T02:04:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28675","created_at":"2026-05-28T02:04:59Z"},{"alias_kind":"pith_short_12","alias_value":"IQXX7PPSD4SZ","created_at":"2026-05-28T02:04:59Z"},{"alias_kind":"pith_short_16","alias_value":"IQXX7PPSD4SZ7OGZ","created_at":"2026-05-28T02:04:59Z"},{"alias_kind":"pith_short_8","alias_value":"IQXX7PPS","created_at":"2026-05-28T02:04:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IQXX7PPSD4SZ7OGZQRXVCQEPNG","target":"record","payload":{"canonical_record":{"source":{"id":"2605.28675","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T16:08:56Z","cross_cats_sorted":[],"title_canon_sha256":"542c5197a9e1f48a0c2fcd5b7d3dfdef648531b2ba7cde3baad76987a16b5a53","abstract_canon_sha256":"43d6d86b709022c2a241fb54385e69488249a42b733920c64b54293837c15d83"},"schema_version":"1.0"},"canonical_sha256":"442f7fbdf21f259fb8d9846f51408f69b976376c7a7f125d8bd1e0ce14e7c504","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:59.555705Z","signature_b64":"HrpubWPdfkSN2vMCN/uyZ7RqH3C//836ZRsxdBhcuAldf+HBcwbZLPE6aSurFDrQuKqW8MLIEFXkSl9Nrn75BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"442f7fbdf21f259fb8d9846f51408f69b976376c7a7f125d8bd1e0ce14e7c504","last_reissued_at":"2026-05-28T02:04:59.555241Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:59.555241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.28675","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":"2026-05-28T02:04:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3/3UuiOXPlChbXGhnryFjapIFVHotwzsFl00T66zglp9+V2B9Ly41x2+lhNcYGWgMUwujnlUeTBtsvC9sxHACQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T18:01:42.351476Z"},"content_sha256":"6c3bf309c417e26d2d4dfaa94acbe32549e8a634ca37c71be910ba875ef82195","schema_version":"1.0","event_id":"sha256:6c3bf309c417e26d2d4dfaa94acbe32549e8a634ca37c71be910ba875ef82195"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IQXX7PPSD4SZ7OGZQRXVCQEPNG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Data Acquisition for Reinforcement Learning: A Large Deviations Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Enlu Zhou, Jian-qiang Hu, Mingjie Hu","submitted_at":"2026-05-27T16:08:56Z","abstract_excerpt":"Data acquisition efficiency is a central challenge in deploying reinforcement learning in business and healthcare operations, where interactions are costly, slow, and often involve humans in the loop. This paper develops a unified large deviations framework for data acquisition in infinite-horizon reinforcement learning. We introduce the exponential decay rate of the policy-selection error probability as a principled efficiency metric and derive a variational characterization of this rate via large deviations theory for Markov chains, yielding a nested optimization problem. Based on this chara"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28675","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/2605.28675/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":"2026-05-28T02:04:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vkVc6hQ6wcdaDQ+NGq5xCYewmgkznu2uJCCtFbzs6ihDEye+pDlKy/vTCza2XIEThpTxlxJcaVLKX4lBz5ECDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T18:01:42.351868Z"},"content_sha256":"94b376e163ed286a57e625cdc33d2f24f3cf31db66b0b06b177c108860c716e5","schema_version":"1.0","event_id":"sha256:94b376e163ed286a57e625cdc33d2f24f3cf31db66b0b06b177c108860c716e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IQXX7PPSD4SZ7OGZQRXVCQEPNG/bundle.json","state_url":"https://pith.science/pith/IQXX7PPSD4SZ7OGZQRXVCQEPNG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IQXX7PPSD4SZ7OGZQRXVCQEPNG/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":"2026-06-04T18:01:42Z","links":{"resolver":"https://pith.science/pith/IQXX7PPSD4SZ7OGZQRXVCQEPNG","bundle":"https://pith.science/pith/IQXX7PPSD4SZ7OGZQRXVCQEPNG/bundle.json","state":"https://pith.science/pith/IQXX7PPSD4SZ7OGZQRXVCQEPNG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IQXX7PPSD4SZ7OGZQRXVCQEPNG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IQXX7PPSD4SZ7OGZQRXVCQEPNG","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":"43d6d86b709022c2a241fb54385e69488249a42b733920c64b54293837c15d83","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T16:08:56Z","title_canon_sha256":"542c5197a9e1f48a0c2fcd5b7d3dfdef648531b2ba7cde3baad76987a16b5a53"},"schema_version":"1.0","source":{"id":"2605.28675","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28675","created_at":"2026-05-28T02:04:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28675v1","created_at":"2026-05-28T02:04:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28675","created_at":"2026-05-28T02:04:59Z"},{"alias_kind":"pith_short_12","alias_value":"IQXX7PPSD4SZ","created_at":"2026-05-28T02:04:59Z"},{"alias_kind":"pith_short_16","alias_value":"IQXX7PPSD4SZ7OGZ","created_at":"2026-05-28T02:04:59Z"},{"alias_kind":"pith_short_8","alias_value":"IQXX7PPS","created_at":"2026-05-28T02:04:59Z"}],"graph_snapshots":[{"event_id":"sha256:94b376e163ed286a57e625cdc33d2f24f3cf31db66b0b06b177c108860c716e5","target":"graph","created_at":"2026-05-28T02:04:59Z","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/2605.28675/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data acquisition efficiency is a central challenge in deploying reinforcement learning in business and healthcare operations, where interactions are costly, slow, and often involve humans in the loop. This paper develops a unified large deviations framework for data acquisition in infinite-horizon reinforcement learning. We introduce the exponential decay rate of the policy-selection error probability as a principled efficiency metric and derive a variational characterization of this rate via large deviations theory for Markov chains, yielding a nested optimization problem. Based on this chara","authors_text":"Enlu Zhou, Jian-qiang Hu, Mingjie Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T16:08:56Z","title":"Optimal Data Acquisition for Reinforcement Learning: A Large Deviations Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28675","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":"sha256:6c3bf309c417e26d2d4dfaa94acbe32549e8a634ca37c71be910ba875ef82195","target":"record","created_at":"2026-05-28T02:04:59Z","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":"43d6d86b709022c2a241fb54385e69488249a42b733920c64b54293837c15d83","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T16:08:56Z","title_canon_sha256":"542c5197a9e1f48a0c2fcd5b7d3dfdef648531b2ba7cde3baad76987a16b5a53"},"schema_version":"1.0","source":{"id":"2605.28675","kind":"arxiv","version":1}},"canonical_sha256":"442f7fbdf21f259fb8d9846f51408f69b976376c7a7f125d8bd1e0ce14e7c504","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"442f7fbdf21f259fb8d9846f51408f69b976376c7a7f125d8bd1e0ce14e7c504","first_computed_at":"2026-05-28T02:04:59.555241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:04:59.555241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HrpubWPdfkSN2vMCN/uyZ7RqH3C//836ZRsxdBhcuAldf+HBcwbZLPE6aSurFDrQuKqW8MLIEFXkSl9Nrn75BA==","signature_status":"signed_v1","signed_at":"2026-05-28T02:04:59.555705Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28675","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c3bf309c417e26d2d4dfaa94acbe32549e8a634ca37c71be910ba875ef82195","sha256:94b376e163ed286a57e625cdc33d2f24f3cf31db66b0b06b177c108860c716e5"],"state_sha256":"814362f364deadb85c697fa88f7637b96c9a10a3f12c00fdd51393b56947008c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7B0Wzd4y9NvFwolPXQ7+OCNWVypIWL+ccn77queQHvPOcAGIitcGr0oA/gX7mcdMTqbb2UPK6LwhugkouPP8Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T18:01:42.354013Z","bundle_sha256":"fcea5896465831f146245d25d9e31e4292f59cd1cb913b97cb0f5a642327575b"}}