{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:557XDQL3ZX4W6TYYMER3WZLMM2","short_pith_number":"pith:557XDQL3","canonical_record":{"source":{"id":"2206.02887","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T20:25:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8821fbde070b43d82f5963d3d4945edff8bed503dd9f534eda1e65b18e2cf2be","abstract_canon_sha256":"cb7ab4279d1afa5f77f702070f3c31025042e63fd7c0eed14eede64525e5ddb8"},"schema_version":"1.0"},"canonical_sha256":"ef7f71c17bcdf96f4f186123bb656c66b262e561214e642e94e8ec1391a5aec5","source":{"kind":"arxiv","id":"2206.02887","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02887","created_at":"2026-07-05T05:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02887v2","created_at":"2026-07-05T05:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02887","created_at":"2026-07-05T05:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"557XDQL3ZX4W","created_at":"2026-07-05T05:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"557XDQL3ZX4W6TYY","created_at":"2026-07-05T05:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"557XDQL3","created_at":"2026-07-05T05:03:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:557XDQL3ZX4W6TYYMER3WZLMM2","target":"record","payload":{"canonical_record":{"source":{"id":"2206.02887","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T20:25:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8821fbde070b43d82f5963d3d4945edff8bed503dd9f534eda1e65b18e2cf2be","abstract_canon_sha256":"cb7ab4279d1afa5f77f702070f3c31025042e63fd7c0eed14eede64525e5ddb8"},"schema_version":"1.0"},"canonical_sha256":"ef7f71c17bcdf96f4f186123bb656c66b262e561214e642e94e8ec1391a5aec5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:01.526022Z","signature_b64":"O2vhM8+RKZDUlI3YAYxk+LHrM2v3iIRacXQeaJWPl598Y03W+9wttgRtp7exULoubLy/IR9V5kXJU/bQJA0BDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef7f71c17bcdf96f4f186123bb656c66b262e561214e642e94e8ec1391a5aec5","last_reissued_at":"2026-07-05T05:03:01.525617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:01.525617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.02887","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hUIG2MK1T6iNcLMvehPhl25Q5XTBvA2fmx1QzE81NVk3RIMrQc1hGdAkDUfbW3Yu2TzjvMKN9mUPAXB/Y40nBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:30:54.214931Z"},"content_sha256":"ff257994c495287e435869b3a6765b8fc38a1d140dd5dfca216a81ba7067b204","schema_version":"1.0","event_id":"sha256:ff257994c495287e435869b3a6765b8fc38a1d140dd5dfca216a81ba7067b204"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:557XDQL3ZX4W6TYYMER3WZLMM2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mengdi Wang, Minshuo Chen, Tuo Zhao, Xiang Ji","submitted_at":"2022-06-06T20:25:20Z","abstract_excerpt":"We consider the off-policy evaluation problem of reinforcement learning using deep convolutional neural networks. We analyze the deep fitted Q-evaluation method for estimating the expected cumulative reward of a target policy, when the data are generated from an unknown behavior policy. We show that, by choosing network size appropriately, one can leverage any low-dimensional manifold structure in the Markov decision process and obtain a sample-efficient estimator without suffering from the curse of high data ambient dimensionality. Specifically, we establish a sharp error bound for fitted Q-e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02887","kind":"arxiv","version":2},"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/2206.02887/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":"2026-07-05T05:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yWXZlSSRVci5pbMDCnHh4+iID5RUqrn0rOXwu2yrkOuwq/VRHXzwZetyZxpZd2c14F1mR1N2tYG3HQ8MzYdZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:30:54.215334Z"},"content_sha256":"091c6d0650c4c3e16260705f8fb7544f966769529a13787bb9137e5409f06d43","schema_version":"1.0","event_id":"sha256:091c6d0650c4c3e16260705f8fb7544f966769529a13787bb9137e5409f06d43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/557XDQL3ZX4W6TYYMER3WZLMM2/bundle.json","state_url":"https://pith.science/pith/557XDQL3ZX4W6TYYMER3WZLMM2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/557XDQL3ZX4W6TYYMER3WZLMM2/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":"2026-07-07T13:30:54Z","links":{"resolver":"https://pith.science/pith/557XDQL3ZX4W6TYYMER3WZLMM2","bundle":"https://pith.science/pith/557XDQL3ZX4W6TYYMER3WZLMM2/bundle.json","state":"https://pith.science/pith/557XDQL3ZX4W6TYYMER3WZLMM2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/557XDQL3ZX4W6TYYMER3WZLMM2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:557XDQL3ZX4W6TYYMER3WZLMM2","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":"cb7ab4279d1afa5f77f702070f3c31025042e63fd7c0eed14eede64525e5ddb8","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T20:25:20Z","title_canon_sha256":"8821fbde070b43d82f5963d3d4945edff8bed503dd9f534eda1e65b18e2cf2be"},"schema_version":"1.0","source":{"id":"2206.02887","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.02887","created_at":"2026-07-05T05:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2206.02887v2","created_at":"2026-07-05T05:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02887","created_at":"2026-07-05T05:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"557XDQL3ZX4W","created_at":"2026-07-05T05:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"557XDQL3ZX4W6TYY","created_at":"2026-07-05T05:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"557XDQL3","created_at":"2026-07-05T05:03:01Z"}],"graph_snapshots":[{"event_id":"sha256:091c6d0650c4c3e16260705f8fb7544f966769529a13787bb9137e5409f06d43","target":"graph","created_at":"2026-07-05T05:03:01Z","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/2206.02887/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the off-policy evaluation problem of reinforcement learning using deep convolutional neural networks. We analyze the deep fitted Q-evaluation method for estimating the expected cumulative reward of a target policy, when the data are generated from an unknown behavior policy. We show that, by choosing network size appropriately, one can leverage any low-dimensional manifold structure in the Markov decision process and obtain a sample-efficient estimator without suffering from the curse of high data ambient dimensionality. Specifically, we establish a sharp error bound for fitted Q-e","authors_text":"Mengdi Wang, Minshuo Chen, Tuo Zhao, Xiang Ji","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T20:25:20Z","title":"Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02887","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:ff257994c495287e435869b3a6765b8fc38a1d140dd5dfca216a81ba7067b204","target":"record","created_at":"2026-07-05T05:03:01Z","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":"cb7ab4279d1afa5f77f702070f3c31025042e63fd7c0eed14eede64525e5ddb8","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T20:25:20Z","title_canon_sha256":"8821fbde070b43d82f5963d3d4945edff8bed503dd9f534eda1e65b18e2cf2be"},"schema_version":"1.0","source":{"id":"2206.02887","kind":"arxiv","version":2}},"canonical_sha256":"ef7f71c17bcdf96f4f186123bb656c66b262e561214e642e94e8ec1391a5aec5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef7f71c17bcdf96f4f186123bb656c66b262e561214e642e94e8ec1391a5aec5","first_computed_at":"2026-07-05T05:03:01.525617Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:01.525617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O2vhM8+RKZDUlI3YAYxk+LHrM2v3iIRacXQeaJWPl598Y03W+9wttgRtp7exULoubLy/IR9V5kXJU/bQJA0BDg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:01.526022Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.02887","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff257994c495287e435869b3a6765b8fc38a1d140dd5dfca216a81ba7067b204","sha256:091c6d0650c4c3e16260705f8fb7544f966769529a13787bb9137e5409f06d43"],"state_sha256":"e9fcce51f796ff5dceab2ed5cd78e8c619fc7854179a80de0dd3a9836005a43d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vH3gOZFKYb96MK8ERhCdg5zYXMQ/CcuQYRkqIMTM/ruCcH4re8CI8XasDXbNlTMAcclvnXQJMVShGoH5lqBFAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:30:54.217343Z","bundle_sha256":"73f00d05aacc37038aa05aaa7bc77ab95f8c864345913e06b2cd5737a2bf9731"}}