{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NHVF46SJITXFFG4MBUEMUHBGAK","short_pith_number":"pith:NHVF46SJ","canonical_record":{"source":{"id":"1902.04779","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T08:26:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"63aa3e220256ea3cf525a33ea21694c84c3e07e38aaa74127e607cc75aab9b0e","abstract_canon_sha256":"66f395bf08d9c05ad8e0ab325070a683a1efc05c8ad27daab29b77bb4e78526f"},"schema_version":"1.0"},"canonical_sha256":"69ea5e7a4944ee529b8c0d08ca1c2602bae2b1a5ef742218d1bc10704f7b1677","source":{"kind":"arxiv","id":"1902.04779","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.04779","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"1902.04779v2","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04779","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"NHVF46SJITXF","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NHVF46SJITXFFG4M","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NHVF46SJ","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NHVF46SJITXFFG4MBUEMUHBGAK","target":"record","payload":{"canonical_record":{"source":{"id":"1902.04779","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T08:26:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"63aa3e220256ea3cf525a33ea21694c84c3e07e38aaa74127e607cc75aab9b0e","abstract_canon_sha256":"66f395bf08d9c05ad8e0ab325070a683a1efc05c8ad27daab29b77bb4e78526f"},"schema_version":"1.0"},"canonical_sha256":"69ea5e7a4944ee529b8c0d08ca1c2602bae2b1a5ef742218d1bc10704f7b1677","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:02.476944Z","signature_b64":"M2OjbZ8nzDvcgzG+7y0TXT8jSYpIjMAldDivfxdOFVzzxzYMp2X0TrsyoY0ANi/vB8nXAw+naHyRQ6Ji8gDuBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69ea5e7a4944ee529b8c0d08ca1c2602bae2b1a5ef742218d1bc10704f7b1677","last_reissued_at":"2026-05-17T23:44:02.476438Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:02.476438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.04779","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":"2026-05-17T23:44:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"74uj1QEemkADvubEgfwq3Jwwi/BzoKVnUEvmuRCp1zhPJUtyf4O5knNHUzawY7eDz6BPAp7G9kYoQqG0cWSzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:01:51.619234Z"},"content_sha256":"4aa6d5777a86a92afa33cc30282225daee7fe95c679ecee68a3cca415135f3a2","schema_version":"1.0","event_id":"sha256:4aa6d5777a86a92afa33cc30282225daee7fe95c679ecee68a3cca415135f3a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NHVF46SJITXFFG4MBUEMUHBGAK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sample-Optimal Parametric Q-Learning Using Linearly Additive Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lin F. Yang, Mengdi Wang","submitted_at":"2019-02-13T08:26:47Z","abstract_excerpt":"Consider a Markov decision process (MDP) that admits a set of state-action features, which can linearly express the process's probabilistic transition model. We propose a parametric Q-learning algorithm that finds an approximate-optimal policy using a sample size proportional to the feature dimension $K$ and invariant with respect to the size of the state space. To further improve its sample efficiency, we exploit the monotonicity property and intrinsic noise structure of the Bellman operator, provided the existence of anchor state-actions that imply implicit non-negativity in the feature spac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04779","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":""},"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":"2026-05-17T23:44:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IshMtfyxJ8y8uQD27gFx5Iev/2drxRgL/tmze/hDiwB3sjGMPVc3Ky1KKC4ZFg+hHNhryDdw5LbKZc+qXrFHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T03:01:51.620005Z"},"content_sha256":"bbceed3d58def9db4a87e7aeb2c55476e264decbe9b8c2778ebdf31147d09b0d","schema_version":"1.0","event_id":"sha256:bbceed3d58def9db4a87e7aeb2c55476e264decbe9b8c2778ebdf31147d09b0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NHVF46SJITXFFG4MBUEMUHBGAK/bundle.json","state_url":"https://pith.science/pith/NHVF46SJITXFFG4MBUEMUHBGAK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NHVF46SJITXFFG4MBUEMUHBGAK/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":"2026-05-31T03:01:51Z","links":{"resolver":"https://pith.science/pith/NHVF46SJITXFFG4MBUEMUHBGAK","bundle":"https://pith.science/pith/NHVF46SJITXFFG4MBUEMUHBGAK/bundle.json","state":"https://pith.science/pith/NHVF46SJITXFFG4MBUEMUHBGAK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NHVF46SJITXFFG4MBUEMUHBGAK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NHVF46SJITXFFG4MBUEMUHBGAK","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":"66f395bf08d9c05ad8e0ab325070a683a1efc05c8ad27daab29b77bb4e78526f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T08:26:47Z","title_canon_sha256":"63aa3e220256ea3cf525a33ea21694c84c3e07e38aaa74127e607cc75aab9b0e"},"schema_version":"1.0","source":{"id":"1902.04779","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.04779","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"arxiv_version","alias_value":"1902.04779v2","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04779","created_at":"2026-05-17T23:44:02Z"},{"alias_kind":"pith_short_12","alias_value":"NHVF46SJITXF","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NHVF46SJITXFFG4M","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NHVF46SJ","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:bbceed3d58def9db4a87e7aeb2c55476e264decbe9b8c2778ebdf31147d09b0d","target":"graph","created_at":"2026-05-17T23:44:02Z","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":"Consider a Markov decision process (MDP) that admits a set of state-action features, which can linearly express the process's probabilistic transition model. We propose a parametric Q-learning algorithm that finds an approximate-optimal policy using a sample size proportional to the feature dimension $K$ and invariant with respect to the size of the state space. To further improve its sample efficiency, we exploit the monotonicity property and intrinsic noise structure of the Bellman operator, provided the existence of anchor state-actions that imply implicit non-negativity in the feature spac","authors_text":"Lin F. Yang, Mengdi Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T08:26:47Z","title":"Sample-Optimal Parametric Q-Learning Using Linearly Additive Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04779","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":"sha256:4aa6d5777a86a92afa33cc30282225daee7fe95c679ecee68a3cca415135f3a2","target":"record","created_at":"2026-05-17T23:44:02Z","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":"66f395bf08d9c05ad8e0ab325070a683a1efc05c8ad27daab29b77bb4e78526f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T08:26:47Z","title_canon_sha256":"63aa3e220256ea3cf525a33ea21694c84c3e07e38aaa74127e607cc75aab9b0e"},"schema_version":"1.0","source":{"id":"1902.04779","kind":"arxiv","version":2}},"canonical_sha256":"69ea5e7a4944ee529b8c0d08ca1c2602bae2b1a5ef742218d1bc10704f7b1677","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69ea5e7a4944ee529b8c0d08ca1c2602bae2b1a5ef742218d1bc10704f7b1677","first_computed_at":"2026-05-17T23:44:02.476438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:02.476438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M2OjbZ8nzDvcgzG+7y0TXT8jSYpIjMAldDivfxdOFVzzxzYMp2X0TrsyoY0ANi/vB8nXAw+naHyRQ6Ji8gDuBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:02.476944Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.04779","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4aa6d5777a86a92afa33cc30282225daee7fe95c679ecee68a3cca415135f3a2","sha256:bbceed3d58def9db4a87e7aeb2c55476e264decbe9b8c2778ebdf31147d09b0d"],"state_sha256":"986a07810cfc09b26eaa72c3d1f6abdeb314a1cfbcce4ae5e6336d4872a45a8c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qufcygegh5SIwBFkZlGfDKlAO14SNrIo+KjJyXNk2q5WaeJrO4FhT4sk45f72lgu6sOxzOEB7pE6/PXw0+ucBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T03:01:51.623147Z","bundle_sha256":"d6de34bbd0b3b290075c06b516761b1d5e341b867f45e169c5c34cf18ab0c16c"}}