{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WQ4FZLMHZXO7LAIG6ACJ5Y7TTY","short_pith_number":"pith:WQ4FZLMH","canonical_record":{"source":{"id":"2501.16243","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2025-01-27T17:38:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5d7e6f60d46ee2680a7d4e1cf9fd0eed36f6f4a2d119256a80ba4005729bea6b","abstract_canon_sha256":"e4149fc409b5cc90f987f839f9db8d45542e4669c264a0027db463a269484bd6"},"schema_version":"1.0"},"canonical_sha256":"b4385cad87cdddf58106f0049ee3f39e1dfa55e9924a59b4c18cb3b21d81e469","source":{"kind":"arxiv","id":"2501.16243","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16243","created_at":"2026-07-05T11:29:54Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16243v3","created_at":"2026-07-05T11:29:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16243","created_at":"2026-07-05T11:29:54Z"},{"alias_kind":"pith_short_12","alias_value":"WQ4FZLMHZXO7","created_at":"2026-07-05T11:29:54Z"},{"alias_kind":"pith_short_16","alias_value":"WQ4FZLMHZXO7LAIG","created_at":"2026-07-05T11:29:54Z"},{"alias_kind":"pith_short_8","alias_value":"WQ4FZLMH","created_at":"2026-07-05T11:29:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WQ4FZLMHZXO7LAIG6ACJ5Y7TTY","target":"record","payload":{"canonical_record":{"source":{"id":"2501.16243","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2025-01-27T17:38:30Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5d7e6f60d46ee2680a7d4e1cf9fd0eed36f6f4a2d119256a80ba4005729bea6b","abstract_canon_sha256":"e4149fc409b5cc90f987f839f9db8d45542e4669c264a0027db463a269484bd6"},"schema_version":"1.0"},"canonical_sha256":"b4385cad87cdddf58106f0049ee3f39e1dfa55e9924a59b4c18cb3b21d81e469","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:54.596975Z","signature_b64":"PvyRhEeE/t5MCNv+8HoR615A0FEpWNKaGnojUS7QUStabKHyMuXZE6VbnB1S4mKbwIUv33y98jum7KC2ZE+rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4385cad87cdddf58106f0049ee3f39e1dfa55e9924a59b4c18cb3b21d81e469","last_reissued_at":"2026-07-05T11:29:54.596593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:54.596593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.16243","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:29:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0WwOHOGNTHfvHrC8DxrRPZQpbnFEIOzFRmIJKa1g+2C9s3/1oPMm54jjW2b2EhbGFAzXwEldyUk/meW5Zrc6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T12:56:20.344838Z"},"content_sha256":"38689a5f75d9888bb6630c7e7e65f4ef8e18e47df89bef233568f81046514e26","schema_version":"1.0","event_id":"sha256:38689a5f75d9888bb6630c7e7e65f4ef8e18e47df89bef233568f81046514e26"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WQ4FZLMHZXO7LAIG6ACJ5Y7TTY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating Quantum Reinforcement Learning with a Quantum Natural Policy Gradient Based Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"quant-ph","authors_text":"Vaneet Aggarwal, Yang Xu","submitted_at":"2025-01-27T17:38:30Z","abstract_excerpt":"We address the problem of quantum reinforcement learning (QRL) under model-free settings with quantum oracle access to the Markov Decision Process (MDP). This paper introduces a Quantum Natural Policy Gradient (QNPG) algorithm, which replaces the random sampling used in classical Natural Policy Gradient (NPG) estimators with a deterministic gradient estimation approach, enabling seamless integration into quantum systems. While this modification introduces a bounded bias in the estimator, the bias decays exponentially with increasing truncation levels. This paper demonstrates that the proposed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16243","kind":"arxiv","version":3},"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/2501.16243/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":"2026-07-05T11:29:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DrqCH8sUoLhus7UTIRjpb2MKZcraJU7sxsd3EH1vWmshp7WzlXe8e4KUpW/PIQQRtVC3XR+/3jd1Fu6SQCmABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T12:56:20.345429Z"},"content_sha256":"7994628639c681059cfaf37a842cafb28c09ff0e98732b24c5fa52386eb8a1b0","schema_version":"1.0","event_id":"sha256:7994628639c681059cfaf37a842cafb28c09ff0e98732b24c5fa52386eb8a1b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WQ4FZLMHZXO7LAIG6ACJ5Y7TTY/bundle.json","state_url":"https://pith.science/pith/WQ4FZLMHZXO7LAIG6ACJ5Y7TTY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WQ4FZLMHZXO7LAIG6ACJ5Y7TTY/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":"2026-08-14T12:56:20Z","links":{"resolver":"https://pith.science/pith/WQ4FZLMHZXO7LAIG6ACJ5Y7TTY","bundle":"https://pith.science/pith/WQ4FZLMHZXO7LAIG6ACJ5Y7TTY/bundle.json","state":"https://pith.science/pith/WQ4FZLMHZXO7LAIG6ACJ5Y7TTY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WQ4FZLMHZXO7LAIG6ACJ5Y7TTY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WQ4FZLMHZXO7LAIG6ACJ5Y7TTY","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":"e4149fc409b5cc90f987f839f9db8d45542e4669c264a0027db463a269484bd6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2025-01-27T17:38:30Z","title_canon_sha256":"5d7e6f60d46ee2680a7d4e1cf9fd0eed36f6f4a2d119256a80ba4005729bea6b"},"schema_version":"1.0","source":{"id":"2501.16243","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.16243","created_at":"2026-07-05T11:29:54Z"},{"alias_kind":"arxiv_version","alias_value":"2501.16243v3","created_at":"2026-07-05T11:29:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16243","created_at":"2026-07-05T11:29:54Z"},{"alias_kind":"pith_short_12","alias_value":"WQ4FZLMHZXO7","created_at":"2026-07-05T11:29:54Z"},{"alias_kind":"pith_short_16","alias_value":"WQ4FZLMHZXO7LAIG","created_at":"2026-07-05T11:29:54Z"},{"alias_kind":"pith_short_8","alias_value":"WQ4FZLMH","created_at":"2026-07-05T11:29:54Z"}],"graph_snapshots":[{"event_id":"sha256:7994628639c681059cfaf37a842cafb28c09ff0e98732b24c5fa52386eb8a1b0","target":"graph","created_at":"2026-07-05T11:29:54Z","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/2501.16243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We address the problem of quantum reinforcement learning (QRL) under model-free settings with quantum oracle access to the Markov Decision Process (MDP). This paper introduces a Quantum Natural Policy Gradient (QNPG) algorithm, which replaces the random sampling used in classical Natural Policy Gradient (NPG) estimators with a deterministic gradient estimation approach, enabling seamless integration into quantum systems. While this modification introduces a bounded bias in the estimator, the bias decays exponentially with increasing truncation levels. This paper demonstrates that the proposed ","authors_text":"Vaneet Aggarwal, Yang Xu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2025-01-27T17:38:30Z","title":"Accelerating Quantum Reinforcement Learning with a Quantum Natural Policy Gradient Based Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16243","kind":"arxiv","version":3},"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":"sha256:38689a5f75d9888bb6630c7e7e65f4ef8e18e47df89bef233568f81046514e26","target":"record","created_at":"2026-07-05T11:29:54Z","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":"e4149fc409b5cc90f987f839f9db8d45542e4669c264a0027db463a269484bd6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2025-01-27T17:38:30Z","title_canon_sha256":"5d7e6f60d46ee2680a7d4e1cf9fd0eed36f6f4a2d119256a80ba4005729bea6b"},"schema_version":"1.0","source":{"id":"2501.16243","kind":"arxiv","version":3}},"canonical_sha256":"b4385cad87cdddf58106f0049ee3f39e1dfa55e9924a59b4c18cb3b21d81e469","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4385cad87cdddf58106f0049ee3f39e1dfa55e9924a59b4c18cb3b21d81e469","first_computed_at":"2026-07-05T11:29:54.596593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:54.596593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PvyRhEeE/t5MCNv+8HoR615A0FEpWNKaGnojUS7QUStabKHyMuXZE6VbnB1S4mKbwIUv33y98jum7KC2ZE+rDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:54.596975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.16243","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:38689a5f75d9888bb6630c7e7e65f4ef8e18e47df89bef233568f81046514e26","sha256:7994628639c681059cfaf37a842cafb28c09ff0e98732b24c5fa52386eb8a1b0"],"state_sha256":"426488ee24d85a0fab95a64a38bfa8ef97f7f0aa75dd600339810878186fd898"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d2daYEQwa35WsH5ttOSj+kW9Kv3/WhUt1INvmnpiQaeWUkDsJ4KiM3OgJdIAZyfhJRzRogKXLd6M4Aneznj3Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T12:56:20.349424Z","bundle_sha256":"2ced9817eb6a1d28d65d03bf444fc5bb4b2f8303a3abc3886efe026a7e4eb24d"}}