{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OZHBN32RHSQFT5F7AXY2MYZDPE","short_pith_number":"pith:OZHBN32R","canonical_record":{"source":{"id":"2203.10591","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-03-20T16:14:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"554b33bd5b55706bd118af4f8f2cee1b41be84ad67166ffebb233e5fd9a6034d","abstract_canon_sha256":"625ce9b318fe2ef7ba83652557f13ccd29f6733060480d6199d8fbb792c41073"},"schema_version":"1.0"},"canonical_sha256":"764e16ef513ca059f4bf05f1a66323791e641be8ba56c6fbfe74bc109783c75a","source":{"kind":"arxiv","id":"2203.10591","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10591","created_at":"2026-07-05T05:33:09Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10591v3","created_at":"2026-07-05T05:33:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10591","created_at":"2026-07-05T05:33:09Z"},{"alias_kind":"pith_short_12","alias_value":"OZHBN32RHSQF","created_at":"2026-07-05T05:33:09Z"},{"alias_kind":"pith_short_16","alias_value":"OZHBN32RHSQFT5F7","created_at":"2026-07-05T05:33:09Z"},{"alias_kind":"pith_short_8","alias_value":"OZHBN32R","created_at":"2026-07-05T05:33:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OZHBN32RHSQFT5F7AXY2MYZDPE","target":"record","payload":{"canonical_record":{"source":{"id":"2203.10591","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-03-20T16:14:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"554b33bd5b55706bd118af4f8f2cee1b41be84ad67166ffebb233e5fd9a6034d","abstract_canon_sha256":"625ce9b318fe2ef7ba83652557f13ccd29f6733060480d6199d8fbb792c41073"},"schema_version":"1.0"},"canonical_sha256":"764e16ef513ca059f4bf05f1a66323791e641be8ba56c6fbfe74bc109783c75a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:09.302322Z","signature_b64":"d1kF3ZDwK410CZ4lftfAey+i35wDqjaZ6VlP9uydgFs+fNg0odWObM9kyn8YRcdDEavcOorB3ObWQoVlHutmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"764e16ef513ca059f4bf05f1a66323791e641be8ba56c6fbfe74bc109783c75a","last_reissued_at":"2026-07-05T05:33:09.301804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:09.301804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.10591","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":"2026-07-05T05:33:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TWq3eHf1N1kVuqonjUaOVLgQr0uRLlqzY3cGGOP1SnXhJj1Ae2L5kPacLfoBf51XG5HgSF1vvHAGfCpfbZgXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T14:21:00.168853Z"},"content_sha256":"98d701054f45f5f719a5467e5219cbd6cbb0b751b907e32f37576a7930788863","schema_version":"1.0","event_id":"sha256:98d701054f45f5f719a5467e5219cbd6cbb0b751b907e32f37576a7930788863"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OZHBN32RHSQFT5F7AXY2MYZDPE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Gradients using Variational Quantum Circuits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Andr\\'e Sequeira, Luis Paulo Santos, Lu\\'is Soares Barbosa","submitted_at":"2022-03-20T16:14:49Z","abstract_excerpt":"Variational Quantum Circuits are being used as versatile Quantum Machine Learning models. Some empirical results exhibit an advantage in supervised and generative learning tasks. However, when applied to Reinforcement Learning, less is known. In this work, we considered a Variational Quantum Circuit composed of a low-depth hardware-efficient ansatz as the parameterized policy of a Reinforcement Learning agent. We show that an $\\epsilon$-approximation of the policy gradient can be obtained using a logarithmic number of samples concerning the total number of parameters. We empirically verify tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10591","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/2203.10591/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":"2026-07-05T05:33:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LQ4Pmemt0Hlnr6Q8UwBndHFyart3bFmCUXA97AIWnDB6gxM/dSTbcIQxpqnDcAqjNLQKfHDjBbwvuA2MR0JBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T14:21:00.169237Z"},"content_sha256":"473630967bf00c241f50325301f7408cc43c7ee64f1a290b5fc5b257cc1329f6","schema_version":"1.0","event_id":"sha256:473630967bf00c241f50325301f7408cc43c7ee64f1a290b5fc5b257cc1329f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OZHBN32RHSQFT5F7AXY2MYZDPE/bundle.json","state_url":"https://pith.science/pith/OZHBN32RHSQFT5F7AXY2MYZDPE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OZHBN32RHSQFT5F7AXY2MYZDPE/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":"2026-07-19T14:21:00Z","links":{"resolver":"https://pith.science/pith/OZHBN32RHSQFT5F7AXY2MYZDPE","bundle":"https://pith.science/pith/OZHBN32RHSQFT5F7AXY2MYZDPE/bundle.json","state":"https://pith.science/pith/OZHBN32RHSQFT5F7AXY2MYZDPE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OZHBN32RHSQFT5F7AXY2MYZDPE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OZHBN32RHSQFT5F7AXY2MYZDPE","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":"625ce9b318fe2ef7ba83652557f13ccd29f6733060480d6199d8fbb792c41073","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-03-20T16:14:49Z","title_canon_sha256":"554b33bd5b55706bd118af4f8f2cee1b41be84ad67166ffebb233e5fd9a6034d"},"schema_version":"1.0","source":{"id":"2203.10591","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.10591","created_at":"2026-07-05T05:33:09Z"},{"alias_kind":"arxiv_version","alias_value":"2203.10591v3","created_at":"2026-07-05T05:33:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10591","created_at":"2026-07-05T05:33:09Z"},{"alias_kind":"pith_short_12","alias_value":"OZHBN32RHSQF","created_at":"2026-07-05T05:33:09Z"},{"alias_kind":"pith_short_16","alias_value":"OZHBN32RHSQFT5F7","created_at":"2026-07-05T05:33:09Z"},{"alias_kind":"pith_short_8","alias_value":"OZHBN32R","created_at":"2026-07-05T05:33:09Z"}],"graph_snapshots":[{"event_id":"sha256:473630967bf00c241f50325301f7408cc43c7ee64f1a290b5fc5b257cc1329f6","target":"graph","created_at":"2026-07-05T05:33:09Z","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/2203.10591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Variational Quantum Circuits are being used as versatile Quantum Machine Learning models. Some empirical results exhibit an advantage in supervised and generative learning tasks. However, when applied to Reinforcement Learning, less is known. In this work, we considered a Variational Quantum Circuit composed of a low-depth hardware-efficient ansatz as the parameterized policy of a Reinforcement Learning agent. We show that an $\\epsilon$-approximation of the policy gradient can be obtained using a logarithmic number of samples concerning the total number of parameters. We empirically verify tha","authors_text":"Andr\\'e Sequeira, Luis Paulo Santos, Lu\\'is Soares Barbosa","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-03-20T16:14:49Z","title":"Policy Gradients using Variational Quantum Circuits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10591","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":"sha256:98d701054f45f5f719a5467e5219cbd6cbb0b751b907e32f37576a7930788863","target":"record","created_at":"2026-07-05T05:33:09Z","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":"625ce9b318fe2ef7ba83652557f13ccd29f6733060480d6199d8fbb792c41073","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2022-03-20T16:14:49Z","title_canon_sha256":"554b33bd5b55706bd118af4f8f2cee1b41be84ad67166ffebb233e5fd9a6034d"},"schema_version":"1.0","source":{"id":"2203.10591","kind":"arxiv","version":3}},"canonical_sha256":"764e16ef513ca059f4bf05f1a66323791e641be8ba56c6fbfe74bc109783c75a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"764e16ef513ca059f4bf05f1a66323791e641be8ba56c6fbfe74bc109783c75a","first_computed_at":"2026-07-05T05:33:09.301804Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:33:09.301804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d1kF3ZDwK410CZ4lftfAey+i35wDqjaZ6VlP9uydgFs+fNg0odWObM9kyn8YRcdDEavcOorB3ObWQoVlHutmBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:33:09.302322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.10591","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98d701054f45f5f719a5467e5219cbd6cbb0b751b907e32f37576a7930788863","sha256:473630967bf00c241f50325301f7408cc43c7ee64f1a290b5fc5b257cc1329f6"],"state_sha256":"e379840d918967a941ba494eaa51d96c18a63c4294c80652378122645a8e575e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8EGH9/eaUC1sb01Y6vuSs69ApvPB7e0dtcY8GtpVmLBWlQZaOg4l9lDvA+0c4FA6bjYOBgKZ6w9xrDPhB0FLBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T14:21:00.171474Z","bundle_sha256":"233d5618bc03a5c0f45b9e1d2999bdcb8a44290c4fde20c1f26b0c5a3a7adfbb"}}