{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BVETB6NJ7TCE4HVQ7F33WX4BCH","short_pith_number":"pith:BVETB6NJ","schema_version":"1.0","canonical_sha256":"0d4930f9a9fcc44e1eb0f977bb5f8111ff8efec7cd3933c5d7f777e2ce754548","source":{"kind":"arxiv","id":"2103.05577","version":2},"attestation_state":"computed","paper":{"title":"Parametrized quantum policies for reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"quant-ph","authors_text":"Casper Gyurik, Hans J. Briegel, Simon C. Marshall, Sofiene Jerbi, Vedran Dunjko","submitted_at":"2021-03-09T17:33:09Z","abstract_excerpt":"With the advent of real-world quantum computing, the idea that parametrized quantum computations can be used as hypothesis families in a quantum-classical machine learning system is gaining increasing traction. Such hybrid systems have already shown the potential to tackle real-world tasks in supervised and generative learning, and recent works have established their provable advantages in special artificial tasks. Yet, in the case of reinforcement learning, which is arguably most challenging and where learning boosts would be extremely valuable, no proposal has been successful in solving even"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2103.05577","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"quant-ph","submitted_at":"2021-03-09T17:33:09Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"f8278a64a480b86e73776ece0da5e31bca3cabe04916a689f19dc0709687568a","abstract_canon_sha256":"bd4fc991a59fd109b0478fa1fd98524dddcca644922c9b8b26c65bb98461e314"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:13.569430Z","signature_b64":"HLAWtY+9gl4X8Z661uyWKDSgEswcak0dCOw9b89QWLiOnsg7FvmWd3Ya84KWgN8Athjyuf2dYcJNv3KE6mRABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d4930f9a9fcc44e1eb0f977bb5f8111ff8efec7cd3933c5d7f777e2ce754548","last_reissued_at":"2026-07-05T03:39:13.568881Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:13.568881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parametrized quantum policies for reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"quant-ph","authors_text":"Casper Gyurik, Hans J. Briegel, Simon C. Marshall, Sofiene Jerbi, Vedran Dunjko","submitted_at":"2021-03-09T17:33:09Z","abstract_excerpt":"With the advent of real-world quantum computing, the idea that parametrized quantum computations can be used as hypothesis families in a quantum-classical machine learning system is gaining increasing traction. Such hybrid systems have already shown the potential to tackle real-world tasks in supervised and generative learning, and recent works have established their provable advantages in special artificial tasks. Yet, in the case of reinforcement learning, which is arguably most challenging and where learning boosts would be extremely valuable, no proposal has been successful in solving even"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.05577","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/2103.05577/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2103.05577","created_at":"2026-07-05T03:39:13.568933+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.05577v2","created_at":"2026-07-05T03:39:13.568933+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.05577","created_at":"2026-07-05T03:39:13.568933+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVETB6NJ7TCE","created_at":"2026-07-05T03:39:13.568933+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVETB6NJ7TCE4HVQ","created_at":"2026-07-05T03:39:13.568933+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVETB6NJ","created_at":"2026-07-05T03:39:13.568933+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08276","citing_title":"QnRL: Quantum-Native Reinforcement Learning","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21213","citing_title":"Enhanced Reinforcement Learning-based Process Synthesis via Quantum Computing","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BVETB6NJ7TCE4HVQ7F33WX4BCH","json":"https://pith.science/pith/BVETB6NJ7TCE4HVQ7F33WX4BCH.json","graph_json":"https://pith.science/api/pith-number/BVETB6NJ7TCE4HVQ7F33WX4BCH/graph.json","events_json":"https://pith.science/api/pith-number/BVETB6NJ7TCE4HVQ7F33WX4BCH/events.json","paper":"https://pith.science/paper/BVETB6NJ"},"agent_actions":{"view_html":"https://pith.science/pith/BVETB6NJ7TCE4HVQ7F33WX4BCH","download_json":"https://pith.science/pith/BVETB6NJ7TCE4HVQ7F33WX4BCH.json","view_paper":"https://pith.science/paper/BVETB6NJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.05577&json=true","fetch_graph":"https://pith.science/api/pith-number/BVETB6NJ7TCE4HVQ7F33WX4BCH/graph.json","fetch_events":"https://pith.science/api/pith-number/BVETB6NJ7TCE4HVQ7F33WX4BCH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVETB6NJ7TCE4HVQ7F33WX4BCH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVETB6NJ7TCE4HVQ7F33WX4BCH/action/storage_attestation","attest_author":"https://pith.science/pith/BVETB6NJ7TCE4HVQ7F33WX4BCH/action/author_attestation","sign_citation":"https://pith.science/pith/BVETB6NJ7TCE4HVQ7F33WX4BCH/action/citation_signature","submit_replication":"https://pith.science/pith/BVETB6NJ7TCE4HVQ7F33WX4BCH/action/replication_record"}},"created_at":"2026-07-05T03:39:13.568933+00:00","updated_at":"2026-07-05T03:39:13.568933+00:00"}