{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HRX4JTCQFFOXIRZUQC3VN6BQBS","short_pith_number":"pith:HRX4JTCQ","schema_version":"1.0","canonical_sha256":"3c6fc4cc50295d74473480b756f8300c865983d39aa918839bc912384df41724","source":{"kind":"arxiv","id":"2101.02464","version":2},"attestation_state":"computed","paper":{"title":"Information-theoretic bounds on quantum advantage in machine learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"quant-ph","authors_text":"Hsin-Yuan Huang, John Preskill, Richard Kueng","submitted_at":"2021-01-07T10:10:09Z","abstract_excerpt":"We study the performance of classical and quantum machine learning (ML) models in predicting outcomes of physical experiments. The experiments depend on an input parameter $x$ and involve execution of a (possibly unknown) quantum process $\\mathcal{E}$. Our figure of merit is the number of runs of $\\mathcal{E}$ required to achieve a desired prediction performance. We consider classical ML models that perform a measurement and record the classical outcome after each run of $\\mathcal{E}$, and quantum ML models that can access $\\mathcal{E}$ coherently to acquire quantum data; the classical or quan"},"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":"2101.02464","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2021-01-07T10:10:09Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"title_canon_sha256":"a708e033462539881f8caae2e3b6ae7f0c3593e375999b267dafe249e583f6ad","abstract_canon_sha256":"cde5db2e9a28dc8089f25abd4a9453b0c1bff1fa9d0500de5024cf224f8c1f28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:41:11.913079Z","signature_b64":"7Nr324tTIg8/dvdlJv9ko8C+U6qiitFjab5Naia+SouOeprKQoZ6+N07SNbFKd+sjRcn51w07VZf6RYxRoxrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c6fc4cc50295d74473480b756f8300c865983d39aa918839bc912384df41724","last_reissued_at":"2026-07-05T02:41:11.912555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:41:11.912555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Information-theoretic bounds on quantum advantage in machine learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"quant-ph","authors_text":"Hsin-Yuan Huang, John Preskill, Richard Kueng","submitted_at":"2021-01-07T10:10:09Z","abstract_excerpt":"We study the performance of classical and quantum machine learning (ML) models in predicting outcomes of physical experiments. The experiments depend on an input parameter $x$ and involve execution of a (possibly unknown) quantum process $\\mathcal{E}$. Our figure of merit is the number of runs of $\\mathcal{E}$ required to achieve a desired prediction performance. We consider classical ML models that perform a measurement and record the classical outcome after each run of $\\mathcal{E}$, and quantum ML models that can access $\\mathcal{E}$ coherently to acquire quantum data; the classical or quan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.02464","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/2101.02464/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":"2101.02464","created_at":"2026-07-05T02:41:11.912611+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.02464v2","created_at":"2026-07-05T02:41:11.912611+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.02464","created_at":"2026-07-05T02:41:11.912611+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRX4JTCQFFOX","created_at":"2026-07-05T02:41:11.912611+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRX4JTCQFFOXIRZU","created_at":"2026-07-05T02:41:11.912611+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRX4JTCQ","created_at":"2026-07-05T02:41:11.912611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23577","citing_title":"Genuine Global Kochen-Specker Contextuality as Classical Coordination Cost","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HRX4JTCQFFOXIRZUQC3VN6BQBS","json":"https://pith.science/pith/HRX4JTCQFFOXIRZUQC3VN6BQBS.json","graph_json":"https://pith.science/api/pith-number/HRX4JTCQFFOXIRZUQC3VN6BQBS/graph.json","events_json":"https://pith.science/api/pith-number/HRX4JTCQFFOXIRZUQC3VN6BQBS/events.json","paper":"https://pith.science/paper/HRX4JTCQ"},"agent_actions":{"view_html":"https://pith.science/pith/HRX4JTCQFFOXIRZUQC3VN6BQBS","download_json":"https://pith.science/pith/HRX4JTCQFFOXIRZUQC3VN6BQBS.json","view_paper":"https://pith.science/paper/HRX4JTCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.02464&json=true","fetch_graph":"https://pith.science/api/pith-number/HRX4JTCQFFOXIRZUQC3VN6BQBS/graph.json","fetch_events":"https://pith.science/api/pith-number/HRX4JTCQFFOXIRZUQC3VN6BQBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRX4JTCQFFOXIRZUQC3VN6BQBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRX4JTCQFFOXIRZUQC3VN6BQBS/action/storage_attestation","attest_author":"https://pith.science/pith/HRX4JTCQFFOXIRZUQC3VN6BQBS/action/author_attestation","sign_citation":"https://pith.science/pith/HRX4JTCQFFOXIRZUQC3VN6BQBS/action/citation_signature","submit_replication":"https://pith.science/pith/HRX4JTCQFFOXIRZUQC3VN6BQBS/action/replication_record"}},"created_at":"2026-07-05T02:41:11.912611+00:00","updated_at":"2026-07-05T02:41:11.912611+00:00"}