{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E23TLP3F4AZIL5PWIXZ3ZYADFM","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":"edc7bba07b767902011bd0b924907a987b2e08f495dde2d13c706b21a81e1889","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2025-11-13T08:50:40Z","title_canon_sha256":"31f8dabc9e554fe3923855f784c7096a629a4702cf5c89b5662bd6d26cb7b274"},"schema_version":"1.0","source":{"id":"2511.10709","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.10709","created_at":"2026-05-18T02:44:32Z"},{"alias_kind":"arxiv_version","alias_value":"2511.10709v2","created_at":"2026-05-18T02:44:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.10709","created_at":"2026-05-18T02:44:32Z"},{"alias_kind":"pith_short_12","alias_value":"E23TLP3F4AZI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"E23TLP3F4AZIL5PW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"E23TLP3F","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:1d3d43cc478f23469ce02322a7bbe6de965a659ef4f45355529d8b566abda084","target":"graph","created_at":"2026-05-18T02:44:32Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"An advantage can be obtained only when features of density matrices that are absent in classical probability distributions are exploited. Such situations depend on the input data as well as the targeted observables."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the classical baseline is restricted to Boltzmann distributions with tunable parameters and that no other classical or hybrid techniques can capture the same quantum-like features without actual quantum hardware."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Quantum advantage in unsupervised machine learning is limited to cases where density-matrix features absent from classical distributions can be exploited, with explicit examples showing strong dependence on input data and target observables."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Quantum advantage in unsupervised machine learning arises only when exploiting features of density matrices not found in classical probability distributions."}],"snapshot_sha256":"3afdc673b66922d520122fe0ec02b795542d3053512f9473f1330935d1e25ef0"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f021f2c525e976143eda033e470633d04ad32e952c8cd601855ea9b00f6f71cf"},"paper":{"abstract_excerpt":"Machine learning models are used for pattern recognition analysis of big data, without direct human intervention. The task of unsupervised learning is to find the probability distribution that would best describe the available data, and then use it to make predictions for observables of interest. Classical models generally fit the data to Boltzmann distribution of Hamiltonians with a large number of tunable parameters. Quantum extensions of these models replace classical probability distributions with quantum density matrices. An advantage can be obtained only when features of density matrices","authors_text":"Apoorva D. Patel","cross_cats":["cs.LG"],"headline":"Quantum advantage in unsupervised machine learning arises only when exploiting features of density matrices not found in classical probability distributions.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2025-11-13T08:50:40Z","title":"Limitations of Quantum Advantage in Unsupervised Machine Learning"},"references":{"count":10,"internal_anchors":0,"resolved_work":10,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"1 A2# QB a 3 Rq b 5'S6DTsEF7Gc(UVW dte)8fu*9:HIJXYZghijvwxyz m ! 1","work_id":"04ef250d-5e51-4674-8fc0-fee6da0e536d","year":1914},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"J. D. Kelleher, B. Mac Namee and A. D'Arcy, Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples, and Case Studies , Second Edition, The MIT Press, Cambridge MA,","work_id":"3950a1be-4699-4f4e-828e-eb5b9a857d8a","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"S. J. Russell and P. Norvig, Artificial Intelligence: A Modern Approach , Fourth Edition, Pearson, India; 2022","work_id":"9cac1d58-bdd4-46b7-afce-8e547a6622be","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction , Second Edition, The MIT Press, Cambridge MA, USA; 2020","work_id":"eac3cbcb-755d-4a8e-82cc-37e08e5da1e5","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"M. Schuld and F. Petruccione, Machine Learning with Quantum Computers , Second Edition, Springer Nature Switzerland AG; 2021","work_id":"2673bcde-115a-41de-9fea-caeca9f9f3e1","year":2021}],"snapshot_sha256":"c2d61cb3c60dbbc3aa83372ec9c3210008b864980b14885d41fa34cd43f7af2b"},"source":{"id":"2511.10709","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T22:48:00.700869Z","id":"5020f986-ba64-4508-aa67-4afbc82e3f1c","model_set":{"reader":"grok-4.3"},"one_line_summary":"Quantum advantage in unsupervised machine learning is limited to cases where density-matrix features absent from classical distributions can be exploited, with explicit examples showing strong dependence on input data and target observables.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Quantum advantage in unsupervised machine learning arises only when exploiting features of density matrices not found in classical probability distributions.","strongest_claim":"An advantage can be obtained only when features of density matrices that are absent in classical probability distributions are exploited. Such situations depend on the input data as well as the targeted observables.","weakest_assumption":"That the classical baseline is restricted to Boltzmann distributions with tunable parameters and that no other classical or hybrid techniques can capture the same quantum-like features without actual quantum hardware."}},"verdict_id":"5020f986-ba64-4508-aa67-4afbc82e3f1c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c06095c65c0eb73df3b794b2b74cd9b86c8e7790171b22b0bd4b7e5d4392768f","target":"record","created_at":"2026-05-18T02:44:32Z","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":"edc7bba07b767902011bd0b924907a987b2e08f495dde2d13c706b21a81e1889","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2025-11-13T08:50:40Z","title_canon_sha256":"31f8dabc9e554fe3923855f784c7096a629a4702cf5c89b5662bd6d26cb7b274"},"schema_version":"1.0","source":{"id":"2511.10709","kind":"arxiv","version":2}},"canonical_sha256":"26b735bf65e03285f5f645f3bce0032b0b1a195e4472b0c676940c79f6f5d9d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26b735bf65e03285f5f645f3bce0032b0b1a195e4472b0c676940c79f6f5d9d2","first_computed_at":"2026-05-18T02:44:32.894365Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:32.894365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WRDC0PKy7PYHnJZyrSga4x9BMv9dMp5PKsAnCT0cq0nkxBaDLDOCQiz98VgmSHxng6kHPWo+A2LeRoLTpgDEAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:32.894810Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.10709","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c06095c65c0eb73df3b794b2b74cd9b86c8e7790171b22b0bd4b7e5d4392768f","sha256:1d3d43cc478f23469ce02322a7bbe6de965a659ef4f45355529d8b566abda084"],"state_sha256":"be1780671d1f26ae63d1b8fe16173c1826233be711fb093883b721404f9c540e"}