{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OAG6QGT72FKDKN52PRFKQYZYA6","short_pith_number":"pith:OAG6QGT7","schema_version":"1.0","canonical_sha256":"700de81a7fd1543537ba7c4aa8633807bd70334193e6431dd105b1f71ab8b271","source":{"kind":"arxiv","id":"2410.23152","version":1},"attestation_state":"computed","paper":{"title":"When can classical neural networks represent quantum states?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.str-el","cs.LG"],"primary_cat":"quant-ph","authors_text":"John Preskill, Mehdi Soleimanifar, Tai-Hsuan Yang, Thiago Bergamaschi","submitted_at":"2024-10-30T16:06:53Z","abstract_excerpt":"A naive classical representation of an n-qubit state requires specifying exponentially many amplitudes in the computational basis. Past works have demonstrated that classical neural networks can succinctly express these amplitudes for many physically relevant states, leading to computationally powerful representations known as neural quantum states. What underpins the efficacy of such representations? We show that conditional correlations present in the measurement distribution of quantum states control the performance of their neural representations. Such conditional correlations are basis de"},"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":"2410.23152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"quant-ph","submitted_at":"2024-10-30T16:06:53Z","cross_cats_sorted":["cond-mat.str-el","cs.LG"],"title_canon_sha256":"cff62760f935d81e428b587b7c9198a48afdc29768397e98bc0147661f03961e","abstract_canon_sha256":"5979134e3d996a5fd2b4e6d8c5b3c257a8f5152cf210b75b4d35c535508d427a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:41.624245Z","signature_b64":"dhve0cDU+gfCb3Z8NHQXFK7wlATB/GgPFVPQ9txr1exY6AKDavXo1QZPX3lhY6bSqg+48P+2WvhSmviA99j9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"700de81a7fd1543537ba7c4aa8633807bd70334193e6431dd105b1f71ab8b271","last_reissued_at":"2026-07-05T09:28:41.623780Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:41.623780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When can classical neural networks represent quantum states?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.str-el","cs.LG"],"primary_cat":"quant-ph","authors_text":"John Preskill, Mehdi Soleimanifar, Tai-Hsuan Yang, Thiago Bergamaschi","submitted_at":"2024-10-30T16:06:53Z","abstract_excerpt":"A naive classical representation of an n-qubit state requires specifying exponentially many amplitudes in the computational basis. Past works have demonstrated that classical neural networks can succinctly express these amplitudes for many physically relevant states, leading to computationally powerful representations known as neural quantum states. What underpins the efficacy of such representations? We show that conditional correlations present in the measurement distribution of quantum states control the performance of their neural representations. Such conditional correlations are basis de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23152","kind":"arxiv","version":1},"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/2410.23152/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":"2410.23152","created_at":"2026-07-05T09:28:41.623840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23152v1","created_at":"2026-07-05T09:28:41.623840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23152","created_at":"2026-07-05T09:28:41.623840+00:00"},{"alias_kind":"pith_short_12","alias_value":"OAG6QGT72FKD","created_at":"2026-07-05T09:28:41.623840+00:00"},{"alias_kind":"pith_short_16","alias_value":"OAG6QGT72FKDKN52","created_at":"2026-07-05T09:28:41.623840+00:00"},{"alias_kind":"pith_short_8","alias_value":"OAG6QGT7","created_at":"2026-07-05T09:28:41.623840+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01336","citing_title":"Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28931","citing_title":"Learning quantum ground states in the space of measurement outcomes","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29683","citing_title":"WF-Bench: A Benchmark for Neural Network WaveFunction Expressivity and Scaling Laws","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26376","citing_title":"Quantum Complexity and New Directions in Nuclear Physics and High-Energy Physics Phenomenology","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08661","citing_title":"Geometry-Induced Long-Range Correlations in Recurrent Neural Network Quantum States","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OAG6QGT72FKDKN52PRFKQYZYA6","json":"https://pith.science/pith/OAG6QGT72FKDKN52PRFKQYZYA6.json","graph_json":"https://pith.science/api/pith-number/OAG6QGT72FKDKN52PRFKQYZYA6/graph.json","events_json":"https://pith.science/api/pith-number/OAG6QGT72FKDKN52PRFKQYZYA6/events.json","paper":"https://pith.science/paper/OAG6QGT7"},"agent_actions":{"view_html":"https://pith.science/pith/OAG6QGT72FKDKN52PRFKQYZYA6","download_json":"https://pith.science/pith/OAG6QGT72FKDKN52PRFKQYZYA6.json","view_paper":"https://pith.science/paper/OAG6QGT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23152&json=true","fetch_graph":"https://pith.science/api/pith-number/OAG6QGT72FKDKN52PRFKQYZYA6/graph.json","fetch_events":"https://pith.science/api/pith-number/OAG6QGT72FKDKN52PRFKQYZYA6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OAG6QGT72FKDKN52PRFKQYZYA6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OAG6QGT72FKDKN52PRFKQYZYA6/action/storage_attestation","attest_author":"https://pith.science/pith/OAG6QGT72FKDKN52PRFKQYZYA6/action/author_attestation","sign_citation":"https://pith.science/pith/OAG6QGT72FKDKN52PRFKQYZYA6/action/citation_signature","submit_replication":"https://pith.science/pith/OAG6QGT72FKDKN52PRFKQYZYA6/action/replication_record"}},"created_at":"2026-07-05T09:28:41.623840+00:00","updated_at":"2026-07-05T09:28:41.623840+00:00"}