{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LQA3RQ7UZIYG37F365PTPBC7B3","short_pith_number":"pith:LQA3RQ7U","schema_version":"1.0","canonical_sha256":"5c01b8c3f4ca306dfcbbf75f37845f0ecad2c35b83c7b778c097f6c391596d7c","source":{"kind":"arxiv","id":"2102.09449","version":2},"attestation_state":"computed","paper":{"title":"Quantum field-theoretic machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG","hep-th"],"primary_cat":"hep-lat","authors_text":"Biagio Lucini, Dimitrios Bachtis, Gert Aarts","submitted_at":"2021-02-18T16:12:51Z","abstract_excerpt":"We derive machine learning algorithms from discretized Euclidean field theories, making inference and learning possible within dynamics described by quantum field theory. Specifically, we demonstrate that the $\\phi^{4}$ scalar field theory satisfies the Hammersley-Clifford theorem, therefore recasting it as a machine learning algorithm within the mathematically rigorous framework of Markov random fields. We illustrate the concepts by minimizing an asymmetric distance between the probability distribution of the $\\phi^{4}$ theory and that of target distributions, by quantifying the overlap of st"},"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":"2102.09449","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"hep-lat","submitted_at":"2021-02-18T16:12:51Z","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG","hep-th"],"title_canon_sha256":"2f1c524f004471458b121667be029d2aa7b6f7b3c88c0c2249503df2c05cf551","abstract_canon_sha256":"ea5fa95a4d3d509f1c8e124731b3672ddd4f0f30fe5026ff109d478824f97f0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:35:38.381200Z","signature_b64":"D1+FpSU7pBHaGZvEeCzIKj2T8JknnWkNGqI2AhIcoCcYTq19m2uNQJ3BmdKXqNP2g1tCkuPAcAFqokx1J7zoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c01b8c3f4ca306dfcbbf75f37845f0ecad2c35b83c7b778c097f6c391596d7c","last_reissued_at":"2026-07-05T02:35:38.380650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:35:38.380650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantum field-theoretic machine learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG","hep-th"],"primary_cat":"hep-lat","authors_text":"Biagio Lucini, Dimitrios Bachtis, Gert Aarts","submitted_at":"2021-02-18T16:12:51Z","abstract_excerpt":"We derive machine learning algorithms from discretized Euclidean field theories, making inference and learning possible within dynamics described by quantum field theory. Specifically, we demonstrate that the $\\phi^{4}$ scalar field theory satisfies the Hammersley-Clifford theorem, therefore recasting it as a machine learning algorithm within the mathematically rigorous framework of Markov random fields. We illustrate the concepts by minimizing an asymmetric distance between the probability distribution of the $\\phi^{4}$ theory and that of target distributions, by quantifying the overlap of st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.09449","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/2102.09449/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":"2102.09449","created_at":"2026-07-05T02:35:38.380707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.09449v2","created_at":"2026-07-05T02:35:38.380707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.09449","created_at":"2026-07-05T02:35:38.380707+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQA3RQ7UZIYG","created_at":"2026-07-05T02:35:38.380707+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQA3RQ7UZIYG37F3","created_at":"2026-07-05T02:35:38.380707+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQA3RQ7U","created_at":"2026-07-05T02:35:38.380707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.01001","citing_title":"Criticality analysis of nuclear binding energy neural networks","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQA3RQ7UZIYG37F365PTPBC7B3","json":"https://pith.science/pith/LQA3RQ7UZIYG37F365PTPBC7B3.json","graph_json":"https://pith.science/api/pith-number/LQA3RQ7UZIYG37F365PTPBC7B3/graph.json","events_json":"https://pith.science/api/pith-number/LQA3RQ7UZIYG37F365PTPBC7B3/events.json","paper":"https://pith.science/paper/LQA3RQ7U"},"agent_actions":{"view_html":"https://pith.science/pith/LQA3RQ7UZIYG37F365PTPBC7B3","download_json":"https://pith.science/pith/LQA3RQ7UZIYG37F365PTPBC7B3.json","view_paper":"https://pith.science/paper/LQA3RQ7U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.09449&json=true","fetch_graph":"https://pith.science/api/pith-number/LQA3RQ7UZIYG37F365PTPBC7B3/graph.json","fetch_events":"https://pith.science/api/pith-number/LQA3RQ7UZIYG37F365PTPBC7B3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQA3RQ7UZIYG37F365PTPBC7B3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQA3RQ7UZIYG37F365PTPBC7B3/action/storage_attestation","attest_author":"https://pith.science/pith/LQA3RQ7UZIYG37F365PTPBC7B3/action/author_attestation","sign_citation":"https://pith.science/pith/LQA3RQ7UZIYG37F365PTPBC7B3/action/citation_signature","submit_replication":"https://pith.science/pith/LQA3RQ7UZIYG37F365PTPBC7B3/action/replication_record"}},"created_at":"2026-07-05T02:35:38.380707+00:00","updated_at":"2026-07-05T02:35:38.380707+00:00"}