{"paper":{"title":"Learning holographic QCD with unflavoured meson spectra","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A neural network reconstructs the five-dimensional holographic geometry and potentials of QCD from unflavored meson mass spectra.","cross_cats":["cond-mat.dis-nn","hep-th"],"primary_cat":"hep-ph","authors_text":"Mathew Thomas Arun, Ritik Pal","submitted_at":"2025-12-18T12:11:16Z","abstract_excerpt":"We develop a data-driven neural network framework to reconstruct the five-dimensional background geometry, the dilaton potential, and the chiral-symmetry-breaking scalar potential of holographic QCD from hadron mass spectra. Framed as an inverse problem, the model is trained using a discretized form of the Schr\\\"odinger-like equation, which resembles a linear moose in ``deconstructed\" 5 dimensions with Dirichlet boundary conditions, in contrast to the AdS/DL with ``emergent\" space-time. Using the masses of the unflavored mesons $\\rho$, $a_1$, $a_2$, and $f_0$ and their excitations as training "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Using the masses of the unflavored mesons ρ, a1, a2, and f0 and their excitations as training data, the model learns confining effective potentials and computes a dilaton profile that satisfies the null energy condition. The network predicts that the dilaton's IR behavior will be much steeper than its quadratic form. The symmetry-breaking bulk potential V(X)=k1 X^3 + k2 X^4 was computed with k1 ∼ -4 and k2 ∼ 9. The deep-learned parameters, metric, and dilaton profile were then used to predict the pion mass and its spectrum with good accuracy.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The discretized Schrödinger-like equation with Dirichlet boundary conditions on a linear moose accurately represents the holographic QCD dynamics, and the chosen set of meson masses is sufficient to determine the geometry and potentials uniquely without significant overfitting or degeneracy.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Neural network learns confining potentials and dilaton profile in holographic QCD from meson spectra, predicting steeper IR dilaton and pion masses with good accuracy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A neural network reconstructs the five-dimensional holographic geometry and potentials of QCD from unflavored meson mass spectra.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5581f67a6b589b3ffa7b0498855ddf806b4ee9e52ef5bda1fb1afe254450a122"},"source":{"id":"2512.16450","kind":"arxiv","version":2},"verdict":{"id":"bfa3d926-ad2d-4e27-8c53-2abb3c4cfb23","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T21:16:24.705026Z","strongest_claim":"Using the masses of the unflavored mesons ρ, a1, a2, and f0 and their excitations as training data, the model learns confining effective potentials and computes a dilaton profile that satisfies the null energy condition. The network predicts that the dilaton's IR behavior will be much steeper than its quadratic form. The symmetry-breaking bulk potential V(X)=k1 X^3 + k2 X^4 was computed with k1 ∼ -4 and k2 ∼ 9. The deep-learned parameters, metric, and dilaton profile were then used to predict the pion mass and its spectrum with good accuracy.","one_line_summary":"Neural network learns confining potentials and dilaton profile in holographic QCD from meson spectra, predicting steeper IR dilaton and pion masses with good accuracy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The discretized Schrödinger-like equation with Dirichlet boundary conditions on a linear moose accurately represents the holographic QCD dynamics, and the chosen set of meson masses is sufficient to determine the geometry and potentials uniquely without significant overfitting or degeneracy.","pith_extraction_headline":"A neural network reconstructs the five-dimensional holographic geometry and potentials of QCD from unflavored meson mass spectra."},"references":{"count":51,"sample":[{"doi":"","year":1998,"title":"The Large N Limit of Superconformal Field Theories and Supergravity","work_id":"d6d2272a-c223-471a-bbbf-bfe4ee6a8ff3","ref_index":1,"cited_arxiv_id":"hep-th/9711200","is_internal_anchor":true},{"doi":"","year":1998,"title":"Gauge Theory Correlators from Non-Critical String Theory","work_id":"31a4a9b9-435c-4d7b-a180-437bbbabbe5a","ref_index":2,"cited_arxiv_id":"hep-th/9802109","is_internal_anchor":true},{"doi":"","year":1998,"title":"Anti De Sitter Space And Holography","work_id":"3559baf4-a73f-4ab9-924e-dc5290a82643","ref_index":3,"cited_arxiv_id":"hep-th/9802150","is_internal_anchor":true},{"doi":"","year":2005,"title":"Low energy hadron physics in holographic QCD","work_id":"128e4410-d03b-46ba-898b-c3f7c701fffe","ref_index":4,"cited_arxiv_id":"hep-th/0412141","is_internal_anchor":true},{"doi":"","year":2005,"title":"More on a holographic dual of QCD","work_id":"34a1e844-cde4-494e-8324-1228055f09c7","ref_index":5,"cited_arxiv_id":"hep-th/0507073","is_internal_anchor":true}],"resolved_work":51,"snapshot_sha256":"78b7e15bd967f765357f4499ea20769a12cc16859d3a53daa064101994564bf0","internal_anchors":23},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f2847e2678935783f5c32641f176537dc1d78e394558f934156063dfa7b999ef"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}