{"paper":{"title":"TMDs in the Lens of Generative AI: A Pixel-Based Approach to Partonic Imaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A nonparametric pixel-based framework with generative AI solves the TMD inverse problem for unbiased parton imaging.","cross_cats":[],"primary_cat":"hep-ph","authors_text":"Alexei Prokudin, Daniel Pitonyak, Jian-Wei Qiu, Leonard Gamberg, Marco Zaccheddu, Nobuo Sato, Wally Melnitchouk","submitted_at":"2026-05-07T17:25:41Z","abstract_excerpt":"This work introduces a novel, nonparametric pixel-based framework for the Bayesian inference and imaging of transverse momentum dependent (TMD) parton distributions. The methodology is built upon a fully differentiable framework that integrates TMD evolution with the Collins-Soper-Sterman formalism, enabling the simultaneous extraction of partonic distributions and the nonperturbative evolution kernel. To achieve efficient and exact sampling of the high-dimensional posterior, we leverage generative AI through a hybrid normalizing flow-driven Metropolis-Hastings approach. The framework is valid"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The new framework provides the first integration of pixel-based discretization, generative AI, and SVD within a Bayesian context to solve the TMD inverse problem. This synergy between machine learning and multi-scale data removes inherent degeneracies and enables unbiased 3D partonic imaging.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the hybrid normalizing flow-driven Metropolis-Hastings sampler achieves efficient and exact sampling of the high-dimensional posterior without introducing biases that affect the reconstructed TMDs or the identification of null components.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A nonparametric pixel-based Bayesian method integrates TMD evolution with generative AI and SVD to image parton distributions and reveal null TMDs unconstrained by observables.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A nonparametric pixel-based framework with generative AI solves the TMD inverse problem for unbiased parton imaging.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"020415eeee125825f3b28dc21d08d8d87923224548d5f29e281b0a776e0d83f2"},"source":{"id":"2605.06606","kind":"arxiv","version":2},"verdict":{"id":"8c69bb45-dead-457f-b2d5-d18c6736802b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T08:09:52.437939Z","strongest_claim":"The new framework provides the first integration of pixel-based discretization, generative AI, and SVD within a Bayesian context to solve the TMD inverse problem. This synergy between machine learning and multi-scale data removes inherent degeneracies and enables unbiased 3D partonic imaging.","one_line_summary":"A nonparametric pixel-based Bayesian method integrates TMD evolution with generative AI and SVD to image parton distributions and reveal null TMDs unconstrained by observables.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the hybrid normalizing flow-driven Metropolis-Hastings sampler achieves efficient and exact sampling of the high-dimensional posterior without introducing biases that affect the reconstructed TMDs or the identification of null components.","pith_extraction_headline":"A nonparametric pixel-based framework with generative AI solves the TMD inverse problem for unbiased parton imaging."},"integrity":{"clean":false,"summary":{"advisory":0,"critical":1,"by_detector":{"doi_compliance":{"total":1,"advisory":0,"critical":1,"informational":0}},"informational":0},"endpoint":"/pith/2605.06606/integrity.json","findings":[{"note":"Identifier '10.1016/c2015-0-04300-3' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","detector":"doi_compliance","severity":"critical","ref_index":62,"audited_at":"2026-05-19T12:33:27.067295Z","detected_doi":"10.1016/c2015-0-04300-3","finding_type":"unresolvable_identifier","verdict_class":"cross_source","detected_arxiv_id":null}],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T18:01:19.337982Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T12:33:27.067295Z","status":"completed","version":"1.0.0","findings_count":1}],"snapshot_sha256":"53aa06e53ab68414d4a63acfdaa6894f8b6b1e1eccf9c9ec16ea26d23eb5cd4a"},"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"}