{"paper":{"title":"Replacing Gaussian Processes with Neural Networks in Pulsar Timing Array Inference of the Gravitational-Wave Background","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Probabilistic neural networks can replace Gaussian process interpolators in pulsar timing array analyses of nanohertz gravitational wave backgrounds, producing matching posteriors at lower computational cost.","cross_cats":["physics.data-an"],"primary_cat":"astro-ph.CO","authors_text":"Chris Gordon, Shreyas Tiruvaskar","submitted_at":"2026-04-06T01:18:42Z","abstract_excerpt":"Bayesian inference of nanohertz gravitational-wave background models in pulsar timing array analyses often relies on Gaussian-process interpolators to avoid repeated, computationally expensive strain-spectrum calculations. However, Gaussian-process training becomes a bottleneck for large training sets. We test whether probabilistic neural networks can replace Gaussian processes in this role for both a self-interacting dark matter model and a phenomenological environmental model. We find that neural networks recover consistent posteriors while significantly reducing both training and Markov cha"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We find that neural networks recover consistent posteriors while significantly reducing both training and Markov chain Monte Carlo runtime, with the largest gains for the more computationally demanding model.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The neural networks, once trained on a finite set of strain-spectrum evaluations, accurately generalize across the full prior volume of the target models without introducing systematic biases into the recovered posteriors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Probabilistic neural networks recover consistent posteriors to Gaussian processes in PTA gravitational-wave background inference while substantially reducing training and MCMC runtime.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Probabilistic neural networks can replace Gaussian process interpolators in pulsar timing array analyses of nanohertz gravitational wave backgrounds, producing matching posteriors at lower computational cost.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"75cb6209a2d03bccfe7954b731c9b780eae72c48e902fcfb042cd838213d4dfe"},"source":{"id":"2604.04340","kind":"arxiv","version":3},"verdict":{"id":"2875f9e5-ca17-4231-8a94-d664be8ef748","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T20:24:52.576017Z","strongest_claim":"We find that neural networks recover consistent posteriors while significantly reducing both training and Markov chain Monte Carlo runtime, with the largest gains for the more computationally demanding model.","one_line_summary":"Probabilistic neural networks recover consistent posteriors to Gaussian processes in PTA gravitational-wave background inference while substantially reducing training and MCMC runtime.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The neural networks, once trained on a finite set of strain-spectrum evaluations, accurately generalize across the full prior volume of the target models without introducing systematic biases into the recovered posteriors.","pith_extraction_headline":"Probabilistic neural networks can replace Gaussian process interpolators in pulsar timing array analyses of nanohertz gravitational wave backgrounds, producing matching posteriors at lower computational cost."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.04340/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"}