{"paper":{"title":"Learning What's Real: Disentangling Signal and Measurement Artifacts in Multi-Sensor Data, with Applications to Astrophysics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Overlapping observations from different instruments train a model to isolate intrinsic galaxy signals from sensor artifacts.","cross_cats":["astro-ph.GA","cs.LG"],"primary_cat":"astro-ph.IM","authors_text":"Carolina Cuesta-Lazaro, Daniel Muthukrishna, David W. Hogg, Jeroen Audenaert, Marc Huertas-Company, Pablo Mercader-Perez, V. Ashley Villar, William T. Freeman","submitted_at":"2026-04-10T18:11:05Z","abstract_excerpt":"Data collected from the physical world is always a combination of multiple sources: an underlying signal from the physical process of interest and a signal from measurement-dependent artifacts from the sensor or instrument. This secondary signal acts as a confounding factor, limiting our ability to extract information about the physics underlying the phenomena we observe. Furthermore, it complicates the combination of observations in heterogeneous or multi-instrument settings. We propose a deep learning framework that leverages overlapping observations, a dual-encoder architecture, and a count"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The resulting representations explicitly separate intrinsic signals from sensor-specific distortions and noise, and can be used for counterfactual view generation, parameter inference unconfounded by measurement distortions, and instrument-independent similarity search.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That overlapping observations of the same physical objects across instruments provide sufficient signal to train a dual-encoder model to isolate sensor artifacts via counterfactual generation without additional labels or strong priors on the artifact distribution.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A dual-encoder deep learning method disentangles intrinsic astrophysical signals from measurement artifacts by treating sensor effects as augmentations and using counterfactual generation on overlapping observations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Overlapping observations from different instruments train a model to isolate intrinsic galaxy signals from sensor artifacts.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"50f8a9d6630486bcd051e2e5a95026994ac3271ef7969809bfab04651f792ea3"},"source":{"id":"2604.09787","kind":"arxiv","version":2},"verdict":{"id":"cd2c52d7-182a-4ec6-9955-29d3326deb5c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:55:20.714668Z","strongest_claim":"The resulting representations explicitly separate intrinsic signals from sensor-specific distortions and noise, and can be used for counterfactual view generation, parameter inference unconfounded by measurement distortions, and instrument-independent similarity search.","one_line_summary":"A dual-encoder deep learning method disentangles intrinsic astrophysical signals from measurement artifacts by treating sensor effects as augmentations and using counterfactual generation on overlapping observations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That overlapping observations of the same physical objects across instruments provide sufficient signal to train a dual-encoder model to isolate sensor artifacts via counterfactual generation without additional labels or strong priors on the artifact distribution.","pith_extraction_headline":"Overlapping observations from different instruments train a model to isolate intrinsic galaxy signals from sensor artifacts."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.09787/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"}