{"paper":{"title":"SPAMoE: Spectrum-Aware Hybrid Operator Framework for Full-Waveform Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"SPAMoE uses spectrum-aware routing to cut errors in learning-based full-waveform inversion by 44 percent.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenfei Liao, Lei Zhang, Peiyuan Li, Ruoyu Wu, Yongxiang Shi, Zhenyu Wang","submitted_at":"2026-04-08T15:21:06Z","abstract_excerpt":"Full-waveform inversion (FWI) is pivotal for reconstructing high-resolution subsurface velocity models but remains computationally intensive and ill-posed. While deep learning approaches promise efficiency, existing Convolutional Neural Networks (CNNs) and single-paradigm Neural Operators (NOs) struggle with one fundamental issue: frequency entanglement of multi-scale geological features. To address this challenge, we propose Spectral-Preserving Adaptive MoE (SPAMoE), a novel spectrum-aware framework for solving inverse problems with complex multi-scale structures. Our approach introduces a Sp"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On the ten OpenFWI sub-datasets, experiments show that SPAMoE reduces the average MAE by 44.4% relative to the best officially reported OpenFWI baseline, thereby establishing a new architectural framework for learning-based full-waveform inversion.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That frequency entanglement is the primary limitation of prior CNNs and single-paradigm neural operators in FWI, and that the Spectral-Preserving DINO Encoder plus frequency-band MoE routing will reliably mitigate it across varied geological settings without introducing new instabilities or overfitting.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SPAMoE reduces average MAE by 44.4% on OpenFWI datasets for full-waveform inversion via a spectral-preserving DINO encoder and dynamic frequency-band routing to specialized neural operators.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SPAMoE uses spectrum-aware routing to cut errors in learning-based full-waveform inversion by 44 percent.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"941862b0d537ecdb39f2be70eccb7d62015886eca267ccfd06694ca01a6aa008"},"source":{"id":"2604.07421","kind":"arxiv","version":3},"verdict":{"id":"1b3ab7fe-baa5-4eeb-b989-37687276868e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T17:30:14.015825Z","strongest_claim":"On the ten OpenFWI sub-datasets, experiments show that SPAMoE reduces the average MAE by 44.4% relative to the best officially reported OpenFWI baseline, thereby establishing a new architectural framework for learning-based full-waveform inversion.","one_line_summary":"SPAMoE reduces average MAE by 44.4% on OpenFWI datasets for full-waveform inversion via a spectral-preserving DINO encoder and dynamic frequency-band routing to specialized neural operators.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That frequency entanglement is the primary limitation of prior CNNs and single-paradigm neural operators in FWI, and that the Spectral-Preserving DINO Encoder plus frequency-band MoE routing will reliably mitigate it across varied geological settings without introducing new instabilities or overfitting.","pith_extraction_headline":"SPAMoE uses spectrum-aware routing to cut errors in learning-based full-waveform inversion by 44 percent."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.07421/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"}