{"paper":{"title":"Quantum Feature Pyramid Gating for Seismic Image Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A 4-qubit quantum circuit at Feature Pyramid merge points raises mean IoU from 0.8404 to 0.9389 on seismic salt segmentation.","cross_cats":["cs.LG"],"primary_cat":"quant-ph","authors_text":"Jyotsna Sharma, Taha Gharaibeh","submitted_at":"2026-05-14T19:50:01Z","abstract_excerpt":"Accurate salt-body delineation is essential for seismic interpretation because salt structures distort wave propagation, complicate velocity-model building, obscure reservoir geometry, and increase uncertainty in exploration and drilling decisions. Although hybrid quantum-classical models have shown competitive performance on small-scale image-classification tasks, their value for dense, pixel-level geophysical prediction remains largely untested. This work introduces quantum feature gating, a hybrid segmentation architecture that embeds a parameterized quantum circuit (PQC) at feature-fusion "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"In a controlled EfficientNetV2-L ablation at 256 x 256 resolution, replacing the three Quantum FPN Gates with element-wise addition while holding the encoder, loss schedule, splits, and threshold search fixed reduces mean IoU from 0.9389 to 0.8404, a 9.85 percentage-point gap.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The performance gap is attributable to the quantum circuit rather than to the introduction of 72 additional trainable parameters or to the specific gating topology; the paper compares against element-wise addition but does not report a classical parametric gate with matched parameter count.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A 4-qubit quantum feature pyramid gating architecture raises mean IoU from 0.8404 to 0.9389 over classical addition in controlled ablations on the TGS salt segmentation dataset.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A 4-qubit quantum circuit at Feature Pyramid merge points raises mean IoU from 0.8404 to 0.9389 on seismic salt segmentation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"97206215bb60a83b1e9f4116a9e27cc15be6f7ffc438355a4437c75cbee1a21e"},"source":{"id":"2605.15370","kind":"arxiv","version":1},"verdict":{"id":"fb2fb72c-f804-4b6b-a9be-e5a2523e6195","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T15:42:31.912482Z","strongest_claim":"In a controlled EfficientNetV2-L ablation at 256 x 256 resolution, replacing the three Quantum FPN Gates with element-wise addition while holding the encoder, loss schedule, splits, and threshold search fixed reduces mean IoU from 0.9389 to 0.8404, a 9.85 percentage-point gap.","one_line_summary":"A 4-qubit quantum feature pyramid gating architecture raises mean IoU from 0.8404 to 0.9389 over classical addition in controlled ablations on the TGS salt segmentation dataset.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The performance gap is attributable to the quantum circuit rather than to the introduction of 72 additional trainable parameters or to the specific gating topology; the paper compares against element-wise addition but does not report a classical parametric gate with matched parameter count.","pith_extraction_headline":"A 4-qubit quantum circuit at Feature Pyramid merge points raises mean IoU from 0.8404 to 0.9389 on seismic salt segmentation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15370/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T16:01:18.064077Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:53:42.707631Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.187387Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.736474Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"58c0b2eeae52bff406b4d5c0868c43319eaa14efbee3656448a9d96ca97270c6"},"references":{"count":33,"sample":[{"doi":"","year":2019,"title":"Parameterized quantum circuits as machine learning models,","work_id":"878f6a7a-264d-4563-8c6e-a31808280049","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Quantum machine learning for image classification,","work_id":"47cd29fb-56cb-49b1-8fcd-4f75882eeb6a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Transfer learning in hybrid classical-quantum neural networks,","work_id":"61a0df57-8a5c-4e61-8b05-233568265ae0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Quanvolutional neural networks: Powering image recognition with quantum circuits,","work_id":"8a3f86ee-cd37-4e6c-99b0-98d3de0295cb","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Effect of data encoding on the expressive power of variational quantum machine-learning models,","work_id":"7d6c57a1-dc06-4f73-9125-48e6db6c2aa2","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":33,"snapshot_sha256":"ded04a748b4870eacf9a56d5362a30f2f95b94295a767f0fcb8331ebc5247f08","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bad0ffab6109eb87d71828540434ac2cb96da9743ec40ff7cdd9cd113bab1803"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}