{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:45ZKNSCI4PS2QLQGAYGRU3BTW7","short_pith_number":"pith:45ZKNSCI","schema_version":"1.0","canonical_sha256":"e772a6c848e3e5a82e06060d1a6c33b7cb884e1a83ea7946a9814fb09f5f698b","source":{"kind":"arxiv","id":"2605.03207","version":1},"attestation_state":"computed","paper":{"title":"Phy2-ExposNet: A Physics-Informed Neural Network for EMF Exposure Mapping in Complex Urban Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Phy2-ExposNet maps urban EMF exposure by first enforcing two physical constraints then refining residuals with a transformer, cutting error and model size.","cross_cats":[],"primary_cat":"eess.SP","authors_text":"Joe Wiart, Shanshan Wang, Shuangning Li, Yarui Zhang","submitted_at":"2026-05-04T22:53:17Z","abstract_excerpt":"Accurate electromagnetic field (EMF) exposure mapping is critical for wireless network planning, environmental monitoring, and the deployment of next generation communication systems. The mapping results can be converted into the form of a radio map, a key technology in digital twin communication systems, used to describe the wireless signal propagation characteristics at every location in a specific area. Existing deep learning approaches treat propagation estimation as a pure regression problem and do not enforce physical consistency in the predicted fields. In this paper, we propose Phy2-Ex"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.03207","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SP","submitted_at":"2026-05-04T22:53:17Z","cross_cats_sorted":[],"title_canon_sha256":"f54ebf3d88e2933b1f3ba02cdf96181370c08da7f39bc7664e6247da7f208e77","abstract_canon_sha256":"9ee2c228b71a152995cbe42349ad6236375e2908c3b4ac7175558294c723825c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:22.079467Z","signature_b64":"bB7ScrTkRqW7TJfOhbMte6ftZbJ7+bSrG8SboOciCRKLXAGeP+YTjmfHhZsgf24S1dM3Hf3ILJf0JQiBDjn8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e772a6c848e3e5a82e06060d1a6c33b7cb884e1a83ea7946a9814fb09f5f698b","last_reissued_at":"2026-06-30T02:17:22.078803Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:22.078803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phy2-ExposNet: A Physics-Informed Neural Network for EMF Exposure Mapping in Complex Urban Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Phy2-ExposNet maps urban EMF exposure by first enforcing two physical constraints then refining residuals with a transformer, cutting error and model size.","cross_cats":[],"primary_cat":"eess.SP","authors_text":"Joe Wiart, Shanshan Wang, Shuangning Li, Yarui Zhang","submitted_at":"2026-05-04T22:53:17Z","abstract_excerpt":"Accurate electromagnetic field (EMF) exposure mapping is critical for wireless network planning, environmental monitoring, and the deployment of next generation communication systems. The mapping results can be converted into the form of a radio map, a key technology in digital twin communication systems, used to describe the wireless signal propagation characteristics at every location in a specific area. Existing deep learning approaches treat propagation estimation as a pure regression problem and do not enforce physical consistency in the predicted fields. In this paper, we propose Phy2-Ex"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments demonstrate that the proposed method achieves lower estimation error while significantly reducing model complexity compared to existing approaches. It achieves around 15% relative error reduction over strong baselines, while using over 80% fewer parameters than conventional physics-informed models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The two unspecified physical constraints in the estimation stage correctly capture EMF propagation physics in complex urban geometries, and the transformer residual stage adds only genuine unmodeled effects without introducing new artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Phy2-ExposNet combines physics-informed neural estimation with transformer refinement to map electromagnetic field exposure, cutting error by ~15% and parameters by >80% versus baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Phy2-ExposNet maps urban EMF exposure by first enforcing two physical constraints then refining residuals with a transformer, cutting error and model size.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e8d628680c7d140f686d199de672bb7322e257fa32036488196a83c2126139a4"},"source":{"id":"2605.03207","kind":"arxiv","version":1},"verdict":{"id":"021abd50-a6e0-41e4-b407-c4bf02409eaf","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T17:17:49.570402Z","strongest_claim":"Experiments demonstrate that the proposed method achieves lower estimation error while significantly reducing model complexity compared to existing approaches. It achieves around 15% relative error reduction over strong baselines, while using over 80% fewer parameters than conventional physics-informed models.","one_line_summary":"Phy2-ExposNet combines physics-informed neural estimation with transformer refinement to map electromagnetic field exposure, cutting error by ~15% and parameters by >80% versus baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The two unspecified physical constraints in the estimation stage correctly capture EMF propagation physics in complex urban geometries, and the transformer residual stage adds only genuine unmodeled effects without introducing new artifacts.","pith_extraction_headline":"Phy2-ExposNet maps urban EMF exposure by first enforcing two physical constraints then refining residuals with a transformer, cutting error and model size."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.03207/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T14:35:34.657172Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T01:31:21.892253Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:34:48.085633Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"6db981ea2eeaef655d483a084b39bfe08480ebe967f8f54bc57ceadafb32fd1b"},"references":{"count":25,"sample":[{"doi":"","year":2023,"title":"S. Faye, R. Camino, G. Rziga, P. A. Sarvari, N. Al-Naffakh, J. C. Estrada-Jim ´enez, E. Pardo, and D. Khadraoui. A survey on EMF-aware mobile net- work planning.IEEE Access, 11:84568–84597, 2023","work_id":"e6fa27e0-966e-4a73-bce6-cadb69612cc1","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Guidelines for limiting exposure to electro- magnetic fields (100 kHz to 300 GHz).Health Phys., 118(5):483–524","work_id":"d0319b0b-68ce-4527-9b9c-493de9693e2f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Chan- nel knowledge maps for 6g wireless networks: Con- struction, applications, and future challenges","work_id":"1c2936d0-3051-4923-b71e-d1ada2eefcf6","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Overview of the first pathloss radio map prediction challenge.IEEE Open Journal of Signal Processing","work_id":"6b0382ac-6103-44b6-afce-77f47f307a93","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Electromagnetic field expo- sure mapping: A taxonomy and survey.Computers","work_id":"10a8a468-5cee-4dd8-8f40-bd8887350bcd","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":25,"snapshot_sha256":"d0352965839335c784f529e7b17585f0ee23e9c2acccec0e7cb48d7179ebe49d","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.03207","created_at":"2026-06-30T02:17:22.078875+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.03207v1","created_at":"2026-06-30T02:17:22.078875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.03207","created_at":"2026-06-30T02:17:22.078875+00:00"},{"alias_kind":"pith_short_12","alias_value":"45ZKNSCI4PS2","created_at":"2026-06-30T02:17:22.078875+00:00"},{"alias_kind":"pith_short_16","alias_value":"45ZKNSCI4PS2QLQG","created_at":"2026-06-30T02:17:22.078875+00:00"},{"alias_kind":"pith_short_8","alias_value":"45ZKNSCI","created_at":"2026-06-30T02:17:22.078875+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/45ZKNSCI4PS2QLQGAYGRU3BTW7","json":"https://pith.science/pith/45ZKNSCI4PS2QLQGAYGRU3BTW7.json","graph_json":"https://pith.science/api/pith-number/45ZKNSCI4PS2QLQGAYGRU3BTW7/graph.json","events_json":"https://pith.science/api/pith-number/45ZKNSCI4PS2QLQGAYGRU3BTW7/events.json","paper":"https://pith.science/paper/45ZKNSCI"},"agent_actions":{"view_html":"https://pith.science/pith/45ZKNSCI4PS2QLQGAYGRU3BTW7","download_json":"https://pith.science/pith/45ZKNSCI4PS2QLQGAYGRU3BTW7.json","view_paper":"https://pith.science/paper/45ZKNSCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.03207&json=true","fetch_graph":"https://pith.science/api/pith-number/45ZKNSCI4PS2QLQGAYGRU3BTW7/graph.json","fetch_events":"https://pith.science/api/pith-number/45ZKNSCI4PS2QLQGAYGRU3BTW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/45ZKNSCI4PS2QLQGAYGRU3BTW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/45ZKNSCI4PS2QLQGAYGRU3BTW7/action/storage_attestation","attest_author":"https://pith.science/pith/45ZKNSCI4PS2QLQGAYGRU3BTW7/action/author_attestation","sign_citation":"https://pith.science/pith/45ZKNSCI4PS2QLQGAYGRU3BTW7/action/citation_signature","submit_replication":"https://pith.science/pith/45ZKNSCI4PS2QLQGAYGRU3BTW7/action/replication_record"}},"created_at":"2026-06-30T02:17:22.078875+00:00","updated_at":"2026-06-30T02:17:22.078875+00:00"}