{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KE225UM4FMR3B5W6IF43EAPNOZ","short_pith_number":"pith:KE225UM4","schema_version":"1.0","canonical_sha256":"5135aed19c2b23b0f6de4179b201ed7654a4358babf423b25ff93b42e61c47b9","source":{"kind":"arxiv","id":"2508.15983","version":1},"attestation_state":"computed","paper":{"title":"A simulation-based training framework for machine-learning applications in ARPES","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","physics.comp-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Andrea Damascelli, Chris Zhou, Matteo Michiardi, MengXing Na, Sydney K. Y. Dufresne","submitted_at":"2025-08-21T21:59:09Z","abstract_excerpt":"In recent years, angle-resolved photoemission spectroscopy (ARPES) has advanced significantly in its ability to probe more observables and simultaneously generate multi-dimensional datasets. These advances present new challenges in data acquisition, processing, and analysis. Machine learning (ML) models can drastically reduce the workload of experimentalists; however, the lack of training data for ML -- and in particular deep learning -- is a significant obstacle. In this work, we introduce an open-source synthetic ARPES spectra simulator - aurelia - for the purpose of generating the large dat"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.15983","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2025-08-21T21:59:09Z","cross_cats_sorted":["cs.LG","physics.comp-ph"],"title_canon_sha256":"87b69a3ef2d1e7ec4f27db3b31140362c5471fbc4a0a3e26157c9291409fb151","abstract_canon_sha256":"c0ff494ac425c0e1bcb546e74c845457713674aab484eda1b73d16d6a67123ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:24.134884Z","signature_b64":"pKrGWLGpobnRWpKm/rm+BMAWyddz++D3R24M93srhy6fqVbmL06HjZAFU2AM+/yWTQQ6YxP2L93oUi4vETxRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5135aed19c2b23b0f6de4179b201ed7654a4358babf423b25ff93b42e61c47b9","last_reissued_at":"2026-07-05T11:57:24.134344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:24.134344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A simulation-based training framework for machine-learning applications in ARPES","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","physics.comp-ph"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Andrea Damascelli, Chris Zhou, Matteo Michiardi, MengXing Na, Sydney K. Y. Dufresne","submitted_at":"2025-08-21T21:59:09Z","abstract_excerpt":"In recent years, angle-resolved photoemission spectroscopy (ARPES) has advanced significantly in its ability to probe more observables and simultaneously generate multi-dimensional datasets. These advances present new challenges in data acquisition, processing, and analysis. Machine learning (ML) models can drastically reduce the workload of experimentalists; however, the lack of training data for ML -- and in particular deep learning -- is a significant obstacle. In this work, we introduce an open-source synthetic ARPES spectra simulator - aurelia - for the purpose of generating the large dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15983","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.15983/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.15983","created_at":"2026-07-05T11:57:24.134406+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.15983v1","created_at":"2026-07-05T11:57:24.134406+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15983","created_at":"2026-07-05T11:57:24.134406+00:00"},{"alias_kind":"pith_short_12","alias_value":"KE225UM4FMR3","created_at":"2026-07-05T11:57:24.134406+00:00"},{"alias_kind":"pith_short_16","alias_value":"KE225UM4FMR3B5W6","created_at":"2026-07-05T11:57:24.134406+00:00"},{"alias_kind":"pith_short_8","alias_value":"KE225UM4","created_at":"2026-07-05T11:57:24.134406+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07819","citing_title":"Probabilistic denoising for reliable signal extraction in spectroscopy","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KE225UM4FMR3B5W6IF43EAPNOZ","json":"https://pith.science/pith/KE225UM4FMR3B5W6IF43EAPNOZ.json","graph_json":"https://pith.science/api/pith-number/KE225UM4FMR3B5W6IF43EAPNOZ/graph.json","events_json":"https://pith.science/api/pith-number/KE225UM4FMR3B5W6IF43EAPNOZ/events.json","paper":"https://pith.science/paper/KE225UM4"},"agent_actions":{"view_html":"https://pith.science/pith/KE225UM4FMR3B5W6IF43EAPNOZ","download_json":"https://pith.science/pith/KE225UM4FMR3B5W6IF43EAPNOZ.json","view_paper":"https://pith.science/paper/KE225UM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.15983&json=true","fetch_graph":"https://pith.science/api/pith-number/KE225UM4FMR3B5W6IF43EAPNOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/KE225UM4FMR3B5W6IF43EAPNOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KE225UM4FMR3B5W6IF43EAPNOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KE225UM4FMR3B5W6IF43EAPNOZ/action/storage_attestation","attest_author":"https://pith.science/pith/KE225UM4FMR3B5W6IF43EAPNOZ/action/author_attestation","sign_citation":"https://pith.science/pith/KE225UM4FMR3B5W6IF43EAPNOZ/action/citation_signature","submit_replication":"https://pith.science/pith/KE225UM4FMR3B5W6IF43EAPNOZ/action/replication_record"}},"created_at":"2026-07-05T11:57:24.134406+00:00","updated_at":"2026-07-05T11:57:24.134406+00:00"}