{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5L4FWBGSAXIJKJSJVVX7M64VKF","short_pith_number":"pith:5L4FWBGS","schema_version":"1.0","canonical_sha256":"eaf85b04d205d0952649ad6ff67b955144913cd05123f154261db0306213bb89","source":{"kind":"arxiv","id":"2605.17968","version":1},"attestation_state":"computed","paper":{"title":"Function graph transformers universally approximate operators between function spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Mis, Ivan Dokmani\\'c, Maarten V. de Hoop, Matti Lassas, Takashi Furuya","submitted_at":"2026-05-18T07:25:14Z","abstract_excerpt":"We study the approximation of nonlinear operators between function spaces by transformers. Our approach is to lift functions to measures supported on their graphs and leverage a recently introduced measure-theoretic view of transformers. A function $h$ is represented by its graph measure $\\gamma_h$, with finite tokens $\\{(x_j,h(x_j))\\}_{j=1}^N$ being its empirical approximations. We show that this framework elegantly models discretization refinement via convergence of measures and provides a natural setting for operator learning. Within this framework, we introduce function graph transformers,"},"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":"2605.17968","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T07:25:14Z","cross_cats_sorted":[],"title_canon_sha256":"88b0f3a4cee88ef72b906ea5f939bb8299261c1f633ac2a33f6b09b2d726c762","abstract_canon_sha256":"d723c2ae5ffdc439e805101de3a65cd942094276b08f6a476f6899c06acb9fbe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:08.616727Z","signature_b64":"HumbtXezydCVJKJ4sqzDMG4OtZxaa3vl+wbGVtRUsH7bjOnAlNpOdb+EbTaayy+VXGzFou5h0K5k/tqqsr66Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaf85b04d205d0952649ad6ff67b955144913cd05123f154261db0306213bb89","last_reissued_at":"2026-05-20T00:05:08.615886Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:08.615886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Function graph transformers universally approximate operators between function spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Mis, Ivan Dokmani\\'c, Maarten V. de Hoop, Matti Lassas, Takashi Furuya","submitted_at":"2026-05-18T07:25:14Z","abstract_excerpt":"We study the approximation of nonlinear operators between function spaces by transformers. Our approach is to lift functions to measures supported on their graphs and leverage a recently introduced measure-theoretic view of transformers. A function $h$ is represented by its graph measure $\\gamma_h$, with finite tokens $\\{(x_j,h(x_j))\\}_{j=1}^N$ being its empirical approximations. We show that this framework elegantly models discretization refinement via convergence of measures and provides a natural setting for operator learning. Within this framework, we introduce function graph transformers,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17968","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/2605.17968/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.578581Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"8c19e717ba1c74ec971f3ce48874ed3ea386229f99090879be448234b7b459aa"},"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":"2605.17968","created_at":"2026-05-20T00:05:08.616018+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17968v1","created_at":"2026-05-20T00:05:08.616018+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17968","created_at":"2026-05-20T00:05:08.616018+00:00"},{"alias_kind":"pith_short_12","alias_value":"5L4FWBGSAXIJ","created_at":"2026-05-20T00:05:08.616018+00:00"},{"alias_kind":"pith_short_16","alias_value":"5L4FWBGSAXIJKJSJ","created_at":"2026-05-20T00:05:08.616018+00:00"},{"alias_kind":"pith_short_8","alias_value":"5L4FWBGS","created_at":"2026-05-20T00:05:08.616018+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/5L4FWBGSAXIJKJSJVVX7M64VKF","json":"https://pith.science/pith/5L4FWBGSAXIJKJSJVVX7M64VKF.json","graph_json":"https://pith.science/api/pith-number/5L4FWBGSAXIJKJSJVVX7M64VKF/graph.json","events_json":"https://pith.science/api/pith-number/5L4FWBGSAXIJKJSJVVX7M64VKF/events.json","paper":"https://pith.science/paper/5L4FWBGS"},"agent_actions":{"view_html":"https://pith.science/pith/5L4FWBGSAXIJKJSJVVX7M64VKF","download_json":"https://pith.science/pith/5L4FWBGSAXIJKJSJVVX7M64VKF.json","view_paper":"https://pith.science/paper/5L4FWBGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17968&json=true","fetch_graph":"https://pith.science/api/pith-number/5L4FWBGSAXIJKJSJVVX7M64VKF/graph.json","fetch_events":"https://pith.science/api/pith-number/5L4FWBGSAXIJKJSJVVX7M64VKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5L4FWBGSAXIJKJSJVVX7M64VKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5L4FWBGSAXIJKJSJVVX7M64VKF/action/storage_attestation","attest_author":"https://pith.science/pith/5L4FWBGSAXIJKJSJVVX7M64VKF/action/author_attestation","sign_citation":"https://pith.science/pith/5L4FWBGSAXIJKJSJVVX7M64VKF/action/citation_signature","submit_replication":"https://pith.science/pith/5L4FWBGSAXIJKJSJVVX7M64VKF/action/replication_record"}},"created_at":"2026-05-20T00:05:08.616018+00:00","updated_at":"2026-05-20T00:05:08.616018+00:00"}