{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SHBLL2UTVDA332NN6DDJ7NU7QP","short_pith_number":"pith:SHBLL2UT","schema_version":"1.0","canonical_sha256":"91c2b5ea93a8c1bde9adf0c69fb69f83ebc61eeda774100baecc397a7e5b075d","source":{"kind":"arxiv","id":"2605.28625","version":1},"attestation_state":"computed","paper":{"title":"Random Process Flow Matching: Generative Implicit Representations of Multivariate Random Fields","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Picard, Jean-Michel Pereira, Julien Lalanne, Leon Barens, Lina-Mar\\'ia Guayac\\'an-Carrillo, Lionel Boillot","submitted_at":"2026-05-27T15:31:29Z","abstract_excerpt":"Generative modeling provides a powerful framework for learning data distributions. These models initially relied on probabilistic methods such as Gaussian Processes (GP) for uncertainty-aware predictions and shifted towards larger trainable models to learn more complex distributions. In this work, we introduce Random Process (RP) Flow, a Flow Matching-based framework that represents the vector field as a neural implicit function. Unlike modern generative methods, our setting involves a single observed field, from which only sparse measurements are available. RP Flow uses Random Fourier Feature"},"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":"2605.28625","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T15:31:29Z","cross_cats_sorted":[],"title_canon_sha256":"82b9a9fd8c0c8fdedf5a5bee213e28930cc129c1703607f0dbe8aae7f0c5a055","abstract_canon_sha256":"2791b020e1f0527beb75276829a591cf0cf522a85ede054fdc7c472e67ad8997"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:58.112360Z","signature_b64":"tkl9hj5zBaYqK1H2jmx2InsdYE26/3ptOi7qJgucPjZ7CZsrB/6FTlxX/OEoJR6LyCxh/OK1Xh3wRy+jAbN+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91c2b5ea93a8c1bde9adf0c69fb69f83ebc61eeda774100baecc397a7e5b075d","last_reissued_at":"2026-05-28T02:04:58.111945Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:58.111945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Random Process Flow Matching: Generative Implicit Representations of Multivariate Random Fields","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Picard, Jean-Michel Pereira, Julien Lalanne, Leon Barens, Lina-Mar\\'ia Guayac\\'an-Carrillo, Lionel Boillot","submitted_at":"2026-05-27T15:31:29Z","abstract_excerpt":"Generative modeling provides a powerful framework for learning data distributions. These models initially relied on probabilistic methods such as Gaussian Processes (GP) for uncertainty-aware predictions and shifted towards larger trainable models to learn more complex distributions. In this work, we introduce Random Process (RP) Flow, a Flow Matching-based framework that represents the vector field as a neural implicit function. Unlike modern generative methods, our setting involves a single observed field, from which only sparse measurements are available. RP Flow uses Random Fourier Feature"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28625","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/2605.28625/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":"2605.28625","created_at":"2026-05-28T02:04:58.112003+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28625v1","created_at":"2026-05-28T02:04:58.112003+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28625","created_at":"2026-05-28T02:04:58.112003+00:00"},{"alias_kind":"pith_short_12","alias_value":"SHBLL2UTVDA3","created_at":"2026-05-28T02:04:58.112003+00:00"},{"alias_kind":"pith_short_16","alias_value":"SHBLL2UTVDA332NN","created_at":"2026-05-28T02:04:58.112003+00:00"},{"alias_kind":"pith_short_8","alias_value":"SHBLL2UT","created_at":"2026-05-28T02:04:58.112003+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/SHBLL2UTVDA332NN6DDJ7NU7QP","json":"https://pith.science/pith/SHBLL2UTVDA332NN6DDJ7NU7QP.json","graph_json":"https://pith.science/api/pith-number/SHBLL2UTVDA332NN6DDJ7NU7QP/graph.json","events_json":"https://pith.science/api/pith-number/SHBLL2UTVDA332NN6DDJ7NU7QP/events.json","paper":"https://pith.science/paper/SHBLL2UT"},"agent_actions":{"view_html":"https://pith.science/pith/SHBLL2UTVDA332NN6DDJ7NU7QP","download_json":"https://pith.science/pith/SHBLL2UTVDA332NN6DDJ7NU7QP.json","view_paper":"https://pith.science/paper/SHBLL2UT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28625&json=true","fetch_graph":"https://pith.science/api/pith-number/SHBLL2UTVDA332NN6DDJ7NU7QP/graph.json","fetch_events":"https://pith.science/api/pith-number/SHBLL2UTVDA332NN6DDJ7NU7QP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SHBLL2UTVDA332NN6DDJ7NU7QP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SHBLL2UTVDA332NN6DDJ7NU7QP/action/storage_attestation","attest_author":"https://pith.science/pith/SHBLL2UTVDA332NN6DDJ7NU7QP/action/author_attestation","sign_citation":"https://pith.science/pith/SHBLL2UTVDA332NN6DDJ7NU7QP/action/citation_signature","submit_replication":"https://pith.science/pith/SHBLL2UTVDA332NN6DDJ7NU7QP/action/replication_record"}},"created_at":"2026-05-28T02:04:58.112003+00:00","updated_at":"2026-05-28T02:04:58.112003+00:00"}