{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4ZUJOLCBGDXW6RQWNTDXZOK7Y5","short_pith_number":"pith:4ZUJOLCB","schema_version":"1.0","canonical_sha256":"e668972c4130ef6f46166cc77cb95fc75b267bb6ba7512e357958ee8106ce934","source":{"kind":"arxiv","id":"2606.01954","version":1},"attestation_state":"computed","paper":{"title":"Flow-Transformed Implicit Processes for Function-Space Variational Inference","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andr\\'es R. Masegosa, Luis A. Ortega, Thomas D. Nielsen","submitted_at":"2026-06-01T09:14:09Z","abstract_excerpt":"Implicit-process priors define distributions over functions through flexible generative mechanisms, making them attractive for Bayesian function-space modelling. However, performing posterior inference with such priors is challenging because their induced function-space distributions are typically not available in closed form. One practical strategy is to approximate the prior using a finite collection of sampled functions, and then represent posterior functions as learned combinations of these samples. Existing approaches commonly place a Gaussian variational distribution over the combination"},"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":"2606.01954","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T09:14:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6f0a780ac5446f53f2550e5f7fe5a04f59fcbe17304798c745ea40d54e47ae24","abstract_canon_sha256":"471e9ce69f230647120b83ff92c34750720074c9c28a7e81c113a993d655e5f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:05:01.546767Z","signature_b64":"4yOzSHtcqJXxe7hkyT3B0VyQoVS/i10oeOCp3etqg56JYrpEA4kG238cWWnUqdl2AOHNiMzs4CAIaMGUx76fCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e668972c4130ef6f46166cc77cb95fc75b267bb6ba7512e357958ee8106ce934","last_reissued_at":"2026-06-02T02:05:01.546366Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:05:01.546366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow-Transformed Implicit Processes for Function-Space Variational Inference","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andr\\'es R. Masegosa, Luis A. Ortega, Thomas D. Nielsen","submitted_at":"2026-06-01T09:14:09Z","abstract_excerpt":"Implicit-process priors define distributions over functions through flexible generative mechanisms, making them attractive for Bayesian function-space modelling. However, performing posterior inference with such priors is challenging because their induced function-space distributions are typically not available in closed form. One practical strategy is to approximate the prior using a finite collection of sampled functions, and then represent posterior functions as learned combinations of these samples. Existing approaches commonly place a Gaussian variational distribution over the combination"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01954","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/2606.01954/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":"2606.01954","created_at":"2026-06-02T02:05:01.546423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01954v1","created_at":"2026-06-02T02:05:01.546423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01954","created_at":"2026-06-02T02:05:01.546423+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZUJOLCBGDXW","created_at":"2026-06-02T02:05:01.546423+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZUJOLCBGDXW6RQW","created_at":"2026-06-02T02:05:01.546423+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZUJOLCB","created_at":"2026-06-02T02:05:01.546423+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/4ZUJOLCBGDXW6RQWNTDXZOK7Y5","json":"https://pith.science/pith/4ZUJOLCBGDXW6RQWNTDXZOK7Y5.json","graph_json":"https://pith.science/api/pith-number/4ZUJOLCBGDXW6RQWNTDXZOK7Y5/graph.json","events_json":"https://pith.science/api/pith-number/4ZUJOLCBGDXW6RQWNTDXZOK7Y5/events.json","paper":"https://pith.science/paper/4ZUJOLCB"},"agent_actions":{"view_html":"https://pith.science/pith/4ZUJOLCBGDXW6RQWNTDXZOK7Y5","download_json":"https://pith.science/pith/4ZUJOLCBGDXW6RQWNTDXZOK7Y5.json","view_paper":"https://pith.science/paper/4ZUJOLCB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01954&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZUJOLCBGDXW6RQWNTDXZOK7Y5/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZUJOLCBGDXW6RQWNTDXZOK7Y5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZUJOLCBGDXW6RQWNTDXZOK7Y5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZUJOLCBGDXW6RQWNTDXZOK7Y5/action/storage_attestation","attest_author":"https://pith.science/pith/4ZUJOLCBGDXW6RQWNTDXZOK7Y5/action/author_attestation","sign_citation":"https://pith.science/pith/4ZUJOLCBGDXW6RQWNTDXZOK7Y5/action/citation_signature","submit_replication":"https://pith.science/pith/4ZUJOLCBGDXW6RQWNTDXZOK7Y5/action/replication_record"}},"created_at":"2026-06-02T02:05:01.546423+00:00","updated_at":"2026-06-02T02:05:01.546423+00:00"}