{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PF2N2PQGVQH2ZZ2EFCZWVRIHDL","short_pith_number":"pith:PF2N2PQG","schema_version":"1.0","canonical_sha256":"7974dd3e06ac0face74428b36ac5071ad369f7a4b5507be0f7ddc7c5add6d872","source":{"kind":"arxiv","id":"2603.01949","version":2},"attestation_state":"computed","paper":{"title":"Probabilistic Retrofitting of Learned Simulators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE"],"primary_cat":"cs.LG","authors_text":"Cristiana Diaconu, Miles Cranmer, Payel Mukhopadhyay, Richard E. Turner, Tanya Marwah","submitted_at":"2026-03-02T15:01:02Z","abstract_excerpt":"Dominant approaches for modelling Partial Differential Equations (PDEs) rely on deterministic predictions, yet many physical systems of interest are inherently chaotic and uncertain. While training probabilistic models from scratch is possible, it is computationally expensive and fails to leverage the significant resources already invested in high-performing deterministic backbones. In this work, we adopt a training-efficient strategy to transform pre-trained deterministic models into probabilistic ones via retrofitting with a proper scoring rule: the Continuous Ranked Probability Score (CRPS)"},"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":"2603.01949","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-02T15:01:02Z","cross_cats_sorted":["cs.AI","cs.CE"],"title_canon_sha256":"7b950b9e2ebf8e86c88547c41ccac6f7dc5aecd81224702911273363cc0c53b5","abstract_canon_sha256":"f7867e8f38d9eadb22901f1267699acf431a7617902c57841c246ea92f4062c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:54.957684Z","signature_b64":"rSnUvUTv1mLwvWn11YFiLu8CPHrXuOSy4ltCbpsuadLc0hPLRmeWBo9gXiaOjUJvbufwTbVxpTobaBWjnOJ3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7974dd3e06ac0face74428b36ac5071ad369f7a4b5507be0f7ddc7c5add6d872","last_reissued_at":"2026-06-23T03:13:54.957192Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:54.957192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Retrofitting of Learned Simulators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE"],"primary_cat":"cs.LG","authors_text":"Cristiana Diaconu, Miles Cranmer, Payel Mukhopadhyay, Richard E. Turner, Tanya Marwah","submitted_at":"2026-03-02T15:01:02Z","abstract_excerpt":"Dominant approaches for modelling Partial Differential Equations (PDEs) rely on deterministic predictions, yet many physical systems of interest are inherently chaotic and uncertain. While training probabilistic models from scratch is possible, it is computationally expensive and fails to leverage the significant resources already invested in high-performing deterministic backbones. In this work, we adopt a training-efficient strategy to transform pre-trained deterministic models into probabilistic ones via retrofitting with a proper scoring rule: the Continuous Ranked Probability Score (CRPS)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.01949","kind":"arxiv","version":2},"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/2603.01949/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":"2603.01949","created_at":"2026-06-23T03:13:54.957254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.01949v2","created_at":"2026-06-23T03:13:54.957254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.01949","created_at":"2026-06-23T03:13:54.957254+00:00"},{"alias_kind":"pith_short_12","alias_value":"PF2N2PQGVQH2","created_at":"2026-06-23T03:13:54.957254+00:00"},{"alias_kind":"pith_short_16","alias_value":"PF2N2PQGVQH2ZZ2E","created_at":"2026-06-23T03:13:54.957254+00:00"},{"alias_kind":"pith_short_8","alias_value":"PF2N2PQG","created_at":"2026-06-23T03:13:54.957254+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.31547","citing_title":"The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09041","citing_title":"U-Cast: A Surprisingly Simple and Efficient Frontier Probabilistic AI Weather Forecaster","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PF2N2PQGVQH2ZZ2EFCZWVRIHDL","json":"https://pith.science/pith/PF2N2PQGVQH2ZZ2EFCZWVRIHDL.json","graph_json":"https://pith.science/api/pith-number/PF2N2PQGVQH2ZZ2EFCZWVRIHDL/graph.json","events_json":"https://pith.science/api/pith-number/PF2N2PQGVQH2ZZ2EFCZWVRIHDL/events.json","paper":"https://pith.science/paper/PF2N2PQG"},"agent_actions":{"view_html":"https://pith.science/pith/PF2N2PQGVQH2ZZ2EFCZWVRIHDL","download_json":"https://pith.science/pith/PF2N2PQGVQH2ZZ2EFCZWVRIHDL.json","view_paper":"https://pith.science/paper/PF2N2PQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.01949&json=true","fetch_graph":"https://pith.science/api/pith-number/PF2N2PQGVQH2ZZ2EFCZWVRIHDL/graph.json","fetch_events":"https://pith.science/api/pith-number/PF2N2PQGVQH2ZZ2EFCZWVRIHDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PF2N2PQGVQH2ZZ2EFCZWVRIHDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PF2N2PQGVQH2ZZ2EFCZWVRIHDL/action/storage_attestation","attest_author":"https://pith.science/pith/PF2N2PQGVQH2ZZ2EFCZWVRIHDL/action/author_attestation","sign_citation":"https://pith.science/pith/PF2N2PQGVQH2ZZ2EFCZWVRIHDL/action/citation_signature","submit_replication":"https://pith.science/pith/PF2N2PQGVQH2ZZ2EFCZWVRIHDL/action/replication_record"}},"created_at":"2026-06-23T03:13:54.957254+00:00","updated_at":"2026-06-23T03:13:54.957254+00:00"}