{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MUUWZO6ENRPMLFYFYM2GFRTJDD","short_pith_number":"pith:MUUWZO6E","schema_version":"1.0","canonical_sha256":"65296cbbc46c5ec59705c33462c66918cd62264d92cf4943e75f45a5dd024fef","source":{"kind":"arxiv","id":"2508.13355","version":2},"attestation_state":"computed","paper":{"title":"Counterfactual Probabilistic Diffusion with Expert Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ME"],"primary_cat":"cs.LG","authors_text":"Alexander Rodr\\'iguez, Mehmed Uludag, Wenhao Mu, Zhi Cao","submitted_at":"2025-08-18T20:44:32Z","abstract_excerpt":"Predicting counterfactual distributions in complex dynamical systems is essential for scientific modeling and decision-making in domains such as public health and medicine. However, existing methods often rely on point estimates or purely data-driven models, which tend to falter under data scarcity. We propose a time series diffusion-based framework that incorporates guidance from imperfect expert models by extracting high-level signals to serve as structured priors for generative modeling. Our method, ODE-Diff, bridges mechanistic and data-driven approaches, enabling more reliable and interpr"},"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":"2508.13355","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-18T20:44:32Z","cross_cats_sorted":["cs.AI","stat.ME"],"title_canon_sha256":"77e7aaef105cb6323354804a9bc3678cf23ec551fafaef6b7a8f898089857f42","abstract_canon_sha256":"7bcbc1657c6e33bf86baecc6c5702e742682c04ff9a730211d7b7a51479e8e22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:45.874264Z","signature_b64":"haiCBsmFPspBpibpWUgucK0tZLxVjTXXJpqt+HfE+ZSYetgab3XcUc5xrFbxVLZfjuChrWFYXHVGBCPHgFhFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65296cbbc46c5ec59705c33462c66918cd62264d92cf4943e75f45a5dd024fef","last_reissued_at":"2026-07-05T12:09:45.873781Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:45.873781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counterfactual Probabilistic Diffusion with Expert Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ME"],"primary_cat":"cs.LG","authors_text":"Alexander Rodr\\'iguez, Mehmed Uludag, Wenhao Mu, Zhi Cao","submitted_at":"2025-08-18T20:44:32Z","abstract_excerpt":"Predicting counterfactual distributions in complex dynamical systems is essential for scientific modeling and decision-making in domains such as public health and medicine. However, existing methods often rely on point estimates or purely data-driven models, which tend to falter under data scarcity. We propose a time series diffusion-based framework that incorporates guidance from imperfect expert models by extracting high-level signals to serve as structured priors for generative modeling. Our method, ODE-Diff, bridges mechanistic and data-driven approaches, enabling more reliable and interpr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13355","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/2508.13355/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":"2508.13355","created_at":"2026-07-05T12:09:45.873838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13355v2","created_at":"2026-07-05T12:09:45.873838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13355","created_at":"2026-07-05T12:09:45.873838+00:00"},{"alias_kind":"pith_short_12","alias_value":"MUUWZO6ENRPM","created_at":"2026-07-05T12:09:45.873838+00:00"},{"alias_kind":"pith_short_16","alias_value":"MUUWZO6ENRPMLFYF","created_at":"2026-07-05T12:09:45.873838+00:00"},{"alias_kind":"pith_short_8","alias_value":"MUUWZO6E","created_at":"2026-07-05T12:09:45.873838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05692","citing_title":"Benchmarking Counterfactual Prediction in Epidemic Time Series with Time-Varying Interventions","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04375","citing_title":"Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14422","citing_title":"What if Tomorrow is the World Cup Final? Counterfactual Time Series Forecasting with Textual Conditions","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04375","citing_title":"Experiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific Discovery","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MUUWZO6ENRPMLFYFYM2GFRTJDD","json":"https://pith.science/pith/MUUWZO6ENRPMLFYFYM2GFRTJDD.json","graph_json":"https://pith.science/api/pith-number/MUUWZO6ENRPMLFYFYM2GFRTJDD/graph.json","events_json":"https://pith.science/api/pith-number/MUUWZO6ENRPMLFYFYM2GFRTJDD/events.json","paper":"https://pith.science/paper/MUUWZO6E"},"agent_actions":{"view_html":"https://pith.science/pith/MUUWZO6ENRPMLFYFYM2GFRTJDD","download_json":"https://pith.science/pith/MUUWZO6ENRPMLFYFYM2GFRTJDD.json","view_paper":"https://pith.science/paper/MUUWZO6E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13355&json=true","fetch_graph":"https://pith.science/api/pith-number/MUUWZO6ENRPMLFYFYM2GFRTJDD/graph.json","fetch_events":"https://pith.science/api/pith-number/MUUWZO6ENRPMLFYFYM2GFRTJDD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MUUWZO6ENRPMLFYFYM2GFRTJDD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MUUWZO6ENRPMLFYFYM2GFRTJDD/action/storage_attestation","attest_author":"https://pith.science/pith/MUUWZO6ENRPMLFYFYM2GFRTJDD/action/author_attestation","sign_citation":"https://pith.science/pith/MUUWZO6ENRPMLFYFYM2GFRTJDD/action/citation_signature","submit_replication":"https://pith.science/pith/MUUWZO6ENRPMLFYFYM2GFRTJDD/action/replication_record"}},"created_at":"2026-07-05T12:09:45.873838+00:00","updated_at":"2026-07-05T12:09:45.873838+00:00"}