{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BMCEFNL3ZH37BNDR6UE4QNN374","short_pith_number":"pith:BMCEFNL3","schema_version":"1.0","canonical_sha256":"0b0442b57bc9f7f0b471f509c835bbff12d52c38dede2a7b7ebb3e10a390d121","source":{"kind":"arxiv","id":"2410.03229","version":3},"attestation_state":"computed","paper":{"title":"Elucidating the Design Choice of Probability Paths in Flow Matching for Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Annan Yu, Emma Hart, Michael W. Mahoney, N. Benjamin Erichson, Soon Hoe Lim, Xiaoye S. Li, Yijin Wang","submitted_at":"2024-10-04T08:34:14Z","abstract_excerpt":"Flow matching has recently emerged as a powerful paradigm for generative modeling and has been extended to probabilistic time series forecasting in latent spaces. However, the impact of the specific choice of probability path model on forecasting performance remains under-explored. In this work, we demonstrate that forecasting spatio-temporal data with flow matching is highly sensitive to the selection of the probability path model. Motivated by this insight, we propose a novel probability path model designed to improve forecasting performance. Our empirical results across various dynamical sy"},"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":"2410.03229","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-10-04T08:34:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"13a24c41e4a2495fb59faee6c4cd557dffd45bf611345001d1824817d136a571","abstract_canon_sha256":"893635d480746ca690d556a3716858dc5cb8338e47dd574f1b5c7b6173085d86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:41.898040Z","signature_b64":"G7qZou6gb19yn64EPiA719Hu6lWT0gC8kbotSxoH2jA05b2d0/A420rLuF1/5HGh4nJor2bVJhX7FwnPyevCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b0442b57bc9f7f0b471f509c835bbff12d52c38dede2a7b7ebb3e10a390d121","last_reissued_at":"2026-07-05T11:54:41.897494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:41.897494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Elucidating the Design Choice of Probability Paths in Flow Matching for Forecasting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Annan Yu, Emma Hart, Michael W. Mahoney, N. Benjamin Erichson, Soon Hoe Lim, Xiaoye S. Li, Yijin Wang","submitted_at":"2024-10-04T08:34:14Z","abstract_excerpt":"Flow matching has recently emerged as a powerful paradigm for generative modeling and has been extended to probabilistic time series forecasting in latent spaces. However, the impact of the specific choice of probability path model on forecasting performance remains under-explored. In this work, we demonstrate that forecasting spatio-temporal data with flow matching is highly sensitive to the selection of the probability path model. Motivated by this insight, we propose a novel probability path model designed to improve forecasting performance. Our empirical results across various dynamical sy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03229","kind":"arxiv","version":3},"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/2410.03229/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":"2410.03229","created_at":"2026-07-05T11:54:41.897585+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03229v3","created_at":"2026-07-05T11:54:41.897585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03229","created_at":"2026-07-05T11:54:41.897585+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMCEFNL3ZH37","created_at":"2026-07-05T11:54:41.897585+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMCEFNL3ZH37BNDR","created_at":"2026-07-05T11:54:41.897585+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMCEFNL3","created_at":"2026-07-05T11:54:41.897585+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.24517","citing_title":"Physics Priors Offer Useful Accuracy-Carbon Trade-Offs in Spatio-Temporal Forecasting","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10989","citing_title":"Variational Optimality of F\\\"ollmer Processes in Generative Diffusions","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2512.16768","citing_title":"On The Hidden Biases of Flow Matching Samplers","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07366","citing_title":"Flow Learners for PDEs: Toward a Physics-to-Physics Paradigm for Scientific Computing","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BMCEFNL3ZH37BNDR6UE4QNN374","json":"https://pith.science/pith/BMCEFNL3ZH37BNDR6UE4QNN374.json","graph_json":"https://pith.science/api/pith-number/BMCEFNL3ZH37BNDR6UE4QNN374/graph.json","events_json":"https://pith.science/api/pith-number/BMCEFNL3ZH37BNDR6UE4QNN374/events.json","paper":"https://pith.science/paper/BMCEFNL3"},"agent_actions":{"view_html":"https://pith.science/pith/BMCEFNL3ZH37BNDR6UE4QNN374","download_json":"https://pith.science/pith/BMCEFNL3ZH37BNDR6UE4QNN374.json","view_paper":"https://pith.science/paper/BMCEFNL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03229&json=true","fetch_graph":"https://pith.science/api/pith-number/BMCEFNL3ZH37BNDR6UE4QNN374/graph.json","fetch_events":"https://pith.science/api/pith-number/BMCEFNL3ZH37BNDR6UE4QNN374/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMCEFNL3ZH37BNDR6UE4QNN374/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMCEFNL3ZH37BNDR6UE4QNN374/action/storage_attestation","attest_author":"https://pith.science/pith/BMCEFNL3ZH37BNDR6UE4QNN374/action/author_attestation","sign_citation":"https://pith.science/pith/BMCEFNL3ZH37BNDR6UE4QNN374/action/citation_signature","submit_replication":"https://pith.science/pith/BMCEFNL3ZH37BNDR6UE4QNN374/action/replication_record"}},"created_at":"2026-07-05T11:54:41.897585+00:00","updated_at":"2026-07-05T11:54:41.897585+00:00"}