{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YXVGFMA6XLB4RS4TCVBOVG3OTP","short_pith_number":"pith:YXVGFMA6","schema_version":"1.0","canonical_sha256":"c5ea62b01ebac3c8cb931542ea9b6e9bfa8aeb47f055cca19483e1a75b5a40aa","source":{"kind":"arxiv","id":"2601.23231","version":2},"attestation_state":"computed","paper":{"title":"Solving Inverse Problems with Flow-based Models via Model Predictive Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.IV","authors_text":"Alexander Denker, Andrew J Reader, George Webber, Riccardo Barbano","submitted_at":"2026-01-30T17:59:09Z","abstract_excerpt":"Flow-based generative models provide strong unconditional priors for inverse problems, but guiding their dynamics for conditional generation remains challenging. Recent work casts training-free conditional generation in flow models as an optimal control problem; however, solving the resulting trajectory optimisation is computationally and memory intensive, requiring differentiation through the flow dynamics or adjoint solves. We propose MPC-Flow, a model predictive control framework that formulates inverse problem solving with flow-based generative models as a sequence of control sub-problems,"},"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":"2601.23231","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-01-30T17:59:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c27da3cca3543e9a9f8a690205428c3bd7f69160d3141b8cabd7d60bdb2bc24f","abstract_canon_sha256":"7df17fc7c753b6c77daecdd504e2d0d3f0a9bcf1413b618e4459afb31c31655a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:38.043834Z","signature_b64":"UqOx/SV/1FIKJaEbvqccFKxibUEDzyDwHD1s/OdlrM6Mm6G9UrFYTzWktnDMxRgSJk3+my8Y76cEJMaxvz1vCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5ea62b01ebac3c8cb931542ea9b6e9bfa8aeb47f055cca19483e1a75b5a40aa","last_reissued_at":"2026-06-09T02:08:38.042658Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:38.042658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving Inverse Problems with Flow-based Models via Model Predictive Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"eess.IV","authors_text":"Alexander Denker, Andrew J Reader, George Webber, Riccardo Barbano","submitted_at":"2026-01-30T17:59:09Z","abstract_excerpt":"Flow-based generative models provide strong unconditional priors for inverse problems, but guiding their dynamics for conditional generation remains challenging. Recent work casts training-free conditional generation in flow models as an optimal control problem; however, solving the resulting trajectory optimisation is computationally and memory intensive, requiring differentiation through the flow dynamics or adjoint solves. We propose MPC-Flow, a model predictive control framework that formulates inverse problem solving with flow-based generative models as a sequence of control sub-problems,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.23231","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/2601.23231/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":"2601.23231","created_at":"2026-06-09T02:08:38.042771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.23231v2","created_at":"2026-06-09T02:08:38.042771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.23231","created_at":"2026-06-09T02:08:38.042771+00:00"},{"alias_kind":"pith_short_12","alias_value":"YXVGFMA6XLB4","created_at":"2026-06-09T02:08:38.042771+00:00"},{"alias_kind":"pith_short_16","alias_value":"YXVGFMA6XLB4RS4T","created_at":"2026-06-09T02:08:38.042771+00:00"},{"alias_kind":"pith_short_8","alias_value":"YXVGFMA6","created_at":"2026-06-09T02:08:38.042771+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.10076","citing_title":"A Stability Benchmark of Generative Regularizers for Inverse Problems","ref_index":202,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YXVGFMA6XLB4RS4TCVBOVG3OTP","json":"https://pith.science/pith/YXVGFMA6XLB4RS4TCVBOVG3OTP.json","graph_json":"https://pith.science/api/pith-number/YXVGFMA6XLB4RS4TCVBOVG3OTP/graph.json","events_json":"https://pith.science/api/pith-number/YXVGFMA6XLB4RS4TCVBOVG3OTP/events.json","paper":"https://pith.science/paper/YXVGFMA6"},"agent_actions":{"view_html":"https://pith.science/pith/YXVGFMA6XLB4RS4TCVBOVG3OTP","download_json":"https://pith.science/pith/YXVGFMA6XLB4RS4TCVBOVG3OTP.json","view_paper":"https://pith.science/paper/YXVGFMA6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.23231&json=true","fetch_graph":"https://pith.science/api/pith-number/YXVGFMA6XLB4RS4TCVBOVG3OTP/graph.json","fetch_events":"https://pith.science/api/pith-number/YXVGFMA6XLB4RS4TCVBOVG3OTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YXVGFMA6XLB4RS4TCVBOVG3OTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YXVGFMA6XLB4RS4TCVBOVG3OTP/action/storage_attestation","attest_author":"https://pith.science/pith/YXVGFMA6XLB4RS4TCVBOVG3OTP/action/author_attestation","sign_citation":"https://pith.science/pith/YXVGFMA6XLB4RS4TCVBOVG3OTP/action/citation_signature","submit_replication":"https://pith.science/pith/YXVGFMA6XLB4RS4TCVBOVG3OTP/action/replication_record"}},"created_at":"2026-06-09T02:08:38.042771+00:00","updated_at":"2026-06-09T02:08:38.042771+00:00"}