{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XNWGXVB6MJZDZO4BT44NFSFCRV","short_pith_number":"pith:XNWGXVB6","schema_version":"1.0","canonical_sha256":"bb6c6bd43e62723cbb819f38d2c8a28d76a63f0385e4d75bd714c8a126c3fccb","source":{"kind":"arxiv","id":"2505.07124","version":3},"attestation_state":"computed","paper":{"title":"Learning from samples: inverse problems over measures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Clarice Poon, Francisco Andrade, Gabriel Peyr\\'e","submitted_at":"2025-05-11T21:26:44Z","abstract_excerpt":"We study inverse problems where an unknown potential is observed only through samples from the measure it induces by a convex variational principle. Such problems arise in learning costs, energies, and dynamics from distributional data, but the associated forward solution map is typically nonlinear and implicit. We show that its optimality gap nevertheless yields convex empirical objectives for finite-dimensional potential classes, and we introduce sharpened Fenchel--Young losses that add a data-dependent discrepancy inside the forward problem. This keeps the estimator calibrated while improvi"},"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":"2505.07124","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-11T21:26:44Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"385011fb719e58d71c6ff6ee4e5270ccf89b6dce0ea75173c15e4d857a823b09","abstract_canon_sha256":"2c5bd4a90ad0a8e859dddc3efae6adf82d5769bc382a3b011cfe9d1c26d1ab68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:16:51.284292Z","signature_b64":"oQ83GXUuK8SZldsITdKOwirl9RwHW/BS6EzydW9yXTrsVdQP6jVOT/sioVDoEQwXCa/wvp3bWvUMb2dxJleHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb6c6bd43e62723cbb819f38d2c8a28d76a63f0385e4d75bd714c8a126c3fccb","last_reissued_at":"2026-06-30T02:16:51.283352Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:16:51.283352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from samples: inverse problems over measures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Clarice Poon, Francisco Andrade, Gabriel Peyr\\'e","submitted_at":"2025-05-11T21:26:44Z","abstract_excerpt":"We study inverse problems where an unknown potential is observed only through samples from the measure it induces by a convex variational principle. Such problems arise in learning costs, energies, and dynamics from distributional data, but the associated forward solution map is typically nonlinear and implicit. We show that its optimality gap nevertheless yields convex empirical objectives for finite-dimensional potential classes, and we introduce sharpened Fenchel--Young losses that add a data-dependent discrepancy inside the forward problem. This keeps the estimator calibrated while improvi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07124","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/2505.07124/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":"2505.07124","created_at":"2026-06-30T02:16:51.283475+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07124v3","created_at":"2026-06-30T02:16:51.283475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07124","created_at":"2026-06-30T02:16:51.283475+00:00"},{"alias_kind":"pith_short_12","alias_value":"XNWGXVB6MJZD","created_at":"2026-06-30T02:16:51.283475+00:00"},{"alias_kind":"pith_short_16","alias_value":"XNWGXVB6MJZDZO4B","created_at":"2026-06-30T02:16:51.283475+00:00"},{"alias_kind":"pith_short_8","alias_value":"XNWGXVB6","created_at":"2026-06-30T02:16:51.283475+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.24987","citing_title":"Sample complexity of unbalanced entropic OT","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2510.03803","citing_title":"Well-Posedness and Efficient Algorithms for Inverse Optimal Transport with Bregman Regularization","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XNWGXVB6MJZDZO4BT44NFSFCRV","json":"https://pith.science/pith/XNWGXVB6MJZDZO4BT44NFSFCRV.json","graph_json":"https://pith.science/api/pith-number/XNWGXVB6MJZDZO4BT44NFSFCRV/graph.json","events_json":"https://pith.science/api/pith-number/XNWGXVB6MJZDZO4BT44NFSFCRV/events.json","paper":"https://pith.science/paper/XNWGXVB6"},"agent_actions":{"view_html":"https://pith.science/pith/XNWGXVB6MJZDZO4BT44NFSFCRV","download_json":"https://pith.science/pith/XNWGXVB6MJZDZO4BT44NFSFCRV.json","view_paper":"https://pith.science/paper/XNWGXVB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07124&json=true","fetch_graph":"https://pith.science/api/pith-number/XNWGXVB6MJZDZO4BT44NFSFCRV/graph.json","fetch_events":"https://pith.science/api/pith-number/XNWGXVB6MJZDZO4BT44NFSFCRV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XNWGXVB6MJZDZO4BT44NFSFCRV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XNWGXVB6MJZDZO4BT44NFSFCRV/action/storage_attestation","attest_author":"https://pith.science/pith/XNWGXVB6MJZDZO4BT44NFSFCRV/action/author_attestation","sign_citation":"https://pith.science/pith/XNWGXVB6MJZDZO4BT44NFSFCRV/action/citation_signature","submit_replication":"https://pith.science/pith/XNWGXVB6MJZDZO4BT44NFSFCRV/action/replication_record"}},"created_at":"2026-06-30T02:16:51.283475+00:00","updated_at":"2026-06-30T02:16:51.283475+00:00"}