{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:U5PXATX2NL5LMYG4E3SRIT7RVP","short_pith_number":"pith:U5PXATX2","schema_version":"1.0","canonical_sha256":"a75f704efa6afab660dc26e5144ff1abf3048c2cb548cd84520ff8f1f44aadf8","source":{"kind":"arxiv","id":"1710.10898","version":1},"attestation_state":"computed","paper":{"title":"Learning to solve inverse problems using Wasserstein loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.FA","math.OC"],"primary_cat":"cs.CV","authors_text":"Axel Ringh, Johan Karlsson, Jonas Adler, Ozan \\\"Oktem","submitted_at":"2017-10-30T12:30:16Z","abstract_excerpt":"We propose using the Wasserstein loss for training in inverse problems. In particular, we consider a learned primal-dual reconstruction scheme for ill-posed inverse problems using the Wasserstein distance as loss function in the learning. This is motivated by miss-alignments in training data, which when using standard mean squared error loss could severely degrade reconstruction quality. We prove that training with the Wasserstein loss gives a reconstruction operator that correctly compensates for miss-alignments in certain cases, whereas training with the mean squared error gives a smeared re"},"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":"1710.10898","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-10-30T12:30:16Z","cross_cats_sorted":["math.FA","math.OC"],"title_canon_sha256":"0fd3c5397362d9b3f2e0988e87ee62eb952b26b1758f5a9e95233b7bbd929292","abstract_canon_sha256":"4c9c2e79a0a8eaead835143664fb17ca1df32fd0d7cae19be3851b663dc06885"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:46.142165Z","signature_b64":"B7h0Dtjnm0iL2Bu0YnsETun7zsi8O/ontsqpdIBwtT4fLrv+vEoL0QQGszw1DDM51g6pSiObvTe+fosby0xBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a75f704efa6afab660dc26e5144ff1abf3048c2cb548cd84520ff8f1f44aadf8","last_reissued_at":"2026-05-18T00:31:46.141670Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:46.141670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to solve inverse problems using Wasserstein loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.FA","math.OC"],"primary_cat":"cs.CV","authors_text":"Axel Ringh, Johan Karlsson, Jonas Adler, Ozan \\\"Oktem","submitted_at":"2017-10-30T12:30:16Z","abstract_excerpt":"We propose using the Wasserstein loss for training in inverse problems. In particular, we consider a learned primal-dual reconstruction scheme for ill-posed inverse problems using the Wasserstein distance as loss function in the learning. This is motivated by miss-alignments in training data, which when using standard mean squared error loss could severely degrade reconstruction quality. We prove that training with the Wasserstein loss gives a reconstruction operator that correctly compensates for miss-alignments in certain cases, whereas training with the mean squared error gives a smeared re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10898","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1710.10898","created_at":"2026-05-18T00:31:46.141742+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.10898v1","created_at":"2026-05-18T00:31:46.141742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10898","created_at":"2026-05-18T00:31:46.141742+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5PXATX2NL5L","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5PXATX2NL5LMYG4","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5PXATX2","created_at":"2026-05-18T12:31:46.661854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2304.04451","citing_title":"Quantitative contraction rates for Sinkhorn's algorithm: beyond bounded costs and compact marginals","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5PXATX2NL5LMYG4E3SRIT7RVP","json":"https://pith.science/pith/U5PXATX2NL5LMYG4E3SRIT7RVP.json","graph_json":"https://pith.science/api/pith-number/U5PXATX2NL5LMYG4E3SRIT7RVP/graph.json","events_json":"https://pith.science/api/pith-number/U5PXATX2NL5LMYG4E3SRIT7RVP/events.json","paper":"https://pith.science/paper/U5PXATX2"},"agent_actions":{"view_html":"https://pith.science/pith/U5PXATX2NL5LMYG4E3SRIT7RVP","download_json":"https://pith.science/pith/U5PXATX2NL5LMYG4E3SRIT7RVP.json","view_paper":"https://pith.science/paper/U5PXATX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.10898&json=true","fetch_graph":"https://pith.science/api/pith-number/U5PXATX2NL5LMYG4E3SRIT7RVP/graph.json","fetch_events":"https://pith.science/api/pith-number/U5PXATX2NL5LMYG4E3SRIT7RVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5PXATX2NL5LMYG4E3SRIT7RVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5PXATX2NL5LMYG4E3SRIT7RVP/action/storage_attestation","attest_author":"https://pith.science/pith/U5PXATX2NL5LMYG4E3SRIT7RVP/action/author_attestation","sign_citation":"https://pith.science/pith/U5PXATX2NL5LMYG4E3SRIT7RVP/action/citation_signature","submit_replication":"https://pith.science/pith/U5PXATX2NL5LMYG4E3SRIT7RVP/action/replication_record"}},"created_at":"2026-05-18T00:31:46.141742+00:00","updated_at":"2026-05-18T00:31:46.141742+00:00"}