{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LBFU7DTC5IFDU7A6YCEC4VYSIH","short_pith_number":"pith:LBFU7DTC","schema_version":"1.0","canonical_sha256":"584b4f8e62ea0a3a7c1ec0882e571241c42d949ffdb3a3439eec0a72d1ee6f66","source":{"kind":"arxiv","id":"1902.01958","version":2},"attestation_state":"computed","paper":{"title":"A General Theory for Structured Prediction with Smooth Convex Surrogates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Rudi, Alex Nowak-Vila, Francis Bach","submitted_at":"2019-02-05T22:27:24Z","abstract_excerpt":"In this work we provide a theoretical framework for structured prediction that generalizes the existing theory of surrogate methods for binary and multiclass classification based on estimating conditional probabilities with smooth convex surrogates (e.g. logistic regression). The theory relies on a natural characterization of structural properties of the task loss and allows to derive statistical guarantees for many widely used methods in the context of multilabeling, ranking, ordinal regression and graph matching. In particular, we characterize the smooth convex surrogates compatible with a g"},"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":"1902.01958","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-05T22:27:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"b6c4d1039d5fc24faa35ad913aa1267ad1ffac69b6aa248e7801dc00a8fb38a9","abstract_canon_sha256":"30cb9b892fdbbcfe07cb10d0d5269c0298cb4da09f96c92c84d86ecb27e73ccc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:06.697335Z","signature_b64":"0mPUs1D7sFA9OO0oOYwFfKzIuOedXoG3A+GUJbHpRWgT6wu6Qr3YdrQAtaCdnPhhxxB/mk88sqTmQJqVaBT1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"584b4f8e62ea0a3a7c1ec0882e571241c42d949ffdb3a3439eec0a72d1ee6f66","last_reissued_at":"2026-05-17T23:54:06.696815Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:06.696815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A General Theory for Structured Prediction with Smooth Convex Surrogates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Rudi, Alex Nowak-Vila, Francis Bach","submitted_at":"2019-02-05T22:27:24Z","abstract_excerpt":"In this work we provide a theoretical framework for structured prediction that generalizes the existing theory of surrogate methods for binary and multiclass classification based on estimating conditional probabilities with smooth convex surrogates (e.g. logistic regression). The theory relies on a natural characterization of structural properties of the task loss and allows to derive statistical guarantees for many widely used methods in the context of multilabeling, ranking, ordinal regression and graph matching. In particular, we characterize the smooth convex surrogates compatible with a g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01958","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":""},"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":"1902.01958","created_at":"2026-05-17T23:54:06.696897+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.01958v2","created_at":"2026-05-17T23:54:06.696897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01958","created_at":"2026-05-17T23:54:06.696897+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBFU7DTC5IFD","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBFU7DTC5IFDU7A6","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBFU7DTC","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2407.17200","citing_title":"Generalization Bounds of Surrogate Policies for Combinatorial Optimization Problems","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LBFU7DTC5IFDU7A6YCEC4VYSIH","json":"https://pith.science/pith/LBFU7DTC5IFDU7A6YCEC4VYSIH.json","graph_json":"https://pith.science/api/pith-number/LBFU7DTC5IFDU7A6YCEC4VYSIH/graph.json","events_json":"https://pith.science/api/pith-number/LBFU7DTC5IFDU7A6YCEC4VYSIH/events.json","paper":"https://pith.science/paper/LBFU7DTC"},"agent_actions":{"view_html":"https://pith.science/pith/LBFU7DTC5IFDU7A6YCEC4VYSIH","download_json":"https://pith.science/pith/LBFU7DTC5IFDU7A6YCEC4VYSIH.json","view_paper":"https://pith.science/paper/LBFU7DTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.01958&json=true","fetch_graph":"https://pith.science/api/pith-number/LBFU7DTC5IFDU7A6YCEC4VYSIH/graph.json","fetch_events":"https://pith.science/api/pith-number/LBFU7DTC5IFDU7A6YCEC4VYSIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBFU7DTC5IFDU7A6YCEC4VYSIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBFU7DTC5IFDU7A6YCEC4VYSIH/action/storage_attestation","attest_author":"https://pith.science/pith/LBFU7DTC5IFDU7A6YCEC4VYSIH/action/author_attestation","sign_citation":"https://pith.science/pith/LBFU7DTC5IFDU7A6YCEC4VYSIH/action/citation_signature","submit_replication":"https://pith.science/pith/LBFU7DTC5IFDU7A6YCEC4VYSIH/action/replication_record"}},"created_at":"2026-05-17T23:54:06.696897+00:00","updated_at":"2026-05-17T23:54:06.696897+00:00"}