{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:44ATN63WT6MLGAKSHRWYMNZ4X7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fb4200af67d5f2a83d5db1b1eccd76bc8c87a56a4cd7f37b35d5518f1b3b3aca","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-18T17:47:02Z","title_canon_sha256":"2cde9bf30fcb038ea11e388ad0f183fba6cc8fef621364e8fe1fdbe51282a28a"},"schema_version":"1.0","source":{"id":"1812.07526","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.07526","created_at":"2026-07-05T00:20:42Z"},{"alias_kind":"arxiv_version","alias_value":"1812.07526v2","created_at":"2026-07-05T00:20:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.07526","created_at":"2026-07-05T00:20:42Z"},{"alias_kind":"pith_short_12","alias_value":"44ATN63WT6ML","created_at":"2026-07-05T00:20:42Z"},{"alias_kind":"pith_short_16","alias_value":"44ATN63WT6MLGAKS","created_at":"2026-07-05T00:20:42Z"},{"alias_kind":"pith_short_8","alias_value":"44ATN63W","created_at":"2026-07-05T00:20:42Z"}],"graph_snapshots":[{"event_id":"sha256:c5ecd9d4416b71f9b5067c8aaa85befef012aa3cd8bb0a3a3e351256299c3451","target":"graph","created_at":"2026-07-05T00:20:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1812.07526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a robust adversarial prediction framework for general multiclass classification. Our method seeks predictive distributions that robustly optimize non-convex and non-continuous multiclass loss metrics against the worst-case conditional label distributions (the adversarial distributions) that (approximately) match the statistics of the training data. Although the optimized loss metrics are non-convex and non-continuous, the dual formulation of the framework is a convex optimization problem that can be recast as a risk minimization model with a prescribed convex surrogate loss we call ","authors_text":"Anqi Liu, Brian D. Ziebart, Kaiser Asif, Mohammad Ali Bashiri, Rizal Fathony, Sima Behpour, Wei Xing, Xinhua Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-18T17:47:02Z","title":"Consistent Robust Adversarial Prediction for General Multiclass Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.07526","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b249f82356afda53d94335c6281c52640351fdc9fcc24da27e2f1d37fb4d6ec7","target":"record","created_at":"2026-07-05T00:20:42Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fb4200af67d5f2a83d5db1b1eccd76bc8c87a56a4cd7f37b35d5518f1b3b3aca","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-18T17:47:02Z","title_canon_sha256":"2cde9bf30fcb038ea11e388ad0f183fba6cc8fef621364e8fe1fdbe51282a28a"},"schema_version":"1.0","source":{"id":"1812.07526","kind":"arxiv","version":2}},"canonical_sha256":"e70136fb769f98b301523c6d86373cbfcbd405f588b05b2978a958100513f380","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e70136fb769f98b301523c6d86373cbfcbd405f588b05b2978a958100513f380","first_computed_at":"2026-07-05T00:20:42.610980Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:20:42.610980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qCT6jTKn6hNyX1HlNbK14tu8KdrSOh9cHdSuJe5hXWMTRyPmvSyeVGz6U4tV1P0jloAZhfv7O4vBOPIdJckUAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:20:42.611498Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.07526","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b249f82356afda53d94335c6281c52640351fdc9fcc24da27e2f1d37fb4d6ec7","sha256:c5ecd9d4416b71f9b5067c8aaa85befef012aa3cd8bb0a3a3e351256299c3451"],"state_sha256":"c04189e7996f09a401e661b8e141eca3cc3c87bd0181731be3edff5471742734"}