{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3M5QKF5XSWJP7XHBI656LCHLA2","short_pith_number":"pith:3M5QKF5X","canonical_record":{"source":{"id":"2306.04178","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T06:15:12Z","cross_cats_sorted":["cs.CG"],"title_canon_sha256":"b6be1a7ed2c4fe53bb0bc7d801ae3a5207d66e5096cac0ea9526fbbcf9dcdec4","abstract_canon_sha256":"bf0a385203255576444b61be1990dc9539ffc6a6d882f492fd5d3ac302169b51"},"schema_version":"1.0"},"canonical_sha256":"db3b0517b79592ffdce147bbe588eb06b46a4753b2f8bd3e52fb8ded178998ec","source":{"kind":"arxiv","id":"2306.04178","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04178","created_at":"2026-07-05T07:07:38Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04178v2","created_at":"2026-07-05T07:07:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04178","created_at":"2026-07-05T07:07:38Z"},{"alias_kind":"pith_short_12","alias_value":"3M5QKF5XSWJP","created_at":"2026-07-05T07:07:38Z"},{"alias_kind":"pith_short_16","alias_value":"3M5QKF5XSWJP7XHB","created_at":"2026-07-05T07:07:38Z"},{"alias_kind":"pith_short_8","alias_value":"3M5QKF5X","created_at":"2026-07-05T07:07:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3M5QKF5XSWJP7XHBI656LCHLA2","target":"record","payload":{"canonical_record":{"source":{"id":"2306.04178","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T06:15:12Z","cross_cats_sorted":["cs.CG"],"title_canon_sha256":"b6be1a7ed2c4fe53bb0bc7d801ae3a5207d66e5096cac0ea9526fbbcf9dcdec4","abstract_canon_sha256":"bf0a385203255576444b61be1990dc9539ffc6a6d882f492fd5d3ac302169b51"},"schema_version":"1.0"},"canonical_sha256":"db3b0517b79592ffdce147bbe588eb06b46a4753b2f8bd3e52fb8ded178998ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:38.311669Z","signature_b64":"Per172E1NXSg/tD0+GKyVImcpbIzPs3yqb0evGFGorzwOGObly/4Rm2wjyAgHHiXiUbssudkmpCnm1QmCcDeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db3b0517b79592ffdce147bbe588eb06b46a4753b2f8bd3e52fb8ded178998ec","last_reissued_at":"2026-07-05T07:07:38.311061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:38.311061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.04178","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:07:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e3O0XzoFFLvvVBz/MY7F97v6ST23Lf5MwykmG0UpU0aAV683+XouLzxCCKLLtEwRi97dZI9ColCIeNY00IaMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:59:46.819550Z"},"content_sha256":"25b3efc4b9ea7d06511b73511ee864788d2989235234871915916a4f90dc8f67","schema_version":"1.0","event_id":"sha256:25b3efc4b9ea7d06511b73511ee864788d2989235234871915916a4f90dc8f67"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3M5QKF5XSWJP7XHBI656LCHLA2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Transport Model Distributional Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CG"],"primary_cat":"cs.LG","authors_text":"Anh Tuan Bui, Dinh Phung, Thanh-Toan Do, Trung Le, Van-Anh Nguyen","submitted_at":"2023-06-07T06:15:12Z","abstract_excerpt":"Distributional robustness is a promising framework for training deep learning models that are less vulnerable to adversarial examples and data distribution shifts. Previous works have mainly focused on exploiting distributional robustness in the data space. In this work, we explore an optimal transport-based distributional robustness framework in model spaces. Specifically, we examine a model distribution within a Wasserstein ball centered on a given model distribution that maximizes the loss. We have developed theories that enable us to learn the optimal robust center model distribution. Inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04178","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/2306.04178/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:07:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lQWI4t/Inzl3TrRHnKBtWIPyO6D3n1cD6BHgD7Ib2NPlol0CwoUn9XzzySyFEA1TOpzqIS/lS50DkbmndbJ2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:59:46.820144Z"},"content_sha256":"be296655276551846fbb1645f5818208fdf3baf43fcc80019a867b37a48452d7","schema_version":"1.0","event_id":"sha256:be296655276551846fbb1645f5818208fdf3baf43fcc80019a867b37a48452d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3M5QKF5XSWJP7XHBI656LCHLA2/bundle.json","state_url":"https://pith.science/pith/3M5QKF5XSWJP7XHBI656LCHLA2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3M5QKF5XSWJP7XHBI656LCHLA2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T20:59:46Z","links":{"resolver":"https://pith.science/pith/3M5QKF5XSWJP7XHBI656LCHLA2","bundle":"https://pith.science/pith/3M5QKF5XSWJP7XHBI656LCHLA2/bundle.json","state":"https://pith.science/pith/3M5QKF5XSWJP7XHBI656LCHLA2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3M5QKF5XSWJP7XHBI656LCHLA2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3M5QKF5XSWJP7XHBI656LCHLA2","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":"bf0a385203255576444b61be1990dc9539ffc6a6d882f492fd5d3ac302169b51","cross_cats_sorted":["cs.CG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T06:15:12Z","title_canon_sha256":"b6be1a7ed2c4fe53bb0bc7d801ae3a5207d66e5096cac0ea9526fbbcf9dcdec4"},"schema_version":"1.0","source":{"id":"2306.04178","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.04178","created_at":"2026-07-05T07:07:38Z"},{"alias_kind":"arxiv_version","alias_value":"2306.04178v2","created_at":"2026-07-05T07:07:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04178","created_at":"2026-07-05T07:07:38Z"},{"alias_kind":"pith_short_12","alias_value":"3M5QKF5XSWJP","created_at":"2026-07-05T07:07:38Z"},{"alias_kind":"pith_short_16","alias_value":"3M5QKF5XSWJP7XHB","created_at":"2026-07-05T07:07:38Z"},{"alias_kind":"pith_short_8","alias_value":"3M5QKF5X","created_at":"2026-07-05T07:07:38Z"}],"graph_snapshots":[{"event_id":"sha256:be296655276551846fbb1645f5818208fdf3baf43fcc80019a867b37a48452d7","target":"graph","created_at":"2026-07-05T07:07:38Z","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/2306.04178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributional robustness is a promising framework for training deep learning models that are less vulnerable to adversarial examples and data distribution shifts. Previous works have mainly focused on exploiting distributional robustness in the data space. In this work, we explore an optimal transport-based distributional robustness framework in model spaces. Specifically, we examine a model distribution within a Wasserstein ball centered on a given model distribution that maximizes the loss. We have developed theories that enable us to learn the optimal robust center model distribution. Inte","authors_text":"Anh Tuan Bui, Dinh Phung, Thanh-Toan Do, Trung Le, Van-Anh Nguyen","cross_cats":["cs.CG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T06:15:12Z","title":"Optimal Transport Model Distributional Robustness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04178","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":"sha256:25b3efc4b9ea7d06511b73511ee864788d2989235234871915916a4f90dc8f67","target":"record","created_at":"2026-07-05T07:07:38Z","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":"bf0a385203255576444b61be1990dc9539ffc6a6d882f492fd5d3ac302169b51","cross_cats_sorted":["cs.CG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-07T06:15:12Z","title_canon_sha256":"b6be1a7ed2c4fe53bb0bc7d801ae3a5207d66e5096cac0ea9526fbbcf9dcdec4"},"schema_version":"1.0","source":{"id":"2306.04178","kind":"arxiv","version":2}},"canonical_sha256":"db3b0517b79592ffdce147bbe588eb06b46a4753b2f8bd3e52fb8ded178998ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db3b0517b79592ffdce147bbe588eb06b46a4753b2f8bd3e52fb8ded178998ec","first_computed_at":"2026-07-05T07:07:38.311061Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:38.311061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Per172E1NXSg/tD0+GKyVImcpbIzPs3yqb0evGFGorzwOGObly/4Rm2wjyAgHHiXiUbssudkmpCnm1QmCcDeBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:38.311669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.04178","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25b3efc4b9ea7d06511b73511ee864788d2989235234871915916a4f90dc8f67","sha256:be296655276551846fbb1645f5818208fdf3baf43fcc80019a867b37a48452d7"],"state_sha256":"e3a2b2954dcfac569b5b59de31708fa852c1389cd4d74409448d23a9f558ae8c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JSpXPeCrOyWtVzfgEbNrOOEgF6Z1lkfh5Js6QmEVKGs4phrgkWSzySEfq2sGHOROlWtIXYw4jlYFKCYnUXaRBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:59:46.825718Z","bundle_sha256":"883d36798feb2d15cfec6c00646c522000245959f95cda8f067fd2237ff7b352"}}