{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:NU25ZIETLS45PW3YP7NPDESRSV","short_pith_number":"pith:NU25ZIET","canonical_record":{"source":{"id":"2006.12301","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-06-22T14:35:33Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"c6c1972ed7493991f09cee863985404f31002de371fb671c36d03dbf093209c8","abstract_canon_sha256":"41bf93cfc3bfc6a9ea9f42e347806ec214f4ccaf4234bfa031951975e947fe69"},"schema_version":"1.0"},"canonical_sha256":"6d35dca0935cb9d7db787fdaf192519574873d9f4b56a83763147147cd0bb1a8","source":{"kind":"arxiv","id":"2006.12301","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.12301","created_at":"2026-07-05T02:58:35Z"},{"alias_kind":"arxiv_version","alias_value":"2006.12301v5","created_at":"2026-07-05T02:58:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.12301","created_at":"2026-07-05T02:58:35Z"},{"alias_kind":"pith_short_12","alias_value":"NU25ZIETLS45","created_at":"2026-07-05T02:58:35Z"},{"alias_kind":"pith_short_16","alias_value":"NU25ZIETLS45PW3Y","created_at":"2026-07-05T02:58:35Z"},{"alias_kind":"pith_short_8","alias_value":"NU25ZIET","created_at":"2026-07-05T02:58:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:NU25ZIETLS45PW3YP7NPDESRSV","target":"record","payload":{"canonical_record":{"source":{"id":"2006.12301","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-06-22T14:35:33Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"c6c1972ed7493991f09cee863985404f31002de371fb671c36d03dbf093209c8","abstract_canon_sha256":"41bf93cfc3bfc6a9ea9f42e347806ec214f4ccaf4234bfa031951975e947fe69"},"schema_version":"1.0"},"canonical_sha256":"6d35dca0935cb9d7db787fdaf192519574873d9f4b56a83763147147cd0bb1a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:58:35.358964Z","signature_b64":"vWw1lUIWHqT4vHqBqWnUMfokVsRWbC5ON5W5LikbZOG/8MdSd/pVE/kOYZW82/YbQgtkIBSIHIMo77C0LN+XBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d35dca0935cb9d7db787fdaf192519574873d9f4b56a83763147147cd0bb1a8","last_reissued_at":"2026-07-05T02:58:35.358499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:58:35.358499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.12301","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:58:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rKPJCBFxoXPNMfXpRL7S23jcTsXupo/5D1xnLyR4YEayx3yrkj6z4XuakaTh23ryl1t3LTtUbeP+C7xZ5uZpBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:34:00.487790Z"},"content_sha256":"da3fe0fc205a8d5812bf6caaee07ddefaa2d35d8bb2939348b8fc5b9c156fc25","schema_version":"1.0","event_id":"sha256:da3fe0fc205a8d5812bf6caaee07ddefaa2d35d8bb2939348b8fc5b9c156fc25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:NU25ZIETLS45PW3YP7NPDESRSV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Elynn Y. Chen, Marco Cuturi, Michael I. Jordan, Tianyi Lin, Zeyu Zheng","submitted_at":"2020-06-22T14:35:33Z","abstract_excerpt":"Optimal transport (OT) distances are increasingly used as loss functions for statistical inference, notably in the learning of generative models or supervised learning. Yet, the behavior of minimum Wasserstein estimators is poorly understood, notably in high-dimensional regimes or under model misspecification. In this work we adopt the viewpoint of projection robust (PR) OT, which seeks to maximize the OT cost between two measures by choosing a $k$-dimensional subspace onto which they can be projected. Our first contribution is to establish several fundamental statistical properties of PR Wass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.12301","kind":"arxiv","version":5},"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/2006.12301/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":"2026-07-05T02:58:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ThtZsYR9q49ercy86NH66p8f+LJpvdL/yklhPKKRuEitetOh1x8byBNX7ib611RKKWTwVCRdu/4cYdr6XQV8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:34:00.488340Z"},"content_sha256":"6e5d05eb69c94ec4b77761861d53b868c9f5c495aeec0d2998565b6cb7719df1","schema_version":"1.0","event_id":"sha256:6e5d05eb69c94ec4b77761861d53b868c9f5c495aeec0d2998565b6cb7719df1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NU25ZIETLS45PW3YP7NPDESRSV/bundle.json","state_url":"https://pith.science/pith/NU25ZIETLS45PW3YP7NPDESRSV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NU25ZIETLS45PW3YP7NPDESRSV/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":"2026-08-10T21:34:00Z","links":{"resolver":"https://pith.science/pith/NU25ZIETLS45PW3YP7NPDESRSV","bundle":"https://pith.science/pith/NU25ZIETLS45PW3YP7NPDESRSV/bundle.json","state":"https://pith.science/pith/NU25ZIETLS45PW3YP7NPDESRSV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NU25ZIETLS45PW3YP7NPDESRSV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:NU25ZIETLS45PW3YP7NPDESRSV","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":"41bf93cfc3bfc6a9ea9f42e347806ec214f4ccaf4234bfa031951975e947fe69","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-06-22T14:35:33Z","title_canon_sha256":"c6c1972ed7493991f09cee863985404f31002de371fb671c36d03dbf093209c8"},"schema_version":"1.0","source":{"id":"2006.12301","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.12301","created_at":"2026-07-05T02:58:35Z"},{"alias_kind":"arxiv_version","alias_value":"2006.12301v5","created_at":"2026-07-05T02:58:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.12301","created_at":"2026-07-05T02:58:35Z"},{"alias_kind":"pith_short_12","alias_value":"NU25ZIETLS45","created_at":"2026-07-05T02:58:35Z"},{"alias_kind":"pith_short_16","alias_value":"NU25ZIETLS45PW3Y","created_at":"2026-07-05T02:58:35Z"},{"alias_kind":"pith_short_8","alias_value":"NU25ZIET","created_at":"2026-07-05T02:58:35Z"}],"graph_snapshots":[{"event_id":"sha256:6e5d05eb69c94ec4b77761861d53b868c9f5c495aeec0d2998565b6cb7719df1","target":"graph","created_at":"2026-07-05T02:58:35Z","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/2006.12301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimal transport (OT) distances are increasingly used as loss functions for statistical inference, notably in the learning of generative models or supervised learning. Yet, the behavior of minimum Wasserstein estimators is poorly understood, notably in high-dimensional regimes or under model misspecification. In this work we adopt the viewpoint of projection robust (PR) OT, which seeks to maximize the OT cost between two measures by choosing a $k$-dimensional subspace onto which they can be projected. Our first contribution is to establish several fundamental statistical properties of PR Wass","authors_text":"Elynn Y. Chen, Marco Cuturi, Michael I. Jordan, Tianyi Lin, Zeyu Zheng","cross_cats":["cs.LG","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-06-22T14:35:33Z","title":"On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.12301","kind":"arxiv","version":5},"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:da3fe0fc205a8d5812bf6caaee07ddefaa2d35d8bb2939348b8fc5b9c156fc25","target":"record","created_at":"2026-07-05T02:58:35Z","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":"41bf93cfc3bfc6a9ea9f42e347806ec214f4ccaf4234bfa031951975e947fe69","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2020-06-22T14:35:33Z","title_canon_sha256":"c6c1972ed7493991f09cee863985404f31002de371fb671c36d03dbf093209c8"},"schema_version":"1.0","source":{"id":"2006.12301","kind":"arxiv","version":5}},"canonical_sha256":"6d35dca0935cb9d7db787fdaf192519574873d9f4b56a83763147147cd0bb1a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d35dca0935cb9d7db787fdaf192519574873d9f4b56a83763147147cd0bb1a8","first_computed_at":"2026-07-05T02:58:35.358499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:58:35.358499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vWw1lUIWHqT4vHqBqWnUMfokVsRWbC5ON5W5LikbZOG/8MdSd/pVE/kOYZW82/YbQgtkIBSIHIMo77C0LN+XBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:58:35.358964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.12301","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da3fe0fc205a8d5812bf6caaee07ddefaa2d35d8bb2939348b8fc5b9c156fc25","sha256:6e5d05eb69c94ec4b77761861d53b868c9f5c495aeec0d2998565b6cb7719df1"],"state_sha256":"cb1c49f6c6b63a6255c20128121fc7e3f9e9e5ef3565ac6bd64904133ae12bb2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8qOjmOLaLD0ynTsJ5rGsW7z6551KF9O3Y0EYTdIcpYGNSd7HOrc0Pf0fL2vAFlbwof7Ct3fvrVAXHU2C0k58DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T21:34:00.494604Z","bundle_sha256":"a8ad8d7fb48120f8d683f020f8c566c86203c13f12f428e51ec79f4bb82edb50"}}