{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:3S2SY5LOTQRKB5WRQE5RCWVZNY","short_pith_number":"pith:3S2SY5LO","canonical_record":{"source":{"id":"1710.10016","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-10-27T07:52:45Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"44c98e9990da97cdbcadcc0d4c522503452135b8b5884ef63559dcd93db62eb9","abstract_canon_sha256":"defd08225bd034ce951866a17fcde6c4f4fb004c91ffbcec0b1d3416cca109e3"},"schema_version":"1.0"},"canonical_sha256":"dcb52c756e9c22a0f6d1813b115ab96e0f62335d6d8432e21cd3c672a38a40e9","source":{"kind":"arxiv","id":"1710.10016","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.10016","created_at":"2026-05-17T23:40:49Z"},{"alias_kind":"arxiv_version","alias_value":"1710.10016v3","created_at":"2026-05-17T23:40:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10016","created_at":"2026-05-17T23:40:49Z"},{"alias_kind":"pith_short_12","alias_value":"3S2SY5LOTQRK","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3S2SY5LOTQRKB5WR","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3S2SY5LO","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:3S2SY5LOTQRKB5WRQE5RCWVZNY","target":"record","payload":{"canonical_record":{"source":{"id":"1710.10016","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-10-27T07:52:45Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"44c98e9990da97cdbcadcc0d4c522503452135b8b5884ef63559dcd93db62eb9","abstract_canon_sha256":"defd08225bd034ce951866a17fcde6c4f4fb004c91ffbcec0b1d3416cca109e3"},"schema_version":"1.0"},"canonical_sha256":"dcb52c756e9c22a0f6d1813b115ab96e0f62335d6d8432e21cd3c672a38a40e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:49.819964Z","signature_b64":"bQtiKHbIUjUvp1eDmF9b5eLUhdWYqw3Do7TpvIqzCufNwUXSE3hcdRHpuFSthHJy9q1ZdmKtc63G8z43T25HDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcb52c756e9c22a0f6d1813b115ab96e0f62335d6d8432e21cd3c672a38a40e9","last_reissued_at":"2026-05-17T23:40:49.819217Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:49.819217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.10016","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:40:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ACk7pLFvchCiyoa0NKlJOdrgRTHA/NRc8AsVbB0DNSiA4oYkdnS4TaSUr+su6wK5BHlZxnBHGON2tLmDMUjACg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T06:38:01.488682Z"},"content_sha256":"157480b6f08d69bbe5e9152b3fdd15093fc45830519a8b999bb3df1dd884605d","schema_version":"1.0","event_id":"sha256:157480b6f08d69bbe5e9152b3fdd15093fc45830519a8b999bb3df1dd884605d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:3S2SY5LOTQRKB5WRQE5RCWVZNY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regularization via Mass Transportation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Daniel Kuhn, Peyman Mohajerin Esfahani, Soroosh Shafieezadeh-Abadeh","submitted_at":"2017-10-27T07:52:45Z","abstract_excerpt":"The goal of regression and classification methods in supervised learning is to minimize the empirical risk, that is, the expectation of some loss function quantifying the prediction error under the empirical distribution. When facing scarce training data, overfitting is typically mitigated by adding regularization terms to the objective that penalize hypothesis complexity. In this paper we introduce new regularization techniques using ideas from distributionally robust optimization, and we give new probabilistic interpretations to existing techniques. Specifically, we propose to minimize the w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10016","kind":"arxiv","version":3},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:40:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1czyhYqp5mqhqN3q1KMWJxrVBgfAUlWZtfQYdkXMBSqMlSAlI9O1UiuWwWKtK4aM57fqsRMxbR02HvpzKZiUBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T06:38:01.489423Z"},"content_sha256":"fca2036d3b31cafbf475df40609f740cf75625b96ac76492d52a1225ff0ed1b4","schema_version":"1.0","event_id":"sha256:fca2036d3b31cafbf475df40609f740cf75625b96ac76492d52a1225ff0ed1b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3S2SY5LOTQRKB5WRQE5RCWVZNY/bundle.json","state_url":"https://pith.science/pith/3S2SY5LOTQRKB5WRQE5RCWVZNY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3S2SY5LOTQRKB5WRQE5RCWVZNY/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":"2026-05-25T06:38:01Z","links":{"resolver":"https://pith.science/pith/3S2SY5LOTQRKB5WRQE5RCWVZNY","bundle":"https://pith.science/pith/3S2SY5LOTQRKB5WRQE5RCWVZNY/bundle.json","state":"https://pith.science/pith/3S2SY5LOTQRKB5WRQE5RCWVZNY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3S2SY5LOTQRKB5WRQE5RCWVZNY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3S2SY5LOTQRKB5WRQE5RCWVZNY","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":"defd08225bd034ce951866a17fcde6c4f4fb004c91ffbcec0b1d3416cca109e3","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-10-27T07:52:45Z","title_canon_sha256":"44c98e9990da97cdbcadcc0d4c522503452135b8b5884ef63559dcd93db62eb9"},"schema_version":"1.0","source":{"id":"1710.10016","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.10016","created_at":"2026-05-17T23:40:49Z"},{"alias_kind":"arxiv_version","alias_value":"1710.10016v3","created_at":"2026-05-17T23:40:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10016","created_at":"2026-05-17T23:40:49Z"},{"alias_kind":"pith_short_12","alias_value":"3S2SY5LOTQRK","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3S2SY5LOTQRKB5WR","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3S2SY5LO","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:fca2036d3b31cafbf475df40609f740cf75625b96ac76492d52a1225ff0ed1b4","target":"graph","created_at":"2026-05-17T23:40:49Z","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"},"paper":{"abstract_excerpt":"The goal of regression and classification methods in supervised learning is to minimize the empirical risk, that is, the expectation of some loss function quantifying the prediction error under the empirical distribution. When facing scarce training data, overfitting is typically mitigated by adding regularization terms to the objective that penalize hypothesis complexity. In this paper we introduce new regularization techniques using ideas from distributionally robust optimization, and we give new probabilistic interpretations to existing techniques. Specifically, we propose to minimize the w","authors_text":"Daniel Kuhn, Peyman Mohajerin Esfahani, Soroosh Shafieezadeh-Abadeh","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-10-27T07:52:45Z","title":"Regularization via Mass Transportation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10016","kind":"arxiv","version":3},"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":"sha256:157480b6f08d69bbe5e9152b3fdd15093fc45830519a8b999bb3df1dd884605d","target":"record","created_at":"2026-05-17T23:40:49Z","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":"defd08225bd034ce951866a17fcde6c4f4fb004c91ffbcec0b1d3416cca109e3","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-10-27T07:52:45Z","title_canon_sha256":"44c98e9990da97cdbcadcc0d4c522503452135b8b5884ef63559dcd93db62eb9"},"schema_version":"1.0","source":{"id":"1710.10016","kind":"arxiv","version":3}},"canonical_sha256":"dcb52c756e9c22a0f6d1813b115ab96e0f62335d6d8432e21cd3c672a38a40e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcb52c756e9c22a0f6d1813b115ab96e0f62335d6d8432e21cd3c672a38a40e9","first_computed_at":"2026-05-17T23:40:49.819217Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:49.819217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bQtiKHbIUjUvp1eDmF9b5eLUhdWYqw3Do7TpvIqzCufNwUXSE3hcdRHpuFSthHJy9q1ZdmKtc63G8z43T25HDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:49.819964Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.10016","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:157480b6f08d69bbe5e9152b3fdd15093fc45830519a8b999bb3df1dd884605d","sha256:fca2036d3b31cafbf475df40609f740cf75625b96ac76492d52a1225ff0ed1b4"],"state_sha256":"ca9765f9e5ac6254323123738b9d2a137ad782d8f1fba09c6d7e3d6dfcd521c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eMmlGBwjJhZi83M99wmy9hEhw6gZhb+4x1BiQIDUGP8sF+hYVlkDyEZBMZfwSpoZlqHIqVennb/PEa3iX7h3Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T06:38:01.493239Z","bundle_sha256":"c9ec15b65f7bfab3ff195fa6420b7c852a1e826229a44d7517e605741a01b880"}}