{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:REZNNERJMT72WJUEPF4XZI2J5P","short_pith_number":"pith:REZNNERJ","canonical_record":{"source":{"id":"1910.04091","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-10-09T16:08:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"37b2268fb49509428f42e054e957b2d7a8eb9dd3b2ac9dca2310cdd048393cd8","abstract_canon_sha256":"c260ed2d5e594787d108eb7248b3ba0cf9395898512890a839615017a5128e22"},"schema_version":"1.0"},"canonical_sha256":"8932d6922964ffab268479797ca349ebc12f59d1c70ba4843b5a3af485eeefe5","source":{"kind":"arxiv","id":"1910.04091","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.04091","created_at":"2026-07-05T03:22:18Z"},{"alias_kind":"arxiv_version","alias_value":"1910.04091v4","created_at":"2026-07-05T03:22:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.04091","created_at":"2026-07-05T03:22:18Z"},{"alias_kind":"pith_short_12","alias_value":"REZNNERJMT72","created_at":"2026-07-05T03:22:18Z"},{"alias_kind":"pith_short_16","alias_value":"REZNNERJMT72WJUE","created_at":"2026-07-05T03:22:18Z"},{"alias_kind":"pith_short_8","alias_value":"REZNNERJ","created_at":"2026-07-05T03:22:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:REZNNERJMT72WJUEPF4XZI2J5P","target":"record","payload":{"canonical_record":{"source":{"id":"1910.04091","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-10-09T16:08:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"37b2268fb49509428f42e054e957b2d7a8eb9dd3b2ac9dca2310cdd048393cd8","abstract_canon_sha256":"c260ed2d5e594787d108eb7248b3ba0cf9395898512890a839615017a5128e22"},"schema_version":"1.0"},"canonical_sha256":"8932d6922964ffab268479797ca349ebc12f59d1c70ba4843b5a3af485eeefe5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:18.784141Z","signature_b64":"u5Ngj08vIAXNCULr+iVaVWSumHxhWnlrawAxmXHKCOPjMvAf5OhjsdnqyO+FNOvfRJjG2GpwygxPLigq/CnGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8932d6922964ffab268479797ca349ebc12f59d1c70ba4843b5a3af485eeefe5","last_reissued_at":"2026-07-05T03:22:18.783745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:18.783745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.04091","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:22:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j2ykIyfqcwk7QF7zNTA7UrGs+CTRU29bteaplXroybZFeFHygkSKnuixvTaOqZY626qhyFW3xV9EVxHPsKxKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:39:14.319773Z"},"content_sha256":"fd19c2d14bd55dd3806d45ed1fefd744b133b46717e3f7b56dd9c79986a0e83f","schema_version":"1.0","event_id":"sha256:fd19c2d14bd55dd3806d45ed1fefd744b133b46717e3f7b56dd9c79986a0e83f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:REZNNERJMT72WJUEPF4XZI2J5P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning with minibatch Wasserstein : asymptotic and gradient properties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kilian Fatras, Nicolas Courty, R\\'emi Flamary, R\\'emi Gribonval, Younes Zine","submitted_at":"2019-10-09T16:08:43Z","abstract_excerpt":"Optimal transport distances are powerful tools to compare probability distributions and have found many applications in machine learning. Yet their algorithmic complexity prevents their direct use on large scale datasets. To overcome this challenge, practitioners compute these distances on minibatches {\\em i.e.} they average the outcome of several smaller optimal transport problems. We propose in this paper an analysis of this practice, which effects are not well understood so far. We notably argue that it is equivalent to an implicit regularization of the original problem, with appealing prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.04091","kind":"arxiv","version":4},"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/1910.04091/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":"2026-07-05T03:22:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V51UWcWal6xz/kz3KbM+NIeIiI8mrgt1ExzdjB2Eeq0mUvchvA4NbPAGHp/N2lMzc1ppvnH/c7/Ci+E5K6tcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:39:14.320277Z"},"content_sha256":"e2e2178543c56c466eb6948fc4be59960e352053073e56bbe3e8ee17d6a9c302","schema_version":"1.0","event_id":"sha256:e2e2178543c56c466eb6948fc4be59960e352053073e56bbe3e8ee17d6a9c302"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/REZNNERJMT72WJUEPF4XZI2J5P/bundle.json","state_url":"https://pith.science/pith/REZNNERJMT72WJUEPF4XZI2J5P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/REZNNERJMT72WJUEPF4XZI2J5P/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":"2026-08-05T10:39:14Z","links":{"resolver":"https://pith.science/pith/REZNNERJMT72WJUEPF4XZI2J5P","bundle":"https://pith.science/pith/REZNNERJMT72WJUEPF4XZI2J5P/bundle.json","state":"https://pith.science/pith/REZNNERJMT72WJUEPF4XZI2J5P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/REZNNERJMT72WJUEPF4XZI2J5P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:REZNNERJMT72WJUEPF4XZI2J5P","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":"c260ed2d5e594787d108eb7248b3ba0cf9395898512890a839615017a5128e22","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-10-09T16:08:43Z","title_canon_sha256":"37b2268fb49509428f42e054e957b2d7a8eb9dd3b2ac9dca2310cdd048393cd8"},"schema_version":"1.0","source":{"id":"1910.04091","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.04091","created_at":"2026-07-05T03:22:18Z"},{"alias_kind":"arxiv_version","alias_value":"1910.04091v4","created_at":"2026-07-05T03:22:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.04091","created_at":"2026-07-05T03:22:18Z"},{"alias_kind":"pith_short_12","alias_value":"REZNNERJMT72","created_at":"2026-07-05T03:22:18Z"},{"alias_kind":"pith_short_16","alias_value":"REZNNERJMT72WJUE","created_at":"2026-07-05T03:22:18Z"},{"alias_kind":"pith_short_8","alias_value":"REZNNERJ","created_at":"2026-07-05T03:22:18Z"}],"graph_snapshots":[{"event_id":"sha256:e2e2178543c56c466eb6948fc4be59960e352053073e56bbe3e8ee17d6a9c302","target":"graph","created_at":"2026-07-05T03:22:18Z","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/1910.04091/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimal transport distances are powerful tools to compare probability distributions and have found many applications in machine learning. Yet their algorithmic complexity prevents their direct use on large scale datasets. To overcome this challenge, practitioners compute these distances on minibatches {\\em i.e.} they average the outcome of several smaller optimal transport problems. We propose in this paper an analysis of this practice, which effects are not well understood so far. We notably argue that it is equivalent to an implicit regularization of the original problem, with appealing prop","authors_text":"Kilian Fatras, Nicolas Courty, R\\'emi Flamary, R\\'emi Gribonval, Younes Zine","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-10-09T16:08:43Z","title":"Learning with minibatch Wasserstein : asymptotic and gradient properties"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.04091","kind":"arxiv","version":4},"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:fd19c2d14bd55dd3806d45ed1fefd744b133b46717e3f7b56dd9c79986a0e83f","target":"record","created_at":"2026-07-05T03:22:18Z","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":"c260ed2d5e594787d108eb7248b3ba0cf9395898512890a839615017a5128e22","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-10-09T16:08:43Z","title_canon_sha256":"37b2268fb49509428f42e054e957b2d7a8eb9dd3b2ac9dca2310cdd048393cd8"},"schema_version":"1.0","source":{"id":"1910.04091","kind":"arxiv","version":4}},"canonical_sha256":"8932d6922964ffab268479797ca349ebc12f59d1c70ba4843b5a3af485eeefe5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8932d6922964ffab268479797ca349ebc12f59d1c70ba4843b5a3af485eeefe5","first_computed_at":"2026-07-05T03:22:18.783745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:18.783745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u5Ngj08vIAXNCULr+iVaVWSumHxhWnlrawAxmXHKCOPjMvAf5OhjsdnqyO+FNOvfRJjG2GpwygxPLigq/CnGBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:18.784141Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.04091","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd19c2d14bd55dd3806d45ed1fefd744b133b46717e3f7b56dd9c79986a0e83f","sha256:e2e2178543c56c466eb6948fc4be59960e352053073e56bbe3e8ee17d6a9c302"],"state_sha256":"03d2857b55a929105912c47b626051f147aa68babe8a25c64317d1b9b8c49204"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wQ1WdCdLKSkLMvxaaKk/5IuWiMyoAnl6yE5NlinXyyITEkUN8ProUMPcQ2GWBIKhuDX7RwYJQuzc8nv70c8TBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:39:14.324176Z","bundle_sha256":"fcca1626c61dc8ba588ead3b9ef0fb4e869e241da79037ac324a060a8f176e4f"}}