{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LZUY4RHR3DNV3NIBTQYUVCQBSQ","short_pith_number":"pith:LZUY4RHR","canonical_record":{"source":{"id":"2002.03860","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-10T15:23:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0bc439a25e3631a5d87da88228c3714351d03728b09f17f2939dfa69fc210c9c","abstract_canon_sha256":"59203a9cc06b553f9a66f802e09e5d995330a4937560d9e74c79796d2cbbafd0"},"schema_version":"1.0"},"canonical_sha256":"5e698e44f1d8db5db5019c314a8a0194326dea0636132f1ac0d12a6ea0241c1b","source":{"kind":"arxiv","id":"2002.03860","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.03860","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"arxiv_version","alias_value":"2002.03860v3","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03860","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"pith_short_12","alias_value":"LZUY4RHR3DNV","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"pith_short_16","alias_value":"LZUY4RHR3DNV3NIB","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"pith_short_8","alias_value":"LZUY4RHR","created_at":"2026-07-05T01:15:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LZUY4RHR3DNV3NIBTQYUVCQBSQ","target":"record","payload":{"canonical_record":{"source":{"id":"2002.03860","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-10T15:23:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0bc439a25e3631a5d87da88228c3714351d03728b09f17f2939dfa69fc210c9c","abstract_canon_sha256":"59203a9cc06b553f9a66f802e09e5d995330a4937560d9e74c79796d2cbbafd0"},"schema_version":"1.0"},"canonical_sha256":"5e698e44f1d8db5db5019c314a8a0194326dea0636132f1ac0d12a6ea0241c1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:24.457736Z","signature_b64":"T+Gxza5rQUCUXqNcfI9fZbuTiwlYbs04HvHd0lxHk3L9Kf26S/XTjwpVVXNBUseTCqDfRxEbOpE378Ey+RGpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e698e44f1d8db5db5019c314a8a0194326dea0636132f1ac0d12a6ea0241c1b","last_reissued_at":"2026-07-05T01:15:24.457335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:24.457335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.03860","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":"2026-07-05T01:15:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zxrRK5ILxIosP0wtDn7UvVInMWrjgs9FU60xucHLd+oYmwRu49O2nQ6w83LxEH9C6y03eYD6Ygwd/JZMzDTDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:22:20.392567Z"},"content_sha256":"d686abdc1d11d2f0597f104ea9f3373e2a4f98a95c770dd8b32546a9234c35d1","schema_version":"1.0","event_id":"sha256:d686abdc1d11d2f0597f104ea9f3373e2a4f98a95c770dd8b32546a9234c35d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LZUY4RHR3DNV3NIBTQYUVCQBSQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Missing Data Imputation using Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Boris Muzellec, Claire Boyer, Julie Josse, Marco Cuturi","submitted_at":"2020-02-10T15:23:42Z","abstract_excerpt":"Missing data is a crucial issue when applying machine learning algorithms to real-world datasets. Starting from the simple assumption that two batches extracted randomly from the same dataset should share the same distribution, we leverage optimal transport distances to quantify that criterion and turn it into a loss function to impute missing data values. We propose practical methods to minimize these losses using end-to-end learning, that can exploit or not parametric assumptions on the underlying distributions of values. We evaluate our methods on datasets from the UCI repository, in MCAR, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03860","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.03860/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":"2026-07-05T01:15:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nvv/AewFUBlHaK8PRUqYR9HI11rc9J20stM+/cdTCpQOntpXHbP1mwESho/FRlbJhqWMGr1BAF4TSlPH33fxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:22:20.393086Z"},"content_sha256":"9baa126dd86f75dbe04867527c4103707fd6ae00213038c62808b9e59c4c30f8","schema_version":"1.0","event_id":"sha256:9baa126dd86f75dbe04867527c4103707fd6ae00213038c62808b9e59c4c30f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZUY4RHR3DNV3NIBTQYUVCQBSQ/bundle.json","state_url":"https://pith.science/pith/LZUY4RHR3DNV3NIBTQYUVCQBSQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZUY4RHR3DNV3NIBTQYUVCQBSQ/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":"2026-08-01T07:22:20Z","links":{"resolver":"https://pith.science/pith/LZUY4RHR3DNV3NIBTQYUVCQBSQ","bundle":"https://pith.science/pith/LZUY4RHR3DNV3NIBTQYUVCQBSQ/bundle.json","state":"https://pith.science/pith/LZUY4RHR3DNV3NIBTQYUVCQBSQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZUY4RHR3DNV3NIBTQYUVCQBSQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LZUY4RHR3DNV3NIBTQYUVCQBSQ","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":"59203a9cc06b553f9a66f802e09e5d995330a4937560d9e74c79796d2cbbafd0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-10T15:23:42Z","title_canon_sha256":"0bc439a25e3631a5d87da88228c3714351d03728b09f17f2939dfa69fc210c9c"},"schema_version":"1.0","source":{"id":"2002.03860","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.03860","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"arxiv_version","alias_value":"2002.03860v3","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03860","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"pith_short_12","alias_value":"LZUY4RHR3DNV","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"pith_short_16","alias_value":"LZUY4RHR3DNV3NIB","created_at":"2026-07-05T01:15:24Z"},{"alias_kind":"pith_short_8","alias_value":"LZUY4RHR","created_at":"2026-07-05T01:15:24Z"}],"graph_snapshots":[{"event_id":"sha256:9baa126dd86f75dbe04867527c4103707fd6ae00213038c62808b9e59c4c30f8","target":"graph","created_at":"2026-07-05T01:15:24Z","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/2002.03860/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Missing data is a crucial issue when applying machine learning algorithms to real-world datasets. Starting from the simple assumption that two batches extracted randomly from the same dataset should share the same distribution, we leverage optimal transport distances to quantify that criterion and turn it into a loss function to impute missing data values. We propose practical methods to minimize these losses using end-to-end learning, that can exploit or not parametric assumptions on the underlying distributions of values. We evaluate our methods on datasets from the UCI repository, in MCAR, ","authors_text":"Boris Muzellec, Claire Boyer, Julie Josse, Marco Cuturi","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-10T15:23:42Z","title":"Missing Data Imputation using Optimal Transport"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03860","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:d686abdc1d11d2f0597f104ea9f3373e2a4f98a95c770dd8b32546a9234c35d1","target":"record","created_at":"2026-07-05T01:15:24Z","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":"59203a9cc06b553f9a66f802e09e5d995330a4937560d9e74c79796d2cbbafd0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-10T15:23:42Z","title_canon_sha256":"0bc439a25e3631a5d87da88228c3714351d03728b09f17f2939dfa69fc210c9c"},"schema_version":"1.0","source":{"id":"2002.03860","kind":"arxiv","version":3}},"canonical_sha256":"5e698e44f1d8db5db5019c314a8a0194326dea0636132f1ac0d12a6ea0241c1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e698e44f1d8db5db5019c314a8a0194326dea0636132f1ac0d12a6ea0241c1b","first_computed_at":"2026-07-05T01:15:24.457335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:15:24.457335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T+Gxza5rQUCUXqNcfI9fZbuTiwlYbs04HvHd0lxHk3L9Kf26S/XTjwpVVXNBUseTCqDfRxEbOpE378Ey+RGpCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:15:24.457736Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.03860","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d686abdc1d11d2f0597f104ea9f3373e2a4f98a95c770dd8b32546a9234c35d1","sha256:9baa126dd86f75dbe04867527c4103707fd6ae00213038c62808b9e59c4c30f8"],"state_sha256":"db2f4d6ed86ab4601122a9d2aecd74af5225095b2cfdc5a14226772501b06ad7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SWPCoLXOYi+cHXZs/hyhsWuqemkFvNMy1wHiTkagkrxIUtpcntV9E+V0g02tGRK1U+c1h/LfDG/10haZOf5WBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T07:22:20.397700Z","bundle_sha256":"559cd733615ec2a3ae71c187a0325e27a63f1e4409b93010d4cefcece1013125"}}