{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:WCQ3VFJIPKIGCGFCIDITYZWBKV","short_pith_number":"pith:WCQ3VFJI","canonical_record":{"source":{"id":"2212.13251","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-26T18:37:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"90a794e5f5386bc0368aa43d9452eef903bdc9159c4529dddb58524396ca06b0","abstract_canon_sha256":"a1c7631a45a00f3f90a8d5b506b7dbdd9eb97b4f360396f6a1b2bd82a420258e"},"schema_version":"1.0"},"canonical_sha256":"b0a1ba95287a906118a240d13c66c155604596459055626f2fc0bc01193d4467","source":{"kind":"arxiv","id":"2212.13251","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.13251","created_at":"2026-07-05T05:28:18Z"},{"alias_kind":"arxiv_version","alias_value":"2212.13251v1","created_at":"2026-07-05T05:28:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.13251","created_at":"2026-07-05T05:28:18Z"},{"alias_kind":"pith_short_12","alias_value":"WCQ3VFJIPKIG","created_at":"2026-07-05T05:28:18Z"},{"alias_kind":"pith_short_16","alias_value":"WCQ3VFJIPKIGCGFC","created_at":"2026-07-05T05:28:18Z"},{"alias_kind":"pith_short_8","alias_value":"WCQ3VFJI","created_at":"2026-07-05T05:28:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:WCQ3VFJIPKIGCGFCIDITYZWBKV","target":"record","payload":{"canonical_record":{"source":{"id":"2212.13251","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-26T18:37:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"90a794e5f5386bc0368aa43d9452eef903bdc9159c4529dddb58524396ca06b0","abstract_canon_sha256":"a1c7631a45a00f3f90a8d5b506b7dbdd9eb97b4f360396f6a1b2bd82a420258e"},"schema_version":"1.0"},"canonical_sha256":"b0a1ba95287a906118a240d13c66c155604596459055626f2fc0bc01193d4467","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:28:18.602023Z","signature_b64":"qqe3j5DCxR24ogdg28Rs1ayCspXjl8WvoWxrwM7QnwzbC9aThhUZdkBLqJIfyTM+wIKyqlKr+1BCgEG95S1FDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0a1ba95287a906118a240d13c66c155604596459055626f2fc0bc01193d4467","last_reissued_at":"2026-07-05T05:28:18.601638Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:28:18.601638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2212.13251","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:28:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u9ef1lR1PyX5bDa8hta/2ELwURxWM0mfMoIGi9D/8vS2/+mY1KMGCgXUQ2i0z78gKlnkroBFQe9DFCnDp45IDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:10:38.631119Z"},"content_sha256":"0eae953ae007a347e1a838b1d0772804ceabd13f09c9d1035b0abd7473bc703d","schema_version":"1.0","event_id":"sha256:0eae953ae007a347e1a838b1d0772804ceabd13f09c9d1035b0abd7473bc703d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:WCQ3VFJIPKIGCGFCIDITYZWBKV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust computation of optimal transport by $\\beta$-potential regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Han Bao, Masashi Sugiyama, Shintaro Nakamura","submitted_at":"2022-12-26T18:37:28Z","abstract_excerpt":"Optimal transport (OT) has become a widely used tool in the machine learning field to measure the discrepancy between probability distributions. For instance, OT is a popular loss function that quantifies the discrepancy between an empirical distribution and a parametric model. Recently, an entropic penalty term and the celebrated Sinkhorn algorithm have been commonly used to approximate the original OT in a computationally efficient way. However, since the Sinkhorn algorithm runs a projection associated with the Kullback-Leibler divergence, it is often vulnerable to outliers. To overcome this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.13251","kind":"arxiv","version":1},"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/2212.13251/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":"2026-07-05T05:28:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2zQ8cE+bvXLIeHJ+t8EE8deec3m3lpyWFM1L4Mm/0P0pkAylU8fpf24DhqIosNGnurXNPadn+YunMZLYDbAiCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:10:38.631511Z"},"content_sha256":"8c81be3606f80a54055271496c78fc07e6800d2f920c3e1b6ceb9bd6be666fc0","schema_version":"1.0","event_id":"sha256:8c81be3606f80a54055271496c78fc07e6800d2f920c3e1b6ceb9bd6be666fc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WCQ3VFJIPKIGCGFCIDITYZWBKV/bundle.json","state_url":"https://pith.science/pith/WCQ3VFJIPKIGCGFCIDITYZWBKV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WCQ3VFJIPKIGCGFCIDITYZWBKV/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":"2026-07-06T08:10:38Z","links":{"resolver":"https://pith.science/pith/WCQ3VFJIPKIGCGFCIDITYZWBKV","bundle":"https://pith.science/pith/WCQ3VFJIPKIGCGFCIDITYZWBKV/bundle.json","state":"https://pith.science/pith/WCQ3VFJIPKIGCGFCIDITYZWBKV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WCQ3VFJIPKIGCGFCIDITYZWBKV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WCQ3VFJIPKIGCGFCIDITYZWBKV","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":"a1c7631a45a00f3f90a8d5b506b7dbdd9eb97b4f360396f6a1b2bd82a420258e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-26T18:37:28Z","title_canon_sha256":"90a794e5f5386bc0368aa43d9452eef903bdc9159c4529dddb58524396ca06b0"},"schema_version":"1.0","source":{"id":"2212.13251","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.13251","created_at":"2026-07-05T05:28:18Z"},{"alias_kind":"arxiv_version","alias_value":"2212.13251v1","created_at":"2026-07-05T05:28:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.13251","created_at":"2026-07-05T05:28:18Z"},{"alias_kind":"pith_short_12","alias_value":"WCQ3VFJIPKIG","created_at":"2026-07-05T05:28:18Z"},{"alias_kind":"pith_short_16","alias_value":"WCQ3VFJIPKIGCGFC","created_at":"2026-07-05T05:28:18Z"},{"alias_kind":"pith_short_8","alias_value":"WCQ3VFJI","created_at":"2026-07-05T05:28:18Z"}],"graph_snapshots":[{"event_id":"sha256:8c81be3606f80a54055271496c78fc07e6800d2f920c3e1b6ceb9bd6be666fc0","target":"graph","created_at":"2026-07-05T05:28:18Z","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/2212.13251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimal transport (OT) has become a widely used tool in the machine learning field to measure the discrepancy between probability distributions. For instance, OT is a popular loss function that quantifies the discrepancy between an empirical distribution and a parametric model. Recently, an entropic penalty term and the celebrated Sinkhorn algorithm have been commonly used to approximate the original OT in a computationally efficient way. However, since the Sinkhorn algorithm runs a projection associated with the Kullback-Leibler divergence, it is often vulnerable to outliers. To overcome this","authors_text":"Han Bao, Masashi Sugiyama, Shintaro Nakamura","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-26T18:37:28Z","title":"Robust computation of optimal transport by $\\beta$-potential regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.13251","kind":"arxiv","version":1},"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":"sha256:0eae953ae007a347e1a838b1d0772804ceabd13f09c9d1035b0abd7473bc703d","target":"record","created_at":"2026-07-05T05:28:18Z","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":"a1c7631a45a00f3f90a8d5b506b7dbdd9eb97b4f360396f6a1b2bd82a420258e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-26T18:37:28Z","title_canon_sha256":"90a794e5f5386bc0368aa43d9452eef903bdc9159c4529dddb58524396ca06b0"},"schema_version":"1.0","source":{"id":"2212.13251","kind":"arxiv","version":1}},"canonical_sha256":"b0a1ba95287a906118a240d13c66c155604596459055626f2fc0bc01193d4467","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0a1ba95287a906118a240d13c66c155604596459055626f2fc0bc01193d4467","first_computed_at":"2026-07-05T05:28:18.601638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:28:18.601638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qqe3j5DCxR24ogdg28Rs1ayCspXjl8WvoWxrwM7QnwzbC9aThhUZdkBLqJIfyTM+wIKyqlKr+1BCgEG95S1FDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:28:18.602023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.13251","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0eae953ae007a347e1a838b1d0772804ceabd13f09c9d1035b0abd7473bc703d","sha256:8c81be3606f80a54055271496c78fc07e6800d2f920c3e1b6ceb9bd6be666fc0"],"state_sha256":"b66114c0179e9a65eacdf2a4792ad90e58ac40bc897011ae77bb6b4d49de3c39"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N3RlcJLATk6EvAv0P+6DDm2n04nKkz/TuxZb0QWhsEKBJl8qjvpaNMKvuxed2VzsrkoR8RtT8knQTt6dg8//DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:10:38.633573Z","bundle_sha256":"bd4fa4cb175850bf9e77a1e71371893beefb96a7be0bf229a8e66b74875a68e4"}}