{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KZRZ5VDV2MVXP6F6KK5OI6RRM2","short_pith_number":"pith:KZRZ5VDV","canonical_record":{"source":{"id":"1905.06005","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-15T07:49:10Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"9aeb2e00e6447efdb68790af47f9c5980f705f29d74b7c67cfd9e4547f8ded92","abstract_canon_sha256":"757ed6d4c2bedf3a916268a01e13f16a067cc7d41cc59f3f910984b563fd61e6"},"schema_version":"1.0"},"canonical_sha256":"56639ed475d32b77f8be52bae47a3166abd19f20637315bbad999f4fb17a8d0f","source":{"kind":"arxiv","id":"1905.06005","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06005","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06005v1","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06005","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"KZRZ5VDV2MVX","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KZRZ5VDV2MVXP6F6","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KZRZ5VDV","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KZRZ5VDV2MVXP6F6KK5OI6RRM2","target":"record","payload":{"canonical_record":{"source":{"id":"1905.06005","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-15T07:49:10Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"9aeb2e00e6447efdb68790af47f9c5980f705f29d74b7c67cfd9e4547f8ded92","abstract_canon_sha256":"757ed6d4c2bedf3a916268a01e13f16a067cc7d41cc59f3f910984b563fd61e6"},"schema_version":"1.0"},"canonical_sha256":"56639ed475d32b77f8be52bae47a3166abd19f20637315bbad999f4fb17a8d0f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:07.779367Z","signature_b64":"OwT1Dsw+byj6FO4KbRXYQbnbZb/eOY/K3p2gw46f/TlWh7rY4q3b7wuwugW3zpuO457w2A2O4+mnoJK7t+HICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56639ed475d32b77f8be52bae47a3166abd19f20637315bbad999f4fb17a8d0f","last_reissued_at":"2026-05-17T23:46:07.778796Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:07.778796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.06005","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":"2026-05-17T23:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eLbh2nlfDbH0D72HKEqs1syO4qmOCAJ5jvL+HBE8v2LBN/a7WFAkcteSB4dgMhgFXm575g7iwee3XL9+4jmZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T13:42:51.367879Z"},"content_sha256":"37b9ca4b0a1426113b133ff5ddcc6ab3bc29f92b903573a4a0a1f40ab725c946","schema_version":"1.0","event_id":"sha256:37b9ca4b0a1426113b133ff5ddcc6ab3bc29f92b903573a4a0a1f40ab725c946"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KZRZ5VDV2MVXP6F6KK5OI6RRM2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Geometric Losses for Distributional Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Arthur Mensch (DMA, CNRS), Gabriel Peyr\\'e (DMA, Mathieu Blondel","submitted_at":"2019-05-15T07:49:10Z","abstract_excerpt":"Building upon recent advances in entropy-regularized optimal transport, and upon Fenchel duality between measures and continuous functions , we propose a generalization of the logistic loss that incorporates a metric or cost between classes. Unlike previous attempts to use optimal transport distances for learning, our loss results in unconstrained convex objective functions, supports infinite (or very large) class spaces, and naturally defines a geometric generalization of the softmax operator. The geometric properties of this loss make it suitable for predicting sparse and singular distributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06005","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":""},"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":"2026-05-17T23:46:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BerHSM5N0Nf2hbvXlSq/DsMnz61YFcZzhVa1wEljoFtKBnj3LNa41Qbm8+GFHsw/36F42p0O/+SMMCF9BilSCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T13:42:51.368222Z"},"content_sha256":"09524aec7294510f73eb220c9cb219895994ada1a8c1ac0fe10262ec973347c4","schema_version":"1.0","event_id":"sha256:09524aec7294510f73eb220c9cb219895994ada1a8c1ac0fe10262ec973347c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KZRZ5VDV2MVXP6F6KK5OI6RRM2/bundle.json","state_url":"https://pith.science/pith/KZRZ5VDV2MVXP6F6KK5OI6RRM2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KZRZ5VDV2MVXP6F6KK5OI6RRM2/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":"2026-06-08T13:42:51Z","links":{"resolver":"https://pith.science/pith/KZRZ5VDV2MVXP6F6KK5OI6RRM2","bundle":"https://pith.science/pith/KZRZ5VDV2MVXP6F6KK5OI6RRM2/bundle.json","state":"https://pith.science/pith/KZRZ5VDV2MVXP6F6KK5OI6RRM2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KZRZ5VDV2MVXP6F6KK5OI6RRM2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KZRZ5VDV2MVXP6F6KK5OI6RRM2","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":"757ed6d4c2bedf3a916268a01e13f16a067cc7d41cc59f3f910984b563fd61e6","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-15T07:49:10Z","title_canon_sha256":"9aeb2e00e6447efdb68790af47f9c5980f705f29d74b7c67cfd9e4547f8ded92"},"schema_version":"1.0","source":{"id":"1905.06005","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.06005","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"arxiv_version","alias_value":"1905.06005v1","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.06005","created_at":"2026-05-17T23:46:07Z"},{"alias_kind":"pith_short_12","alias_value":"KZRZ5VDV2MVX","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KZRZ5VDV2MVXP6F6","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KZRZ5VDV","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:09524aec7294510f73eb220c9cb219895994ada1a8c1ac0fe10262ec973347c4","target":"graph","created_at":"2026-05-17T23:46:07Z","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":"Building upon recent advances in entropy-regularized optimal transport, and upon Fenchel duality between measures and continuous functions , we propose a generalization of the logistic loss that incorporates a metric or cost between classes. Unlike previous attempts to use optimal transport distances for learning, our loss results in unconstrained convex objective functions, supports infinite (or very large) class spaces, and naturally defines a geometric generalization of the softmax operator. The geometric properties of this loss make it suitable for predicting sparse and singular distributi","authors_text":"Arthur Mensch (DMA, CNRS), Gabriel Peyr\\'e (DMA, Mathieu Blondel","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-15T07:49:10Z","title":"Geometric Losses for Distributional Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.06005","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":"sha256:37b9ca4b0a1426113b133ff5ddcc6ab3bc29f92b903573a4a0a1f40ab725c946","target":"record","created_at":"2026-05-17T23:46:07Z","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":"757ed6d4c2bedf3a916268a01e13f16a067cc7d41cc59f3f910984b563fd61e6","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-15T07:49:10Z","title_canon_sha256":"9aeb2e00e6447efdb68790af47f9c5980f705f29d74b7c67cfd9e4547f8ded92"},"schema_version":"1.0","source":{"id":"1905.06005","kind":"arxiv","version":1}},"canonical_sha256":"56639ed475d32b77f8be52bae47a3166abd19f20637315bbad999f4fb17a8d0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56639ed475d32b77f8be52bae47a3166abd19f20637315bbad999f4fb17a8d0f","first_computed_at":"2026-05-17T23:46:07.778796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:07.778796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OwT1Dsw+byj6FO4KbRXYQbnbZb/eOY/K3p2gw46f/TlWh7rY4q3b7wuwugW3zpuO457w2A2O4+mnoJK7t+HICA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:07.779367Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.06005","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37b9ca4b0a1426113b133ff5ddcc6ab3bc29f92b903573a4a0a1f40ab725c946","sha256:09524aec7294510f73eb220c9cb219895994ada1a8c1ac0fe10262ec973347c4"],"state_sha256":"559465cff1a4bf402c60cc3253bd63b6cc5c052dc6a343e8a3052857c6fe6aeb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fInPXNP7ZtgTMu7W6WA2fC1wk5QE2IXqepMTjRU+GHECL5838T0HOQA0VrnWtmi0zlvR0O7EZIH60jLxLdrCDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T13:42:51.370110Z","bundle_sha256":"fb5dc14b11508f0f852beedf2911d7e409680ef39806e97b6da5abbf98b33d55"}}