{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:AG5OU4KN7QYSMHW2GBTP5DK7TS","short_pith_number":"pith:AG5OU4KN","canonical_record":{"source":{"id":"1705.10743","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-30T16:53:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c473720684ffca84c46d138925e42b6151a245dd888bf0fbc36a792d77132727","abstract_canon_sha256":"fa30c534324168569bb3cdef80ff792029db28eb4089278cfd82b36049e62c8f"},"schema_version":"1.0"},"canonical_sha256":"01baea714dfc31261eda3066fe8d5f9cb571645b9178dd91b95d2054c371d961","source":{"kind":"arxiv","id":"1705.10743","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.10743","created_at":"2026-05-18T00:43:20Z"},{"alias_kind":"arxiv_version","alias_value":"1705.10743v1","created_at":"2026-05-18T00:43:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10743","created_at":"2026-05-18T00:43:20Z"},{"alias_kind":"pith_short_12","alias_value":"AG5OU4KN7QYS","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AG5OU4KN7QYSMHW2","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AG5OU4KN","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:AG5OU4KN7QYSMHW2GBTP5DK7TS","target":"record","payload":{"canonical_record":{"source":{"id":"1705.10743","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-30T16:53:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c473720684ffca84c46d138925e42b6151a245dd888bf0fbc36a792d77132727","abstract_canon_sha256":"fa30c534324168569bb3cdef80ff792029db28eb4089278cfd82b36049e62c8f"},"schema_version":"1.0"},"canonical_sha256":"01baea714dfc31261eda3066fe8d5f9cb571645b9178dd91b95d2054c371d961","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:20.258645Z","signature_b64":"2cy0Jzbw48OoOLTg8Mghg+miNOM5DrnnBmsNwgaiUrzNJYxla7XsQAR2kUfwbS97vt0cly7y1N5UgpEQ28WYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01baea714dfc31261eda3066fe8d5f9cb571645b9178dd91b95d2054c371d961","last_reissued_at":"2026-05-18T00:43:20.257984Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:20.257984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.10743","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":"2026-05-18T00:43:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"62t/NenMyvHh6Ql9E65Sso/PIO5enDSt4KuXGdhd69NyrcSC3efVJgY+xvjXXyJmrO9wW38Zu34aA63Ep7toDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T15:22:52.466101Z"},"content_sha256":"9b0479702d8dcca7bac2a568948691f4231cea8024f78ac62655ebd5ed046b69","schema_version":"1.0","event_id":"sha256:9b0479702d8dcca7bac2a568948691f4231cea8024f78ac62655ebd5ed046b69"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:AG5OU4KN7QYSMHW2GBTP5DK7TS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Cramer Distance as a Solution to Biased Wasserstein Gradients","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Balaji Lakshminarayanan, Ivo Danihelka, Marc G. Bellemare, R\\'emi Munos, Shakir Mohamed, Stephan Hoyer, Will Dabney","submitted_at":"2017-05-30T16:53:12Z","abstract_excerpt":"The Wasserstein probability metric has received much attention from the machine learning community. Unlike the Kullback-Leibler divergence, which strictly measures change in probability, the Wasserstein metric reflects the underlying geometry between outcomes. The value of being sensitive to this geometry has been demonstrated, among others, in ordinal regression and generative modelling. In this paper we describe three natural properties of probability divergences that reflect requirements from machine learning: sum invariance, scale sensitivity, and unbiased sample gradients. The Wasserstein"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10743","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":"2026-05-18T00:43:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WGW/ZLK3FC66TgYs/2KdlseuMQp5IvqlnHeCEchOagQOiqLT8s4hT7m1IB5HsPy8Eg404jKUBPs9Jvk55DLLBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T15:22:52.466848Z"},"content_sha256":"7bed4d2ae7b37f5e3a3a457eec2b6f245227cb9515a1d3b30307dc42176e0fce","schema_version":"1.0","event_id":"sha256:7bed4d2ae7b37f5e3a3a457eec2b6f245227cb9515a1d3b30307dc42176e0fce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AG5OU4KN7QYSMHW2GBTP5DK7TS/bundle.json","state_url":"https://pith.science/pith/AG5OU4KN7QYSMHW2GBTP5DK7TS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AG5OU4KN7QYSMHW2GBTP5DK7TS/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":"2026-06-11T15:22:52Z","links":{"resolver":"https://pith.science/pith/AG5OU4KN7QYSMHW2GBTP5DK7TS","bundle":"https://pith.science/pith/AG5OU4KN7QYSMHW2GBTP5DK7TS/bundle.json","state":"https://pith.science/pith/AG5OU4KN7QYSMHW2GBTP5DK7TS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AG5OU4KN7QYSMHW2GBTP5DK7TS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:AG5OU4KN7QYSMHW2GBTP5DK7TS","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":"fa30c534324168569bb3cdef80ff792029db28eb4089278cfd82b36049e62c8f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-30T16:53:12Z","title_canon_sha256":"c473720684ffca84c46d138925e42b6151a245dd888bf0fbc36a792d77132727"},"schema_version":"1.0","source":{"id":"1705.10743","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.10743","created_at":"2026-05-18T00:43:20Z"},{"alias_kind":"arxiv_version","alias_value":"1705.10743v1","created_at":"2026-05-18T00:43:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10743","created_at":"2026-05-18T00:43:20Z"},{"alias_kind":"pith_short_12","alias_value":"AG5OU4KN7QYS","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AG5OU4KN7QYSMHW2","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AG5OU4KN","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:7bed4d2ae7b37f5e3a3a457eec2b6f245227cb9515a1d3b30307dc42176e0fce","target":"graph","created_at":"2026-05-18T00:43:20Z","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 Wasserstein probability metric has received much attention from the machine learning community. Unlike the Kullback-Leibler divergence, which strictly measures change in probability, the Wasserstein metric reflects the underlying geometry between outcomes. The value of being sensitive to this geometry has been demonstrated, among others, in ordinal regression and generative modelling. In this paper we describe three natural properties of probability divergences that reflect requirements from machine learning: sum invariance, scale sensitivity, and unbiased sample gradients. The Wasserstein","authors_text":"Balaji Lakshminarayanan, Ivo Danihelka, Marc G. Bellemare, R\\'emi Munos, Shakir Mohamed, Stephan Hoyer, Will Dabney","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-30T16:53:12Z","title":"The Cramer Distance as a Solution to Biased Wasserstein Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10743","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":"sha256:9b0479702d8dcca7bac2a568948691f4231cea8024f78ac62655ebd5ed046b69","target":"record","created_at":"2026-05-18T00:43:20Z","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":"fa30c534324168569bb3cdef80ff792029db28eb4089278cfd82b36049e62c8f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-30T16:53:12Z","title_canon_sha256":"c473720684ffca84c46d138925e42b6151a245dd888bf0fbc36a792d77132727"},"schema_version":"1.0","source":{"id":"1705.10743","kind":"arxiv","version":1}},"canonical_sha256":"01baea714dfc31261eda3066fe8d5f9cb571645b9178dd91b95d2054c371d961","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01baea714dfc31261eda3066fe8d5f9cb571645b9178dd91b95d2054c371d961","first_computed_at":"2026-05-18T00:43:20.257984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:20.257984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2cy0Jzbw48OoOLTg8Mghg+miNOM5DrnnBmsNwgaiUrzNJYxla7XsQAR2kUfwbS97vt0cly7y1N5UgpEQ28WYDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:20.258645Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.10743","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b0479702d8dcca7bac2a568948691f4231cea8024f78ac62655ebd5ed046b69","sha256:7bed4d2ae7b37f5e3a3a457eec2b6f245227cb9515a1d3b30307dc42176e0fce"],"state_sha256":"6505d6cc755e46b836095714166f765a083ea3d9698bfbf466a9db2a92b3cc57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ifo1pTjupBVeC1nYEBAFIGCXh+rUIAUuykTPVf6ZNZSbYfdLKcM+kz3YVeUeRxvDTqPeSsgm9XpbLFEyg/XmCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T15:22:52.469851Z","bundle_sha256":"46436eb611755b14776eb1c30951640ae4b1d26e7fdb568716a06494973cf283"}}