{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7ZAG65ZK2N7J3W6NX5NELMIDF2","short_pith_number":"pith:7ZAG65ZK","canonical_record":{"source":{"id":"1911.03117","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-08T08:27:19Z","cross_cats_sorted":["cs.GR","cs.LG","math.OC"],"title_canon_sha256":"1394efecff4fad28bd31a4fab3605ba3bf039fb6843caafb625f6ac6d405a435","abstract_canon_sha256":"41ed807d7629886740f22b42cf576e715c05a577c3dcd25be781e8f744416b74"},"schema_version":"1.0"},"canonical_sha256":"fe406f772ad37e9ddbcdbf5a45b1032e8afff723c3933cc9ace9a9778f42c363","source":{"kind":"arxiv","id":"1911.03117","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.03117","created_at":"2026-07-05T01:49:14Z"},{"alias_kind":"arxiv_version","alias_value":"1911.03117v3","created_at":"2026-07-05T01:49:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03117","created_at":"2026-07-05T01:49:14Z"},{"alias_kind":"pith_short_12","alias_value":"7ZAG65ZK2N7J","created_at":"2026-07-05T01:49:14Z"},{"alias_kind":"pith_short_16","alias_value":"7ZAG65ZK2N7J3W6N","created_at":"2026-07-05T01:49:14Z"},{"alias_kind":"pith_short_8","alias_value":"7ZAG65ZK","created_at":"2026-07-05T01:49:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7ZAG65ZK2N7J3W6NX5NELMIDF2","target":"record","payload":{"canonical_record":{"source":{"id":"1911.03117","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-08T08:27:19Z","cross_cats_sorted":["cs.GR","cs.LG","math.OC"],"title_canon_sha256":"1394efecff4fad28bd31a4fab3605ba3bf039fb6843caafb625f6ac6d405a435","abstract_canon_sha256":"41ed807d7629886740f22b42cf576e715c05a577c3dcd25be781e8f744416b74"},"schema_version":"1.0"},"canonical_sha256":"fe406f772ad37e9ddbcdbf5a45b1032e8afff723c3933cc9ace9a9778f42c363","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:14.292918Z","signature_b64":"hxaysseXAQBEl3P9RruSRcwQXvtitKCo9HM4H2S0fBqcRx4Ak5OybOiZ+VtTf70GKzdpzHuoHP9SyAKq8F6wBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe406f772ad37e9ddbcdbf5a45b1032e8afff723c3933cc9ace9a9778f42c363","last_reissued_at":"2026-07-05T01:49:14.292452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:14.292452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.03117","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":"2026-07-05T01:49:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1nRdKbCaQv7826rg2KsrNUUR1Co39AuAUbl3CWsnjn6Rsss9r7YRt9HhnQgtJbPd/Eh3XUsKWGxvl7ua2KaMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:43:26.345660Z"},"content_sha256":"d0dc79442ac0c4f5f05d2990766650105ad65f6ba74e9750d4a65e0c05241f88","schema_version":"1.0","event_id":"sha256:d0dc79442ac0c4f5f05d2990766650105ad65f6ba74e9750d4a65e0c05241f88"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7ZAG65ZK2N7J3W6NX5NELMIDF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ground Metric Learning on Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"David Coeurjolly, Gabriel Peyr\\'e, Marco Cuturi, Matthieu Heitz, Nicolas Bonneel","submitted_at":"2019-11-08T08:27:19Z","abstract_excerpt":"Optimal transport (OT) distances between probability distributions are parameterized by the ground metric they use between observations. Their relevance for real-life applications strongly hinges on whether that ground metric parameter is suitably chosen. Selecting it adaptively and algorithmically from prior knowledge, the so-called ground metric learning GML) problem, has therefore appeared in various settings. We consider it in this paper when the learned metric is constrained to be a geodesic distance on a graph that supports the measures of interest. This imposes a rich structure for cand"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03117","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/1911.03117/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":"2026-07-05T01:49:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Wj3ref4yNZa+/1m/O4Dz+ObYjNs2sj4958EQqyz3NGLWdd4RuGZPGUzIDwGYJN8pFEWR+x64drMOPMszK43Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:43:26.346900Z"},"content_sha256":"4b8832838cde6cbd11779851522705cbdd8ab6eb8fb93327d6ce90512e3c5d66","schema_version":"1.0","event_id":"sha256:4b8832838cde6cbd11779851522705cbdd8ab6eb8fb93327d6ce90512e3c5d66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7ZAG65ZK2N7J3W6NX5NELMIDF2/bundle.json","state_url":"https://pith.science/pith/7ZAG65ZK2N7J3W6NX5NELMIDF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7ZAG65ZK2N7J3W6NX5NELMIDF2/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":"2026-08-10T18:43:26Z","links":{"resolver":"https://pith.science/pith/7ZAG65ZK2N7J3W6NX5NELMIDF2","bundle":"https://pith.science/pith/7ZAG65ZK2N7J3W6NX5NELMIDF2/bundle.json","state":"https://pith.science/pith/7ZAG65ZK2N7J3W6NX5NELMIDF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7ZAG65ZK2N7J3W6NX5NELMIDF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7ZAG65ZK2N7J3W6NX5NELMIDF2","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":"41ed807d7629886740f22b42cf576e715c05a577c3dcd25be781e8f744416b74","cross_cats_sorted":["cs.GR","cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-08T08:27:19Z","title_canon_sha256":"1394efecff4fad28bd31a4fab3605ba3bf039fb6843caafb625f6ac6d405a435"},"schema_version":"1.0","source":{"id":"1911.03117","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.03117","created_at":"2026-07-05T01:49:14Z"},{"alias_kind":"arxiv_version","alias_value":"1911.03117v3","created_at":"2026-07-05T01:49:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03117","created_at":"2026-07-05T01:49:14Z"},{"alias_kind":"pith_short_12","alias_value":"7ZAG65ZK2N7J","created_at":"2026-07-05T01:49:14Z"},{"alias_kind":"pith_short_16","alias_value":"7ZAG65ZK2N7J3W6N","created_at":"2026-07-05T01:49:14Z"},{"alias_kind":"pith_short_8","alias_value":"7ZAG65ZK","created_at":"2026-07-05T01:49:14Z"}],"graph_snapshots":[{"event_id":"sha256:4b8832838cde6cbd11779851522705cbdd8ab6eb8fb93327d6ce90512e3c5d66","target":"graph","created_at":"2026-07-05T01:49:14Z","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/1911.03117/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimal transport (OT) distances between probability distributions are parameterized by the ground metric they use between observations. Their relevance for real-life applications strongly hinges on whether that ground metric parameter is suitably chosen. Selecting it adaptively and algorithmically from prior knowledge, the so-called ground metric learning GML) problem, has therefore appeared in various settings. We consider it in this paper when the learned metric is constrained to be a geodesic distance on a graph that supports the measures of interest. This imposes a rich structure for cand","authors_text":"David Coeurjolly, Gabriel Peyr\\'e, Marco Cuturi, Matthieu Heitz, Nicolas Bonneel","cross_cats":["cs.GR","cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-08T08:27:19Z","title":"Ground Metric Learning on Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03117","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:d0dc79442ac0c4f5f05d2990766650105ad65f6ba74e9750d4a65e0c05241f88","target":"record","created_at":"2026-07-05T01:49:14Z","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":"41ed807d7629886740f22b42cf576e715c05a577c3dcd25be781e8f744416b74","cross_cats_sorted":["cs.GR","cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-08T08:27:19Z","title_canon_sha256":"1394efecff4fad28bd31a4fab3605ba3bf039fb6843caafb625f6ac6d405a435"},"schema_version":"1.0","source":{"id":"1911.03117","kind":"arxiv","version":3}},"canonical_sha256":"fe406f772ad37e9ddbcdbf5a45b1032e8afff723c3933cc9ace9a9778f42c363","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe406f772ad37e9ddbcdbf5a45b1032e8afff723c3933cc9ace9a9778f42c363","first_computed_at":"2026-07-05T01:49:14.292452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:14.292452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hxaysseXAQBEl3P9RruSRcwQXvtitKCo9HM4H2S0fBqcRx4Ak5OybOiZ+VtTf70GKzdpzHuoHP9SyAKq8F6wBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:14.292918Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.03117","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0dc79442ac0c4f5f05d2990766650105ad65f6ba74e9750d4a65e0c05241f88","sha256:4b8832838cde6cbd11779851522705cbdd8ab6eb8fb93327d6ce90512e3c5d66"],"state_sha256":"ef5d10f8ed34ae86adba278835488ce14db6d857c6d2444c6ec2607efd295adb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w6lWMCawiub8weJ73AfAjVbB4tOAeM02oQooGHC68f1rZaQD2WCUNgxTz7BPkUCdPuyrT/A/8Vvr4DfsH22fBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:43:26.353131Z","bundle_sha256":"59376ac6eea35c45c7df782d49d2f5eec23d87188fbc4a88670089f033ec5a1e"}}