{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BR3VQDVPVSDRXEESAGR4GI2N44","short_pith_number":"pith:BR3VQDVP","schema_version":"1.0","canonical_sha256":"0c77580eafac871b909201a3c3234de718f6bcebc456fb7696a76ea658fb31cf","source":{"kind":"arxiv","id":"1805.09114","version":3},"attestation_state":"computed","paper":{"title":"Optimal Transport for structured data with application on graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Laetitia Chapel, Nicolas Courty, R\\'emi Flamary, Romain Tavenard, Titouan Vayer","submitted_at":"2018-05-23T13:13:27Z","abstract_excerpt":"This work considers the problem of computing distances between structured objects such as undirected graphs, seen as probability distributions in a specific metric space. We consider a new transportation distance (i.e. that minimizes a total cost of transporting probability masses) that unveils the geometric nature of the structured objects space. Unlike Wasserstein or Gromov-Wasserstein metrics that focus solely and respectively on features (by considering a metric in the feature space) or structure (by seeing structure as a metric space), our new distance exploits jointly both information, a"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1805.09114","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-05-23T13:13:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a50dcfce384fe6698be2a8f1e0fe8c67e038a432520c816d1a3230348695fbb7","abstract_canon_sha256":"7b5beca70fcf5bd11669b83135e141a2a22aca75cd71b319926dc959d1d14777"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:30.429110Z","signature_b64":"LbZi7bwSkpO5dq49jeOWEItzBFJ7LR0c6jQB9otTCmCnYdDS0sQFi/Dw2+YgGMxGp1EyvoGQg4qnm3/zIdbPDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c77580eafac871b909201a3c3234de718f6bcebc456fb7696a76ea658fb31cf","last_reissued_at":"2026-05-17T23:46:30.428623Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:30.428623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Transport for structured data with application on graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Laetitia Chapel, Nicolas Courty, R\\'emi Flamary, Romain Tavenard, Titouan Vayer","submitted_at":"2018-05-23T13:13:27Z","abstract_excerpt":"This work considers the problem of computing distances between structured objects such as undirected graphs, seen as probability distributions in a specific metric space. We consider a new transportation distance (i.e. that minimizes a total cost of transporting probability masses) that unveils the geometric nature of the structured objects space. Unlike Wasserstein or Gromov-Wasserstein metrics that focus solely and respectively on features (by considering a metric in the feature space) or structure (by seeing structure as a metric space), our new distance exploits jointly both information, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09114","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1805.09114","created_at":"2026-05-17T23:46:30.428701+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.09114v3","created_at":"2026-05-17T23:46:30.428701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09114","created_at":"2026-05-17T23:46:30.428701+00:00"},{"alias_kind":"pith_short_12","alias_value":"BR3VQDVPVSDR","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"BR3VQDVPVSDRXEES","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"BR3VQDVP","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.00257","citing_title":"Hausdorff and Wasserstein metrics on graphs and other structured data","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2602.06810","citing_title":"Calibrating Tabular Anomaly Detection via Optimal Transport","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BR3VQDVPVSDRXEESAGR4GI2N44","json":"https://pith.science/pith/BR3VQDVPVSDRXEESAGR4GI2N44.json","graph_json":"https://pith.science/api/pith-number/BR3VQDVPVSDRXEESAGR4GI2N44/graph.json","events_json":"https://pith.science/api/pith-number/BR3VQDVPVSDRXEESAGR4GI2N44/events.json","paper":"https://pith.science/paper/BR3VQDVP"},"agent_actions":{"view_html":"https://pith.science/pith/BR3VQDVPVSDRXEESAGR4GI2N44","download_json":"https://pith.science/pith/BR3VQDVPVSDRXEESAGR4GI2N44.json","view_paper":"https://pith.science/paper/BR3VQDVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.09114&json=true","fetch_graph":"https://pith.science/api/pith-number/BR3VQDVPVSDRXEESAGR4GI2N44/graph.json","fetch_events":"https://pith.science/api/pith-number/BR3VQDVPVSDRXEESAGR4GI2N44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BR3VQDVPVSDRXEESAGR4GI2N44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BR3VQDVPVSDRXEESAGR4GI2N44/action/storage_attestation","attest_author":"https://pith.science/pith/BR3VQDVPVSDRXEESAGR4GI2N44/action/author_attestation","sign_citation":"https://pith.science/pith/BR3VQDVPVSDRXEESAGR4GI2N44/action/citation_signature","submit_replication":"https://pith.science/pith/BR3VQDVPVSDRXEESAGR4GI2N44/action/replication_record"}},"created_at":"2026-05-17T23:46:30.428701+00:00","updated_at":"2026-05-17T23:46:30.428701+00:00"}