{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RVHHO6FNSSAV3F3BAFMR3QPYPF","short_pith_number":"pith:RVHHO6FN","schema_version":"1.0","canonical_sha256":"8d4e7778ad94815d976101591dc1f87953e2a12d055c51764b5708874e46b4aa","source":{"kind":"arxiv","id":"2110.02753","version":3},"attestation_state":"computed","paper":{"title":"Semi-relaxed Gromov-Wasserstein divergence with applications on graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"C\\'edric Vincent-Cuaz, Marco Corneli, Nicolas Courty, R\\'emi Flamary, Titouan Vayer","submitted_at":"2021-10-06T13:38:31Z","abstract_excerpt":"Comparing structured objects such as graphs is a fundamental operation involved in many learning tasks. To this end, the Gromov-Wasserstein (GW) distance, based on Optimal Transport (OT), has proven to be successful in handling the specific nature of the associated objects. More specifically, through the nodes connectivity relations, GW operates on graphs, seen as probability measures over specific spaces. At the core of OT is the idea of conservation of mass, which imposes a coupling between all the nodes from the two considered graphs. We argue in this paper that this property can be detrime"},"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":"2110.02753","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-06T13:38:31Z","cross_cats_sorted":[],"title_canon_sha256":"9b3ea0852c3e2dbb2e8dad57a792311ea7bb3a6c574bd9a11a5c1d44c4d7e482","abstract_canon_sha256":"cd2b567cfce029843b45b403a15607b5641bf798af61ae2518cbbfa44b86b76c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:58.304511Z","signature_b64":"h9yNGJYy7JU/OUzOoz9l6NVf6lgTfKhOM2rRyggDwVOsxsOM1KfGt+8GWefoqfdjpsPT2XwKhffJ/A5XXAcLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d4e7778ad94815d976101591dc1f87953e2a12d055c51764b5708874e46b4aa","last_reissued_at":"2026-07-05T04:00:58.304087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:58.304087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-relaxed Gromov-Wasserstein divergence with applications on graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"C\\'edric Vincent-Cuaz, Marco Corneli, Nicolas Courty, R\\'emi Flamary, Titouan Vayer","submitted_at":"2021-10-06T13:38:31Z","abstract_excerpt":"Comparing structured objects such as graphs is a fundamental operation involved in many learning tasks. To this end, the Gromov-Wasserstein (GW) distance, based on Optimal Transport (OT), has proven to be successful in handling the specific nature of the associated objects. More specifically, through the nodes connectivity relations, GW operates on graphs, seen as probability measures over specific spaces. At the core of OT is the idea of conservation of mass, which imposes a coupling between all the nodes from the two considered graphs. We argue in this paper that this property can be detrime"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.02753","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/2110.02753/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2110.02753","created_at":"2026-07-05T04:00:58.304146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.02753v3","created_at":"2026-07-05T04:00:58.304146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.02753","created_at":"2026-07-05T04:00:58.304146+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVHHO6FNSSAV","created_at":"2026-07-05T04:00:58.304146+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVHHO6FNSSAV3F3B","created_at":"2026-07-05T04:00:58.304146+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVHHO6FN","created_at":"2026-07-05T04:00:58.304146+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28488","citing_title":"Bridging Maximum Likelihood and Optimal Transport for Efficient Inference and Model Selection in Stochastic Block Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2501.17443","citing_title":"Gradual Domain Adaptation for Graph Learning","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08546","citing_title":"Sliced Inner Product Gromov-Wasserstein Distances","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RVHHO6FNSSAV3F3BAFMR3QPYPF","json":"https://pith.science/pith/RVHHO6FNSSAV3F3BAFMR3QPYPF.json","graph_json":"https://pith.science/api/pith-number/RVHHO6FNSSAV3F3BAFMR3QPYPF/graph.json","events_json":"https://pith.science/api/pith-number/RVHHO6FNSSAV3F3BAFMR3QPYPF/events.json","paper":"https://pith.science/paper/RVHHO6FN"},"agent_actions":{"view_html":"https://pith.science/pith/RVHHO6FNSSAV3F3BAFMR3QPYPF","download_json":"https://pith.science/pith/RVHHO6FNSSAV3F3BAFMR3QPYPF.json","view_paper":"https://pith.science/paper/RVHHO6FN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.02753&json=true","fetch_graph":"https://pith.science/api/pith-number/RVHHO6FNSSAV3F3BAFMR3QPYPF/graph.json","fetch_events":"https://pith.science/api/pith-number/RVHHO6FNSSAV3F3BAFMR3QPYPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVHHO6FNSSAV3F3BAFMR3QPYPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVHHO6FNSSAV3F3BAFMR3QPYPF/action/storage_attestation","attest_author":"https://pith.science/pith/RVHHO6FNSSAV3F3BAFMR3QPYPF/action/author_attestation","sign_citation":"https://pith.science/pith/RVHHO6FNSSAV3F3BAFMR3QPYPF/action/citation_signature","submit_replication":"https://pith.science/pith/RVHHO6FNSSAV3F3BAFMR3QPYPF/action/replication_record"}},"created_at":"2026-07-05T04:00:58.304146+00:00","updated_at":"2026-07-05T04:00:58.304146+00:00"}