{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VUNM5EQSPYJGQMAEYRMH4QNHGM","short_pith_number":"pith:VUNM5EQS","schema_version":"1.0","canonical_sha256":"ad1ace92127e12683004c4587e41a73303f8ea0e246c061c6de0a05beff24c5e","source":{"kind":"arxiv","id":"2007.03373","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical and Unsupervised Graph Representation Learning with Loukas's Coarsening","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amaury Habrard, Aur\\'elien Garivier, Louis B\\'ethune, Pierre Borgnat, Yacouba Kaloga","submitted_at":"2020-07-07T12:04:38Z","abstract_excerpt":"We propose a novel algorithm for unsupervised graph representation learning with attributed graphs. It combines three advantages addressing some current limitations of the literature: i) The model is inductive: it can embed new graphs without re-training in the presence of new data; ii) The method takes into account both micro-structures and macro-structures by looking at the attributed graphs at different scales; iii) The model is end-to-end differentiable: it is a building block that can be plugged into deep learning pipelines and allows for back-propagation. We show that combining a coarsen"},"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":"2007.03373","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-07-07T12:04:38Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"a0ca980cbdb8fd58f1a8bcd886b0418f9b97aca0c6d55fd55b84ce1b33a0a4cc","abstract_canon_sha256":"7d5652b93908a4a7055127ef6df1692278c12c8bb2a1076921c21c368f312567"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:25.604175Z","signature_b64":"PDwyIVKuJEnHqHelH7DO6Xt/FTuhPyfil2Au3CUIRVJuDTUMKcYz7MVTgck7BrlyWtNFZG5xzIrGG4MlI+xlCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad1ace92127e12683004c4587e41a73303f8ea0e246c061c6de0a05beff24c5e","last_reissued_at":"2026-07-05T01:27:25.603667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:25.603667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical and Unsupervised Graph Representation Learning with Loukas's Coarsening","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amaury Habrard, Aur\\'elien Garivier, Louis B\\'ethune, Pierre Borgnat, Yacouba Kaloga","submitted_at":"2020-07-07T12:04:38Z","abstract_excerpt":"We propose a novel algorithm for unsupervised graph representation learning with attributed graphs. It combines three advantages addressing some current limitations of the literature: i) The model is inductive: it can embed new graphs without re-training in the presence of new data; ii) The method takes into account both micro-structures and macro-structures by looking at the attributed graphs at different scales; iii) The model is end-to-end differentiable: it is a building block that can be plugged into deep learning pipelines and allows for back-propagation. We show that combining a coarsen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.03373","kind":"arxiv","version":2},"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/2007.03373/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":"2007.03373","created_at":"2026-07-05T01:27:25.603730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.03373v2","created_at":"2026-07-05T01:27:25.603730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.03373","created_at":"2026-07-05T01:27:25.603730+00:00"},{"alias_kind":"pith_short_12","alias_value":"VUNM5EQSPYJG","created_at":"2026-07-05T01:27:25.603730+00:00"},{"alias_kind":"pith_short_16","alias_value":"VUNM5EQSPYJGQMAE","created_at":"2026-07-05T01:27:25.603730+00:00"},{"alias_kind":"pith_short_8","alias_value":"VUNM5EQS","created_at":"2026-07-05T01:27:25.603730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.04366","citing_title":"DispFormer: A Pretrained Transformer Incorporating Physical Constraints for Dispersion Curve Inversion","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VUNM5EQSPYJGQMAEYRMH4QNHGM","json":"https://pith.science/pith/VUNM5EQSPYJGQMAEYRMH4QNHGM.json","graph_json":"https://pith.science/api/pith-number/VUNM5EQSPYJGQMAEYRMH4QNHGM/graph.json","events_json":"https://pith.science/api/pith-number/VUNM5EQSPYJGQMAEYRMH4QNHGM/events.json","paper":"https://pith.science/paper/VUNM5EQS"},"agent_actions":{"view_html":"https://pith.science/pith/VUNM5EQSPYJGQMAEYRMH4QNHGM","download_json":"https://pith.science/pith/VUNM5EQSPYJGQMAEYRMH4QNHGM.json","view_paper":"https://pith.science/paper/VUNM5EQS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.03373&json=true","fetch_graph":"https://pith.science/api/pith-number/VUNM5EQSPYJGQMAEYRMH4QNHGM/graph.json","fetch_events":"https://pith.science/api/pith-number/VUNM5EQSPYJGQMAEYRMH4QNHGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VUNM5EQSPYJGQMAEYRMH4QNHGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VUNM5EQSPYJGQMAEYRMH4QNHGM/action/storage_attestation","attest_author":"https://pith.science/pith/VUNM5EQSPYJGQMAEYRMH4QNHGM/action/author_attestation","sign_citation":"https://pith.science/pith/VUNM5EQSPYJGQMAEYRMH4QNHGM/action/citation_signature","submit_replication":"https://pith.science/pith/VUNM5EQSPYJGQMAEYRMH4QNHGM/action/replication_record"}},"created_at":"2026-07-05T01:27:25.603730+00:00","updated_at":"2026-07-05T01:27:25.603730+00:00"}