{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AWBIJIBIBRR2WJAPXLOSYLH2JO","short_pith_number":"pith:AWBIJIBI","schema_version":"1.0","canonical_sha256":"058284a0280c63ab240fbadd2c2cfa4b86341499d00f16ea65771491127b4f0c","source":{"kind":"arxiv","id":"2405.19933","version":2},"attestation_state":"computed","paper":{"title":"Learning Latent Graph Structures and their Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Manenti, Cesare Alippi, Daniele Zambon","submitted_at":"2024-05-30T10:49:22Z","abstract_excerpt":"Graph neural networks use relational information as an inductive bias to enhance prediction performance. Not rarely, task-relevant relations are unknown and graph structure learning approaches have been proposed to learn them from data. Given their latent nature, no graph observations are available to provide a direct training signal to the learnable relations. Therefore, graph topologies are typically learned on the prediction task alongside the other graph neural network parameters. In this paper, we demonstrate that minimizing point-prediction losses does not guarantee proper learning of th"},"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":"2405.19933","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-30T10:49:22Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1514e17299fecbce49d79994bb8c50f3c0cc9c0580e22099e2201368bc54e1e0","abstract_canon_sha256":"bad69c3315956e9fdab03f0f3cbff446dc77d9ce5607d4574445d7b7af3ec8c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:45.957784Z","signature_b64":"Q19j82+KK3hEWKfWWHyMxNin06mTqfrf7jWI2jWz1f4b2+6XwNtycLMpA43/YlB5a+UarDWn1cv3XjHQOLjJCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"058284a0280c63ab240fbadd2c2cfa4b86341499d00f16ea65771491127b4f0c","last_reissued_at":"2026-07-05T11:10:45.957272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:45.957272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Latent Graph Structures and their Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Manenti, Cesare Alippi, Daniele Zambon","submitted_at":"2024-05-30T10:49:22Z","abstract_excerpt":"Graph neural networks use relational information as an inductive bias to enhance prediction performance. Not rarely, task-relevant relations are unknown and graph structure learning approaches have been proposed to learn them from data. Given their latent nature, no graph observations are available to provide a direct training signal to the learnable relations. Therefore, graph topologies are typically learned on the prediction task alongside the other graph neural network parameters. In this paper, we demonstrate that minimizing point-prediction losses does not guarantee proper learning of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19933","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/2405.19933/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":"2405.19933","created_at":"2026-07-05T11:10:45.957341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19933v2","created_at":"2026-07-05T11:10:45.957341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19933","created_at":"2026-07-05T11:10:45.957341+00:00"},{"alias_kind":"pith_short_12","alias_value":"AWBIJIBIBRR2","created_at":"2026-07-05T11:10:45.957341+00:00"},{"alias_kind":"pith_short_16","alias_value":"AWBIJIBIBRR2WJAP","created_at":"2026-07-05T11:10:45.957341+00:00"},{"alias_kind":"pith_short_8","alias_value":"AWBIJIBI","created_at":"2026-07-05T11:10:45.957341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11831","citing_title":"From Uniform to Learned Graph Priors: Diffusion for Structure Discovery","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AWBIJIBIBRR2WJAPXLOSYLH2JO","json":"https://pith.science/pith/AWBIJIBIBRR2WJAPXLOSYLH2JO.json","graph_json":"https://pith.science/api/pith-number/AWBIJIBIBRR2WJAPXLOSYLH2JO/graph.json","events_json":"https://pith.science/api/pith-number/AWBIJIBIBRR2WJAPXLOSYLH2JO/events.json","paper":"https://pith.science/paper/AWBIJIBI"},"agent_actions":{"view_html":"https://pith.science/pith/AWBIJIBIBRR2WJAPXLOSYLH2JO","download_json":"https://pith.science/pith/AWBIJIBIBRR2WJAPXLOSYLH2JO.json","view_paper":"https://pith.science/paper/AWBIJIBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19933&json=true","fetch_graph":"https://pith.science/api/pith-number/AWBIJIBIBRR2WJAPXLOSYLH2JO/graph.json","fetch_events":"https://pith.science/api/pith-number/AWBIJIBIBRR2WJAPXLOSYLH2JO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AWBIJIBIBRR2WJAPXLOSYLH2JO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AWBIJIBIBRR2WJAPXLOSYLH2JO/action/storage_attestation","attest_author":"https://pith.science/pith/AWBIJIBIBRR2WJAPXLOSYLH2JO/action/author_attestation","sign_citation":"https://pith.science/pith/AWBIJIBIBRR2WJAPXLOSYLH2JO/action/citation_signature","submit_replication":"https://pith.science/pith/AWBIJIBIBRR2WJAPXLOSYLH2JO/action/replication_record"}},"created_at":"2026-07-05T11:10:45.957341+00:00","updated_at":"2026-07-05T11:10:45.957341+00:00"}