{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3PDXLHM3PNIEOD5UVUEM3HIA5E","short_pith_number":"pith:3PDXLHM3","schema_version":"1.0","canonical_sha256":"dbc7759d9b7b50470fb4ad08cd9d00e91829fab0c510d9b1426afe66038a7a48","source":{"kind":"arxiv","id":"2506.11869","version":3},"attestation_state":"computed","paper":{"title":"How do Probabilistic Graphical Models and Graph Neural Networks Look at Network Data?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG","physics.soc-ph"],"primary_cat":"stat.ML","authors_text":"Caterina De Bacco, Michela Lapenna","submitted_at":"2025-06-13T15:19:28Z","abstract_excerpt":"Graphs are a powerful data structure for representing relational data and are widely used to describe complex real-world systems. Probabilistic Graphical Models (PGMs) and Graph Neural Networks (GNNs) can both leverage graph-structured data, but their inherent functioning is different. The question is how do they compare in capturing the information contained in networked datasets? We address this objective by solving a link prediction task and we conduct three main experiments, on both synthetic and real networks: one focuses on how PGMs and GNNs handle input features, while the other two inv"},"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":"2506.11869","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-13T15:19:28Z","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG","physics.soc-ph"],"title_canon_sha256":"4949087405e7bc0a0048abec6c1a47f6163bef2a5a144340249d901fae953fe8","abstract_canon_sha256":"cb5dde0cebe3929adae67b4d062467d1b98259e5d32d4ab715982787a1dff052"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:57.168146Z","signature_b64":"Yh7Q97o2eA6pAagcp2/X+YTOieDIE8PM/CSE9R8ww8fGgwoSlUYfy3YpZ1RbZz+LN52TqLIU4rs05qcGYHbvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbc7759d9b7b50470fb4ad08cd9d00e91829fab0c510d9b1426afe66038a7a48","last_reissued_at":"2026-07-05T11:57:57.167670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:57.167670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How do Probabilistic Graphical Models and Graph Neural Networks Look at Network Data?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cond-mat.stat-mech","cs.LG","physics.soc-ph"],"primary_cat":"stat.ML","authors_text":"Caterina De Bacco, Michela Lapenna","submitted_at":"2025-06-13T15:19:28Z","abstract_excerpt":"Graphs are a powerful data structure for representing relational data and are widely used to describe complex real-world systems. Probabilistic Graphical Models (PGMs) and Graph Neural Networks (GNNs) can both leverage graph-structured data, but their inherent functioning is different. The question is how do they compare in capturing the information contained in networked datasets? We address this objective by solving a link prediction task and we conduct three main experiments, on both synthetic and real networks: one focuses on how PGMs and GNNs handle input features, while the other two inv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11869","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/2506.11869/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":"2506.11869","created_at":"2026-07-05T11:57:57.167727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11869v3","created_at":"2026-07-05T11:57:57.167727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11869","created_at":"2026-07-05T11:57:57.167727+00:00"},{"alias_kind":"pith_short_12","alias_value":"3PDXLHM3PNIE","created_at":"2026-07-05T11:57:57.167727+00:00"},{"alias_kind":"pith_short_16","alias_value":"3PDXLHM3PNIEOD5U","created_at":"2026-07-05T11:57:57.167727+00:00"},{"alias_kind":"pith_short_8","alias_value":"3PDXLHM3","created_at":"2026-07-05T11:57:57.167727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3PDXLHM3PNIEOD5UVUEM3HIA5E","json":"https://pith.science/pith/3PDXLHM3PNIEOD5UVUEM3HIA5E.json","graph_json":"https://pith.science/api/pith-number/3PDXLHM3PNIEOD5UVUEM3HIA5E/graph.json","events_json":"https://pith.science/api/pith-number/3PDXLHM3PNIEOD5UVUEM3HIA5E/events.json","paper":"https://pith.science/paper/3PDXLHM3"},"agent_actions":{"view_html":"https://pith.science/pith/3PDXLHM3PNIEOD5UVUEM3HIA5E","download_json":"https://pith.science/pith/3PDXLHM3PNIEOD5UVUEM3HIA5E.json","view_paper":"https://pith.science/paper/3PDXLHM3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11869&json=true","fetch_graph":"https://pith.science/api/pith-number/3PDXLHM3PNIEOD5UVUEM3HIA5E/graph.json","fetch_events":"https://pith.science/api/pith-number/3PDXLHM3PNIEOD5UVUEM3HIA5E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3PDXLHM3PNIEOD5UVUEM3HIA5E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3PDXLHM3PNIEOD5UVUEM3HIA5E/action/storage_attestation","attest_author":"https://pith.science/pith/3PDXLHM3PNIEOD5UVUEM3HIA5E/action/author_attestation","sign_citation":"https://pith.science/pith/3PDXLHM3PNIEOD5UVUEM3HIA5E/action/citation_signature","submit_replication":"https://pith.science/pith/3PDXLHM3PNIEOD5UVUEM3HIA5E/action/replication_record"}},"created_at":"2026-07-05T11:57:57.167727+00:00","updated_at":"2026-07-05T11:57:57.167727+00:00"}