{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:D5JUQ2JBD5JOY466ZLLJGDOB7M","short_pith_number":"pith:D5JUQ2JB","schema_version":"1.0","canonical_sha256":"1f534869211f52ec73decad6930dc1fb1dbfccea710ad26608477e9ee589ea43","source":{"kind":"arxiv","id":"2402.07845","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Optimisation of GNNs for Node Clustering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ryan McConville, William Leeney","submitted_at":"2024-02-12T17:53:43Z","abstract_excerpt":"Graph Neural Networks (GNNs) can be trained to detect communities within a graph by learning from the duality of feature and connectivity information. Currently, the common approach for optimisation of GNNs is to use comparisons to ground-truth for hyperparameter tuning and model selection. In this work, we show that nodes can be clustered into communities with GNNs by solely optimising for modularity, without any comparison to ground-truth. Although modularity is a graph partitioning quality metric, we show that this can be used to optimise GNNs that also encode features without a drop in per"},"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":"2402.07845","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T17:53:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c81c6ed14a965e192996a73ad569aeb46a750108509113bc53c1cdcd526f8ebf","abstract_canon_sha256":"f14112bcb0a7e625ff97550fd3b9972075c8dd794fe590b2f35f4da8a6a889e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:09.149981Z","signature_b64":"OzoilvuG5fNdZeJqsrhn7Ht2lUgeM8qLuSOmUm/lLPHq8tZbk/oB2kbHyRF1ycp18BajZ7s+wUzG0ARCVccVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f534869211f52ec73decad6930dc1fb1dbfccea710ad26608477e9ee589ea43","last_reissued_at":"2026-07-05T07:47:09.149506Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:09.149506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Optimisation of GNNs for Node Clustering","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ryan McConville, William Leeney","submitted_at":"2024-02-12T17:53:43Z","abstract_excerpt":"Graph Neural Networks (GNNs) can be trained to detect communities within a graph by learning from the duality of feature and connectivity information. Currently, the common approach for optimisation of GNNs is to use comparisons to ground-truth for hyperparameter tuning and model selection. In this work, we show that nodes can be clustered into communities with GNNs by solely optimising for modularity, without any comparison to ground-truth. Although modularity is a graph partitioning quality metric, we show that this can be used to optimise GNNs that also encode features without a drop in per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07845","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/2402.07845/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":"2402.07845","created_at":"2026-07-05T07:47:09.149568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07845v2","created_at":"2026-07-05T07:47:09.149568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07845","created_at":"2026-07-05T07:47:09.149568+00:00"},{"alias_kind":"pith_short_12","alias_value":"D5JUQ2JBD5JO","created_at":"2026-07-05T07:47:09.149568+00:00"},{"alias_kind":"pith_short_16","alias_value":"D5JUQ2JBD5JOY466","created_at":"2026-07-05T07:47:09.149568+00:00"},{"alias_kind":"pith_short_8","alias_value":"D5JUQ2JB","created_at":"2026-07-05T07:47:09.149568+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.00290","citing_title":"Multi-Hierarchical Fine-Grained Feature Mapping Driven by Feature Contribution for Molecular Odor Prediction","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D5JUQ2JBD5JOY466ZLLJGDOB7M","json":"https://pith.science/pith/D5JUQ2JBD5JOY466ZLLJGDOB7M.json","graph_json":"https://pith.science/api/pith-number/D5JUQ2JBD5JOY466ZLLJGDOB7M/graph.json","events_json":"https://pith.science/api/pith-number/D5JUQ2JBD5JOY466ZLLJGDOB7M/events.json","paper":"https://pith.science/paper/D5JUQ2JB"},"agent_actions":{"view_html":"https://pith.science/pith/D5JUQ2JBD5JOY466ZLLJGDOB7M","download_json":"https://pith.science/pith/D5JUQ2JBD5JOY466ZLLJGDOB7M.json","view_paper":"https://pith.science/paper/D5JUQ2JB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07845&json=true","fetch_graph":"https://pith.science/api/pith-number/D5JUQ2JBD5JOY466ZLLJGDOB7M/graph.json","fetch_events":"https://pith.science/api/pith-number/D5JUQ2JBD5JOY466ZLLJGDOB7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D5JUQ2JBD5JOY466ZLLJGDOB7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D5JUQ2JBD5JOY466ZLLJGDOB7M/action/storage_attestation","attest_author":"https://pith.science/pith/D5JUQ2JBD5JOY466ZLLJGDOB7M/action/author_attestation","sign_citation":"https://pith.science/pith/D5JUQ2JBD5JOY466ZLLJGDOB7M/action/citation_signature","submit_replication":"https://pith.science/pith/D5JUQ2JBD5JOY466ZLLJGDOB7M/action/replication_record"}},"created_at":"2026-07-05T07:47:09.149568+00:00","updated_at":"2026-07-05T07:47:09.149568+00:00"}