{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:T54WUWYW64MHYVPQG3MJRPTRXQ","short_pith_number":"pith:T54WUWYW","schema_version":"1.0","canonical_sha256":"9f796a5b16f7187c55f036d898be71bc11264c716ee2b973f6e7eed19cbccf91","source":{"kind":"arxiv","id":"2003.12169","version":2},"attestation_state":"computed","paper":{"title":"A Collective Learning Framework to Boost GNN Expressiveness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bruno Ribeiro, Jennifer Neville, Mengyue Hang","submitted_at":"2020-03-26T22:07:28Z","abstract_excerpt":"Graph Neural Networks (GNNs) have recently been used for node and graph classification tasks with great success, but GNNs model dependencies among the attributes of nearby neighboring nodes rather than dependencies among observed node labels. In this work, we consider the task of inductive node classification using GNNs in supervised and semi-supervised settings, with the goal of incorporating label dependencies. Because current GNNs are not universal (i.e., most-expressive) graph representations, we propose a general collective learning approach to increase the representation power of any exi"},"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":"2003.12169","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-26T22:07:28Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"577657fe1365e1a740497624559f4e1559de91b6d8d710b5beb82f2096b5c086","abstract_canon_sha256":"031b63c3bd2d50f6046156e855d777a925e6bdc5bbbcc1c6438e753fc8e86b98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:35.604083Z","signature_b64":"XpvOwwirQIBL8Tgg8sJddagHoXCkpfiBoBFmfMF6qBDpdrcntnE72SaLbaMoHzpLa8R+fIQH1q2lMZk4R/9GDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f796a5b16f7187c55f036d898be71bc11264c716ee2b973f6e7eed19cbccf91","last_reissued_at":"2026-07-05T01:38:35.603685Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:35.603685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Collective Learning Framework to Boost GNN Expressiveness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bruno Ribeiro, Jennifer Neville, Mengyue Hang","submitted_at":"2020-03-26T22:07:28Z","abstract_excerpt":"Graph Neural Networks (GNNs) have recently been used for node and graph classification tasks with great success, but GNNs model dependencies among the attributes of nearby neighboring nodes rather than dependencies among observed node labels. In this work, we consider the task of inductive node classification using GNNs in supervised and semi-supervised settings, with the goal of incorporating label dependencies. Because current GNNs are not universal (i.e., most-expressive) graph representations, we propose a general collective learning approach to increase the representation power of any exi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12169","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/2003.12169/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":"2003.12169","created_at":"2026-07-05T01:38:35.603742+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.12169v2","created_at":"2026-07-05T01:38:35.603742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12169","created_at":"2026-07-05T01:38:35.603742+00:00"},{"alias_kind":"pith_short_12","alias_value":"T54WUWYW64MH","created_at":"2026-07-05T01:38:35.603742+00:00"},{"alias_kind":"pith_short_16","alias_value":"T54WUWYW64MHYVPQ","created_at":"2026-07-05T01:38:35.603742+00:00"},{"alias_kind":"pith_short_8","alias_value":"T54WUWYW","created_at":"2026-07-05T01:38:35.603742+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.01650","citing_title":"AromaGen: Interactive Generation of Rich Olfactory Experiences with Multimodal Language Models","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T54WUWYW64MHYVPQG3MJRPTRXQ","json":"https://pith.science/pith/T54WUWYW64MHYVPQG3MJRPTRXQ.json","graph_json":"https://pith.science/api/pith-number/T54WUWYW64MHYVPQG3MJRPTRXQ/graph.json","events_json":"https://pith.science/api/pith-number/T54WUWYW64MHYVPQG3MJRPTRXQ/events.json","paper":"https://pith.science/paper/T54WUWYW"},"agent_actions":{"view_html":"https://pith.science/pith/T54WUWYW64MHYVPQG3MJRPTRXQ","download_json":"https://pith.science/pith/T54WUWYW64MHYVPQG3MJRPTRXQ.json","view_paper":"https://pith.science/paper/T54WUWYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.12169&json=true","fetch_graph":"https://pith.science/api/pith-number/T54WUWYW64MHYVPQG3MJRPTRXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/T54WUWYW64MHYVPQG3MJRPTRXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T54WUWYW64MHYVPQG3MJRPTRXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T54WUWYW64MHYVPQG3MJRPTRXQ/action/storage_attestation","attest_author":"https://pith.science/pith/T54WUWYW64MHYVPQG3MJRPTRXQ/action/author_attestation","sign_citation":"https://pith.science/pith/T54WUWYW64MHYVPQG3MJRPTRXQ/action/citation_signature","submit_replication":"https://pith.science/pith/T54WUWYW64MHYVPQG3MJRPTRXQ/action/replication_record"}},"created_at":"2026-07-05T01:38:35.603742+00:00","updated_at":"2026-07-05T01:38:35.603742+00:00"}