{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:POMUAOZWBOKB7S3RHESYIR2FKU","short_pith_number":"pith:POMUAOZW","schema_version":"1.0","canonical_sha256":"7b99403b360b941fcb71392584474555184753b02bdbe44068bb2234dc0c5de1","source":{"kind":"arxiv","id":"2209.06589","version":4},"attestation_state":"computed","paper":{"title":"Towards Better Generalization with Flexible Representation of Multi-Module Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hyungeun Lee, KiJung Yoon","submitted_at":"2022-09-14T12:13:59Z","abstract_excerpt":"Graph neural networks (GNNs) have become compelling models designed to perform learning and inference on graph-structured data. However, little work has been done to understand the fundamental limitations of GNNs for scaling to larger graphs and generalizing to out-of-distribution (OOD) inputs. In this paper, we use a random graph generator to systematically investigate how the graph size and structural properties affect the predictive performance of GNNs. We present specific evidence that the average node degree is a key feature in determining whether GNNs can generalize to unseen graphs, and"},"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":"2209.06589","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-14T12:13:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5049731191ca18141aee90a0016a181f3a510366e88771fadc730555387f2109","abstract_canon_sha256":"c89b742139b8e6fc3910593fa40a4b15e72d4b19a031d8560799e51c3b26b8af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:29.788858Z","signature_b64":"HzLVTbRBHszzLh4npqOMe7uYhWifjBdA5u/PA1PVRnROuNqZg6mQXfbFECtqaXawLHAqI7HbxgGG8R5jCAAaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b99403b360b941fcb71392584474555184753b02bdbe44068bb2234dc0c5de1","last_reissued_at":"2026-07-05T07:05:29.788340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:29.788340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Better Generalization with Flexible Representation of Multi-Module Graph Neural Networks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hyungeun Lee, KiJung Yoon","submitted_at":"2022-09-14T12:13:59Z","abstract_excerpt":"Graph neural networks (GNNs) have become compelling models designed to perform learning and inference on graph-structured data. However, little work has been done to understand the fundamental limitations of GNNs for scaling to larger graphs and generalizing to out-of-distribution (OOD) inputs. In this paper, we use a random graph generator to systematically investigate how the graph size and structural properties affect the predictive performance of GNNs. We present specific evidence that the average node degree is a key feature in determining whether GNNs can generalize to unseen graphs, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06589","kind":"arxiv","version":4},"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/2209.06589/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":"2209.06589","created_at":"2026-07-05T07:05:29.788432+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.06589v4","created_at":"2026-07-05T07:05:29.788432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06589","created_at":"2026-07-05T07:05:29.788432+00:00"},{"alias_kind":"pith_short_12","alias_value":"POMUAOZWBOKB","created_at":"2026-07-05T07:05:29.788432+00:00"},{"alias_kind":"pith_short_16","alias_value":"POMUAOZWBOKB7S3R","created_at":"2026-07-05T07:05:29.788432+00:00"},{"alias_kind":"pith_short_8","alias_value":"POMUAOZW","created_at":"2026-07-05T07:05:29.788432+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12226","citing_title":"Learning Causality for Modern Machine Learning","ref_index":1998,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POMUAOZWBOKB7S3RHESYIR2FKU","json":"https://pith.science/pith/POMUAOZWBOKB7S3RHESYIR2FKU.json","graph_json":"https://pith.science/api/pith-number/POMUAOZWBOKB7S3RHESYIR2FKU/graph.json","events_json":"https://pith.science/api/pith-number/POMUAOZWBOKB7S3RHESYIR2FKU/events.json","paper":"https://pith.science/paper/POMUAOZW"},"agent_actions":{"view_html":"https://pith.science/pith/POMUAOZWBOKB7S3RHESYIR2FKU","download_json":"https://pith.science/pith/POMUAOZWBOKB7S3RHESYIR2FKU.json","view_paper":"https://pith.science/paper/POMUAOZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.06589&json=true","fetch_graph":"https://pith.science/api/pith-number/POMUAOZWBOKB7S3RHESYIR2FKU/graph.json","fetch_events":"https://pith.science/api/pith-number/POMUAOZWBOKB7S3RHESYIR2FKU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POMUAOZWBOKB7S3RHESYIR2FKU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POMUAOZWBOKB7S3RHESYIR2FKU/action/storage_attestation","attest_author":"https://pith.science/pith/POMUAOZWBOKB7S3RHESYIR2FKU/action/author_attestation","sign_citation":"https://pith.science/pith/POMUAOZWBOKB7S3RHESYIR2FKU/action/citation_signature","submit_replication":"https://pith.science/pith/POMUAOZWBOKB7S3RHESYIR2FKU/action/replication_record"}},"created_at":"2026-07-05T07:05:29.788432+00:00","updated_at":"2026-07-05T07:05:29.788432+00:00"}