{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AYA6PLW4APNNFHGCNTWK3RJP24","short_pith_number":"pith:AYA6PLW4","schema_version":"1.0","canonical_sha256":"0601e7aedc03dad29cc26cecadc52fd7254c1d9b905969916e9711fc0de969a5","source":{"kind":"arxiv","id":"2503.00547","version":1},"attestation_state":"computed","paper":{"title":"Performance Heterogeneity in Graph Neural Networks: Lessons for Architecture Design and Preprocessing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lukas Fesser, Melanie Weber","submitted_at":"2025-03-01T16:18:07Z","abstract_excerpt":"Graph Neural Networks have emerged as the most popular architecture for graph-level learning, including graph classification and regression tasks, which frequently arise in areas such as biochemistry and drug discovery. Achieving good performance in practice requires careful model design. Due to gaps in our understanding of the relationship between model and data characteristics, this often requires manual architecture and hyperparameter tuning. This is particularly pronounced in graph-level tasks, due to much higher variation in the input data than in node-level tasks. To work towards closing"},"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":"2503.00547","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-01T16:18:07Z","cross_cats_sorted":[],"title_canon_sha256":"e4d3120c15f99d09a5a687acd15a60d483bebddbe6b142904b40d59d933221ee","abstract_canon_sha256":"2f1a153755f974dc22b6de6daf3b90e95e544e38b1ba4e24b8da01d3463b8a8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:24.997649Z","signature_b64":"Ng1gj+VF1xE+Mvwj8TO7JW/EAO0IZeWSqf6cCIdS5u5z4t9UBi2o9QHyxsPMy9A8Fd9Fd5rENnV3fmAVVi5oCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0601e7aedc03dad29cc26cecadc52fd7254c1d9b905969916e9711fc0de969a5","last_reissued_at":"2026-07-05T10:22:24.997062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:24.997062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Performance Heterogeneity in Graph Neural Networks: Lessons for Architecture Design and Preprocessing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lukas Fesser, Melanie Weber","submitted_at":"2025-03-01T16:18:07Z","abstract_excerpt":"Graph Neural Networks have emerged as the most popular architecture for graph-level learning, including graph classification and regression tasks, which frequently arise in areas such as biochemistry and drug discovery. Achieving good performance in practice requires careful model design. Due to gaps in our understanding of the relationship between model and data characteristics, this often requires manual architecture and hyperparameter tuning. This is particularly pronounced in graph-level tasks, due to much higher variation in the input data than in node-level tasks. To work towards closing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00547","kind":"arxiv","version":1},"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/2503.00547/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":"2503.00547","created_at":"2026-07-05T10:22:24.997140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00547v1","created_at":"2026-07-05T10:22:24.997140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00547","created_at":"2026-07-05T10:22:24.997140+00:00"},{"alias_kind":"pith_short_12","alias_value":"AYA6PLW4APNN","created_at":"2026-07-05T10:22:24.997140+00:00"},{"alias_kind":"pith_short_16","alias_value":"AYA6PLW4APNNFHGC","created_at":"2026-07-05T10:22:24.997140+00:00"},{"alias_kind":"pith_short_8","alias_value":"AYA6PLW4","created_at":"2026-07-05T10:22:24.997140+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/AYA6PLW4APNNFHGCNTWK3RJP24","json":"https://pith.science/pith/AYA6PLW4APNNFHGCNTWK3RJP24.json","graph_json":"https://pith.science/api/pith-number/AYA6PLW4APNNFHGCNTWK3RJP24/graph.json","events_json":"https://pith.science/api/pith-number/AYA6PLW4APNNFHGCNTWK3RJP24/events.json","paper":"https://pith.science/paper/AYA6PLW4"},"agent_actions":{"view_html":"https://pith.science/pith/AYA6PLW4APNNFHGCNTWK3RJP24","download_json":"https://pith.science/pith/AYA6PLW4APNNFHGCNTWK3RJP24.json","view_paper":"https://pith.science/paper/AYA6PLW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00547&json=true","fetch_graph":"https://pith.science/api/pith-number/AYA6PLW4APNNFHGCNTWK3RJP24/graph.json","fetch_events":"https://pith.science/api/pith-number/AYA6PLW4APNNFHGCNTWK3RJP24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AYA6PLW4APNNFHGCNTWK3RJP24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AYA6PLW4APNNFHGCNTWK3RJP24/action/storage_attestation","attest_author":"https://pith.science/pith/AYA6PLW4APNNFHGCNTWK3RJP24/action/author_attestation","sign_citation":"https://pith.science/pith/AYA6PLW4APNNFHGCNTWK3RJP24/action/citation_signature","submit_replication":"https://pith.science/pith/AYA6PLW4APNNFHGCNTWK3RJP24/action/replication_record"}},"created_at":"2026-07-05T10:22:24.997140+00:00","updated_at":"2026-07-05T10:22:24.997140+00:00"}