{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OUIV3RAPFJ37CEWWWO45S6I4GO","short_pith_number":"pith:OUIV3RAP","schema_version":"1.0","canonical_sha256":"75115dc40f2a77f112d6b3b9d9791c3398e1053e6ab72168c2eb737014f32ea8","source":{"kind":"arxiv","id":"1910.12091","version":2},"attestation_state":"computed","paper":{"title":"Understanding Isomorphism Bias in Graph Data Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Evgeny Burnaev, Sergei Ivanov, Sergei Sviridov","submitted_at":"2019-10-26T15:52:42Z","abstract_excerpt":"In recent years there has been a rapid increase in classification methods on graph structured data. Both in graph kernels and graph neural networks, one of the implicit assumptions of successful state-of-the-art models was that incorporating graph isomorphism features into the architecture leads to better empirical performance. However, as we discover in this work, commonly used data sets for graph classification have repeating instances which cause the problem of isomorphism bias, i.e. artificially increasing the accuracy of the models by memorizing target information from the training set. T"},"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":"1910.12091","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-26T15:52:42Z","cross_cats_sorted":["cs.SI","stat.ML"],"title_canon_sha256":"5a9ba8540ec41cca025df49bbd23cbd0a7d9fc2748bc2c53eda219ff9607a873","abstract_canon_sha256":"2b9492eac04b4db48b2191c242fcf54682026ece433257d87527b551b8b50c72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:06.747974Z","signature_b64":"ZNmMUgRtw9Ak8C1e5l5eVd+/OG1mT9ZX66xcCEfO4NL3vOwXU/BYgyHbFgpDBdF9r/0S7B23A2hV24v5gLmNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75115dc40f2a77f112d6b3b9d9791c3398e1053e6ab72168c2eb737014f32ea8","last_reissued_at":"2026-07-05T00:16:06.747546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:06.747546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Isomorphism Bias in Graph Data Sets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Evgeny Burnaev, Sergei Ivanov, Sergei Sviridov","submitted_at":"2019-10-26T15:52:42Z","abstract_excerpt":"In recent years there has been a rapid increase in classification methods on graph structured data. Both in graph kernels and graph neural networks, one of the implicit assumptions of successful state-of-the-art models was that incorporating graph isomorphism features into the architecture leads to better empirical performance. However, as we discover in this work, commonly used data sets for graph classification have repeating instances which cause the problem of isomorphism bias, i.e. artificially increasing the accuracy of the models by memorizing target information from the training set. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.12091","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/1910.12091/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":"1910.12091","created_at":"2026-07-05T00:16:06.747600+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.12091v2","created_at":"2026-07-05T00:16:06.747600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.12091","created_at":"2026-07-05T00:16:06.747600+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUIV3RAPFJ37","created_at":"2026-07-05T00:16:06.747600+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUIV3RAPFJ37CEWW","created_at":"2026-07-05T00:16:06.747600+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUIV3RAP","created_at":"2026-07-05T00:16:06.747600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.15474","citing_title":"BadImplant: Injection-based Multi-Targeted Graph Backdoor Attack","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OUIV3RAPFJ37CEWWWO45S6I4GO","json":"https://pith.science/pith/OUIV3RAPFJ37CEWWWO45S6I4GO.json","graph_json":"https://pith.science/api/pith-number/OUIV3RAPFJ37CEWWWO45S6I4GO/graph.json","events_json":"https://pith.science/api/pith-number/OUIV3RAPFJ37CEWWWO45S6I4GO/events.json","paper":"https://pith.science/paper/OUIV3RAP"},"agent_actions":{"view_html":"https://pith.science/pith/OUIV3RAPFJ37CEWWWO45S6I4GO","download_json":"https://pith.science/pith/OUIV3RAPFJ37CEWWWO45S6I4GO.json","view_paper":"https://pith.science/paper/OUIV3RAP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.12091&json=true","fetch_graph":"https://pith.science/api/pith-number/OUIV3RAPFJ37CEWWWO45S6I4GO/graph.json","fetch_events":"https://pith.science/api/pith-number/OUIV3RAPFJ37CEWWWO45S6I4GO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUIV3RAPFJ37CEWWWO45S6I4GO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUIV3RAPFJ37CEWWWO45S6I4GO/action/storage_attestation","attest_author":"https://pith.science/pith/OUIV3RAPFJ37CEWWWO45S6I4GO/action/author_attestation","sign_citation":"https://pith.science/pith/OUIV3RAPFJ37CEWWWO45S6I4GO/action/citation_signature","submit_replication":"https://pith.science/pith/OUIV3RAPFJ37CEWWWO45S6I4GO/action/replication_record"}},"created_at":"2026-07-05T00:16:06.747600+00:00","updated_at":"2026-07-05T00:16:06.747600+00:00"}