{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UVH2DQX5N2HWS5TTYVUFSIM7SK","short_pith_number":"pith:UVH2DQX5","schema_version":"1.0","canonical_sha256":"a54fa1c2fd6e8f697673c56859219f92992879062607d56a9a30a3e8b59826b2","source":{"kind":"arxiv","id":"1905.04579","version":3},"attestation_state":"computed","paper":{"title":"Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Song Bian, Ting Chen, Yizhou Sun","submitted_at":"2019-05-11T19:47:19Z","abstract_excerpt":"Graph Neural Nets (GNNs) have received increasing attentions, partially due to their superior performance in many node and graph classification tasks. However, there is a lack of understanding on what they are learning and how sophisticated the learned graph functions are. In this work, we propose a dissection of GNNs on graph classification into two parts: 1) the graph filtering, where graph-based neighbor aggregations are performed, and 2) the set function, where a set of hidden node features are composed for prediction. To study the importance of both parts, we propose to linearize them sep"},"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":"1905.04579","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-11T19:47:19Z","cross_cats_sorted":["cs.SI","stat.ML"],"title_canon_sha256":"8d729d7264f152f7926458d9f9fdc9cdafa26cb0b45e539b15b147f0136f1f8e","abstract_canon_sha256":"2aae453ebc93511bceb4879790aa393ac6a1010ea3ee2582c03b9199c844d9a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:08:59.431455Z","signature_b64":"6jMJHbBmEA/nQDi5RSbaOrpgKkL5cp4L765xFSp6Rdn8/b7OYxg83UGPE1CnPqn+SRHFUY+j659Xd9j1LmmnCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a54fa1c2fd6e8f697673c56859219f92992879062607d56a9a30a3e8b59826b2","last_reissued_at":"2026-07-05T01:08:59.431018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:08:59.431018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Song Bian, Ting Chen, Yizhou Sun","submitted_at":"2019-05-11T19:47:19Z","abstract_excerpt":"Graph Neural Nets (GNNs) have received increasing attentions, partially due to their superior performance in many node and graph classification tasks. However, there is a lack of understanding on what they are learning and how sophisticated the learned graph functions are. In this work, we propose a dissection of GNNs on graph classification into two parts: 1) the graph filtering, where graph-based neighbor aggregations are performed, and 2) the set function, where a set of hidden node features are composed for prediction. To study the importance of both parts, we propose to linearize them sep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04579","kind":"arxiv","version":3},"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/1905.04579/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":"1905.04579","created_at":"2026-07-05T01:08:59.431071+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.04579v3","created_at":"2026-07-05T01:08:59.431071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04579","created_at":"2026-07-05T01:08:59.431071+00:00"},{"alias_kind":"pith_short_12","alias_value":"UVH2DQX5N2HW","created_at":"2026-07-05T01:08:59.431071+00:00"},{"alias_kind":"pith_short_16","alias_value":"UVH2DQX5N2HWS5TT","created_at":"2026-07-05T01:08:59.431071+00:00"},{"alias_kind":"pith_short_8","alias_value":"UVH2DQX5","created_at":"2026-07-05T01:08:59.431071+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17854","citing_title":"Learning over Positive and Negative Edges with Contrastive Message Passing","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2507.19205","citing_title":"Physics-Informed Graph Neural Networks for Transverse Momentum Estimation in CMS Trigger Systems","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UVH2DQX5N2HWS5TTYVUFSIM7SK","json":"https://pith.science/pith/UVH2DQX5N2HWS5TTYVUFSIM7SK.json","graph_json":"https://pith.science/api/pith-number/UVH2DQX5N2HWS5TTYVUFSIM7SK/graph.json","events_json":"https://pith.science/api/pith-number/UVH2DQX5N2HWS5TTYVUFSIM7SK/events.json","paper":"https://pith.science/paper/UVH2DQX5"},"agent_actions":{"view_html":"https://pith.science/pith/UVH2DQX5N2HWS5TTYVUFSIM7SK","download_json":"https://pith.science/pith/UVH2DQX5N2HWS5TTYVUFSIM7SK.json","view_paper":"https://pith.science/paper/UVH2DQX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.04579&json=true","fetch_graph":"https://pith.science/api/pith-number/UVH2DQX5N2HWS5TTYVUFSIM7SK/graph.json","fetch_events":"https://pith.science/api/pith-number/UVH2DQX5N2HWS5TTYVUFSIM7SK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UVH2DQX5N2HWS5TTYVUFSIM7SK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UVH2DQX5N2HWS5TTYVUFSIM7SK/action/storage_attestation","attest_author":"https://pith.science/pith/UVH2DQX5N2HWS5TTYVUFSIM7SK/action/author_attestation","sign_citation":"https://pith.science/pith/UVH2DQX5N2HWS5TTYVUFSIM7SK/action/citation_signature","submit_replication":"https://pith.science/pith/UVH2DQX5N2HWS5TTYVUFSIM7SK/action/replication_record"}},"created_at":"2026-07-05T01:08:59.431071+00:00","updated_at":"2026-07-05T01:08:59.431071+00:00"}