{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BYO4GEC2W6SBEBWADWEMRM6CUP","short_pith_number":"pith:BYO4GEC2","schema_version":"1.0","canonical_sha256":"0e1dc3105ab7a41206c01d88c8b3c2a3eb636b451d1b93253424333135d6a1d3","source":{"kind":"arxiv","id":"2106.04319","version":1},"attestation_state":"computed","paper":{"title":"Breaking the Limits of Message Passing Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benoit Ga\\\"uz\\`ere, Muhammet Balcilar, Pascal Vasseur, Paul Honeine, Pierre H\\'eroux, S\\'ebastien Adam","submitted_at":"2021-06-08T13:26:56Z","abstract_excerpt":"Since the Message Passing (Graph) Neural Networks (MPNNs) have a linear complexity with respect to the number of nodes when applied to sparse graphs, they have been widely implemented and still raise a lot of interest even though their theoretical expressive power is limited to the first order Weisfeiler-Lehman test (1-WL). In this paper, we show that if the graph convolution supports are designed in spectral-domain by a non-linear custom function of eigenvalues and masked with an arbitrary large receptive field, the MPNN is theoretically more powerful than the 1-WL test and experimentally as "},"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":"2106.04319","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-08T13:26:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a1846d4550e64f1b684b49d918bdcba58d51d74191eb2b7053e7ae8c3567b6a6","abstract_canon_sha256":"90105cad55c89865b6dfc3ec58992ce0f112481a773a603e718d3f46506df6f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:38.580855Z","signature_b64":"gvvfsZjuiQCa3Sgdyrf8/Ex0uv5T27U0oP4vX7j+vFvJQIax15hXu2BSn1kGdbr/I4YuHnQYMGc1LOPCcGWwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e1dc3105ab7a41206c01d88c8b3c2a3eb636b451d1b93253424333135d6a1d3","last_reissued_at":"2026-07-05T02:48:38.580368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:38.580368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Breaking the Limits of Message Passing Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benoit Ga\\\"uz\\`ere, Muhammet Balcilar, Pascal Vasseur, Paul Honeine, Pierre H\\'eroux, S\\'ebastien Adam","submitted_at":"2021-06-08T13:26:56Z","abstract_excerpt":"Since the Message Passing (Graph) Neural Networks (MPNNs) have a linear complexity with respect to the number of nodes when applied to sparse graphs, they have been widely implemented and still raise a lot of interest even though their theoretical expressive power is limited to the first order Weisfeiler-Lehman test (1-WL). In this paper, we show that if the graph convolution supports are designed in spectral-domain by a non-linear custom function of eigenvalues and masked with an arbitrary large receptive field, the MPNN is theoretically more powerful than the 1-WL test and experimentally as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04319","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/2106.04319/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":"2106.04319","created_at":"2026-07-05T02:48:38.580428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.04319v1","created_at":"2026-07-05T02:48:38.580428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04319","created_at":"2026-07-05T02:48:38.580428+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYO4GEC2W6SB","created_at":"2026-07-05T02:48:38.580428+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYO4GEC2W6SBEBWA","created_at":"2026-07-05T02:48:38.580428+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYO4GEC2","created_at":"2026-07-05T02:48:38.580428+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07327","citing_title":"Six Open Questions in Machine-Learned Interatomic Potential Foundation Models","ref_index":109,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BYO4GEC2W6SBEBWADWEMRM6CUP","json":"https://pith.science/pith/BYO4GEC2W6SBEBWADWEMRM6CUP.json","graph_json":"https://pith.science/api/pith-number/BYO4GEC2W6SBEBWADWEMRM6CUP/graph.json","events_json":"https://pith.science/api/pith-number/BYO4GEC2W6SBEBWADWEMRM6CUP/events.json","paper":"https://pith.science/paper/BYO4GEC2"},"agent_actions":{"view_html":"https://pith.science/pith/BYO4GEC2W6SBEBWADWEMRM6CUP","download_json":"https://pith.science/pith/BYO4GEC2W6SBEBWADWEMRM6CUP.json","view_paper":"https://pith.science/paper/BYO4GEC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.04319&json=true","fetch_graph":"https://pith.science/api/pith-number/BYO4GEC2W6SBEBWADWEMRM6CUP/graph.json","fetch_events":"https://pith.science/api/pith-number/BYO4GEC2W6SBEBWADWEMRM6CUP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYO4GEC2W6SBEBWADWEMRM6CUP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYO4GEC2W6SBEBWADWEMRM6CUP/action/storage_attestation","attest_author":"https://pith.science/pith/BYO4GEC2W6SBEBWADWEMRM6CUP/action/author_attestation","sign_citation":"https://pith.science/pith/BYO4GEC2W6SBEBWADWEMRM6CUP/action/citation_signature","submit_replication":"https://pith.science/pith/BYO4GEC2W6SBEBWADWEMRM6CUP/action/replication_record"}},"created_at":"2026-07-05T02:48:38.580428+00:00","updated_at":"2026-07-05T02:48:38.580428+00:00"}