{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GSTHIFDAZEO7B6IP5Y3YB5U3PD","short_pith_number":"pith:GSTHIFDA","schema_version":"1.0","canonical_sha256":"34a6741460c91df0f90fee3780f69b78e0f619dc1c301fb3b8da4f6a42d7d9b1","source":{"kind":"arxiv","id":"2211.16494","version":5},"attestation_state":"computed","paper":{"title":"On the Ability of Graph Neural Networks to Model Interactions Between Vertices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Nadav Cohen, Noam Razin, Tom Verbin","submitted_at":"2022-11-29T18:58:07Z","abstract_excerpt":"Graph neural networks (GNNs) are widely used for modeling complex interactions between entities represented as vertices of a graph. Despite recent efforts to theoretically analyze the expressive power of GNNs, a formal characterization of their ability to model interactions is lacking. The current paper aims to address this gap. Formalizing strength of interactions through an established measure known as separation rank, we quantify the ability of certain GNNs to model interaction between a given subset of vertices and its complement, i.e. between the sides of a given partition of input vertic"},"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":"2211.16494","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-29T18:58:07Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"1d6ddba64c344f735aef9afa0cd014d3ea81ec325b0401827c1a71caa02e2753","abstract_canon_sha256":"38204ba99f7b4e8652036fffcafcdba74cc76580aa25b571b0264c8007dd1968"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:57.345723Z","signature_b64":"1rxJXT+zRhggeGi30yXSZqEm+krgv2tl53Nl6Vi2FZKrupxz3ShrhJMFy1a2umsnXvvnngpZBuJ/9jpZKwIbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34a6741460c91df0f90fee3780f69b78e0f619dc1c301fb3b8da4f6a42d7d9b1","last_reissued_at":"2026-07-05T07:03:57.345213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:57.345213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Ability of Graph Neural Networks to Model Interactions Between Vertices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Nadav Cohen, Noam Razin, Tom Verbin","submitted_at":"2022-11-29T18:58:07Z","abstract_excerpt":"Graph neural networks (GNNs) are widely used for modeling complex interactions between entities represented as vertices of a graph. Despite recent efforts to theoretically analyze the expressive power of GNNs, a formal characterization of their ability to model interactions is lacking. The current paper aims to address this gap. Formalizing strength of interactions through an established measure known as separation rank, we quantify the ability of certain GNNs to model interaction between a given subset of vertices and its complement, i.e. between the sides of a given partition of input vertic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.16494","kind":"arxiv","version":5},"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/2211.16494/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":"2211.16494","created_at":"2026-07-05T07:03:57.345283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.16494v5","created_at":"2026-07-05T07:03:57.345283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.16494","created_at":"2026-07-05T07:03:57.345283+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSTHIFDAZEO7","created_at":"2026-07-05T07:03:57.345283+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSTHIFDAZEO7B6IP","created_at":"2026-07-05T07:03:57.345283+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSTHIFDA","created_at":"2026-07-05T07:03:57.345283+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.03634","citing_title":"Explainable Malware Detection through Integrated Graph Reduction and Learning Techniques","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GSTHIFDAZEO7B6IP5Y3YB5U3PD","json":"https://pith.science/pith/GSTHIFDAZEO7B6IP5Y3YB5U3PD.json","graph_json":"https://pith.science/api/pith-number/GSTHIFDAZEO7B6IP5Y3YB5U3PD/graph.json","events_json":"https://pith.science/api/pith-number/GSTHIFDAZEO7B6IP5Y3YB5U3PD/events.json","paper":"https://pith.science/paper/GSTHIFDA"},"agent_actions":{"view_html":"https://pith.science/pith/GSTHIFDAZEO7B6IP5Y3YB5U3PD","download_json":"https://pith.science/pith/GSTHIFDAZEO7B6IP5Y3YB5U3PD.json","view_paper":"https://pith.science/paper/GSTHIFDA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.16494&json=true","fetch_graph":"https://pith.science/api/pith-number/GSTHIFDAZEO7B6IP5Y3YB5U3PD/graph.json","fetch_events":"https://pith.science/api/pith-number/GSTHIFDAZEO7B6IP5Y3YB5U3PD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSTHIFDAZEO7B6IP5Y3YB5U3PD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSTHIFDAZEO7B6IP5Y3YB5U3PD/action/storage_attestation","attest_author":"https://pith.science/pith/GSTHIFDAZEO7B6IP5Y3YB5U3PD/action/author_attestation","sign_citation":"https://pith.science/pith/GSTHIFDAZEO7B6IP5Y3YB5U3PD/action/citation_signature","submit_replication":"https://pith.science/pith/GSTHIFDAZEO7B6IP5Y3YB5U3PD/action/replication_record"}},"created_at":"2026-07-05T07:03:57.345283+00:00","updated_at":"2026-07-05T07:03:57.345283+00:00"}