{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3LGHK3WKDREC3QRZGYEUAYISON","short_pith_number":"pith:3LGHK3WK","schema_version":"1.0","canonical_sha256":"dacc756eca1c482dc2393609406112737e5cd3e208a3519fc17d28c7644ece40","source":{"kind":"arxiv","id":"2112.03499","version":1},"attestation_state":"computed","paper":{"title":"A Piece-wise Polynomial Filtering Approach for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arun Iyer, Chanakya Ekbote, Manan Sharma, Rahul Ragesh, Sundararajan Sellamanickam, Vijay Lingam","submitted_at":"2021-12-07T05:16:53Z","abstract_excerpt":"Graph Neural Networks (GNNs) exploit signals from node features and the input graph topology to improve node classification task performance. However, these models tend to perform poorly on heterophilic graphs, where connected nodes have different labels. Recently proposed GNNs work across graphs having varying levels of homophily. Among these, models relying on polynomial graph filters have shown promise. We observe that solutions to these polynomial graph filter models are also solutions to an overdetermined system of equations. It suggests that in some instances, the model needs to learn a "},"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":"2112.03499","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T05:16:53Z","cross_cats_sorted":[],"title_canon_sha256":"f7e7d3b1d4bc8ecc86041cabee1df475b84310cfaa957afb76e4e3f219db38ec","abstract_canon_sha256":"98e8c454b4577f63f023549c66dd42ce9669c6dc014cdae07b1aea9772029bd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:46.197525Z","signature_b64":"ZrA4iEQlsnDQv2GwanwFECc2zCUs96CuOMS4do4siHHXbwwE0iZh5Eqs8jPGvYy6P74OQLIU2aOMkLLUDqHBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dacc756eca1c482dc2393609406112737e5cd3e208a3519fc17d28c7644ece40","last_reissued_at":"2026-07-05T03:38:46.197052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:46.197052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Piece-wise Polynomial Filtering Approach for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arun Iyer, Chanakya Ekbote, Manan Sharma, Rahul Ragesh, Sundararajan Sellamanickam, Vijay Lingam","submitted_at":"2021-12-07T05:16:53Z","abstract_excerpt":"Graph Neural Networks (GNNs) exploit signals from node features and the input graph topology to improve node classification task performance. However, these models tend to perform poorly on heterophilic graphs, where connected nodes have different labels. Recently proposed GNNs work across graphs having varying levels of homophily. Among these, models relying on polynomial graph filters have shown promise. We observe that solutions to these polynomial graph filter models are also solutions to an overdetermined system of equations. It suggests that in some instances, the model needs to learn a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03499","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/2112.03499/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":"2112.03499","created_at":"2026-07-05T03:38:46.197105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.03499v1","created_at":"2026-07-05T03:38:46.197105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03499","created_at":"2026-07-05T03:38:46.197105+00:00"},{"alias_kind":"pith_short_12","alias_value":"3LGHK3WKDREC","created_at":"2026-07-05T03:38:46.197105+00:00"},{"alias_kind":"pith_short_16","alias_value":"3LGHK3WKDREC3QRZ","created_at":"2026-07-05T03:38:46.197105+00:00"},{"alias_kind":"pith_short_8","alias_value":"3LGHK3WK","created_at":"2026-07-05T03:38:46.197105+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/3LGHK3WKDREC3QRZGYEUAYISON","json":"https://pith.science/pith/3LGHK3WKDREC3QRZGYEUAYISON.json","graph_json":"https://pith.science/api/pith-number/3LGHK3WKDREC3QRZGYEUAYISON/graph.json","events_json":"https://pith.science/api/pith-number/3LGHK3WKDREC3QRZGYEUAYISON/events.json","paper":"https://pith.science/paper/3LGHK3WK"},"agent_actions":{"view_html":"https://pith.science/pith/3LGHK3WKDREC3QRZGYEUAYISON","download_json":"https://pith.science/pith/3LGHK3WKDREC3QRZGYEUAYISON.json","view_paper":"https://pith.science/paper/3LGHK3WK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.03499&json=true","fetch_graph":"https://pith.science/api/pith-number/3LGHK3WKDREC3QRZGYEUAYISON/graph.json","fetch_events":"https://pith.science/api/pith-number/3LGHK3WKDREC3QRZGYEUAYISON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3LGHK3WKDREC3QRZGYEUAYISON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3LGHK3WKDREC3QRZGYEUAYISON/action/storage_attestation","attest_author":"https://pith.science/pith/3LGHK3WKDREC3QRZGYEUAYISON/action/author_attestation","sign_citation":"https://pith.science/pith/3LGHK3WKDREC3QRZGYEUAYISON/action/citation_signature","submit_replication":"https://pith.science/pith/3LGHK3WKDREC3QRZGYEUAYISON/action/replication_record"}},"created_at":"2026-07-05T03:38:46.197105+00:00","updated_at":"2026-07-05T03:38:46.197105+00:00"}