{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SRBB64H2OODKMXJECIX2FDEBVL","short_pith_number":"pith:SRBB64H2","schema_version":"1.0","canonical_sha256":"94421f70fa7386a65d24122fa28c81aaefb8dacc8b718c52f2f8bd2340b924de","source":{"kind":"arxiv","id":"2404.13344","version":2},"attestation_state":"computed","paper":{"title":"GRANOLA: Adaptive Normalization for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Beatrice Bevilacqua, Carola-Bibiane Sch\\\"onlieb, Haggai Maron, Moshe Eliasof","submitted_at":"2024-04-20T10:44:13Z","abstract_excerpt":"In recent years, significant efforts have been made to refine the design of Graph Neural Network (GNN) layers, aiming to overcome diverse challenges, such as limited expressive power and oversmoothing. Despite their widespread adoption, the incorporation of off-the-shelf normalization layers like BatchNorm or InstanceNorm within a GNN architecture may not effectively capture the unique characteristics of graph-structured data, potentially reducing the expressive power of the overall architecture. Moreover, existing graph-specific normalization layers often struggle to offer substantial and con"},"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":"2404.13344","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-20T10:44:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7865abd484445da24da9b5da5be3d25ffb3c9ab898402c1b62fc4991eb2b4d04","abstract_canon_sha256":"53a16b31541d3801f7b038ea0a4d758d4fccfa2530f6c0696b7028244520ac79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:27.978066Z","signature_b64":"2TALKLzcHJfgbq8zlMuAerqoOF6p9uUHOBis1yUv3zGZwdRsU0yIe8EkzfJuw0GtQF4DYO0VRMsMB2kK78JrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94421f70fa7386a65d24122fa28c81aaefb8dacc8b718c52f2f8bd2340b924de","last_reissued_at":"2026-07-05T09:29:27.977572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:27.977572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRANOLA: Adaptive Normalization for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Beatrice Bevilacqua, Carola-Bibiane Sch\\\"onlieb, Haggai Maron, Moshe Eliasof","submitted_at":"2024-04-20T10:44:13Z","abstract_excerpt":"In recent years, significant efforts have been made to refine the design of Graph Neural Network (GNN) layers, aiming to overcome diverse challenges, such as limited expressive power and oversmoothing. Despite their widespread adoption, the incorporation of off-the-shelf normalization layers like BatchNorm or InstanceNorm within a GNN architecture may not effectively capture the unique characteristics of graph-structured data, potentially reducing the expressive power of the overall architecture. Moreover, existing graph-specific normalization layers often struggle to offer substantial and con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13344","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/2404.13344/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":"2404.13344","created_at":"2026-07-05T09:29:27.977630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13344v2","created_at":"2026-07-05T09:29:27.977630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13344","created_at":"2026-07-05T09:29:27.977630+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRBB64H2OODK","created_at":"2026-07-05T09:29:27.977630+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRBB64H2OODKMXJE","created_at":"2026-07-05T09:29:27.977630+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRBB64H2","created_at":"2026-07-05T09:29:27.977630+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01170","citing_title":"ADMP-GNN: Adaptive Depth Message Passing GNN","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SRBB64H2OODKMXJECIX2FDEBVL","json":"https://pith.science/pith/SRBB64H2OODKMXJECIX2FDEBVL.json","graph_json":"https://pith.science/api/pith-number/SRBB64H2OODKMXJECIX2FDEBVL/graph.json","events_json":"https://pith.science/api/pith-number/SRBB64H2OODKMXJECIX2FDEBVL/events.json","paper":"https://pith.science/paper/SRBB64H2"},"agent_actions":{"view_html":"https://pith.science/pith/SRBB64H2OODKMXJECIX2FDEBVL","download_json":"https://pith.science/pith/SRBB64H2OODKMXJECIX2FDEBVL.json","view_paper":"https://pith.science/paper/SRBB64H2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13344&json=true","fetch_graph":"https://pith.science/api/pith-number/SRBB64H2OODKMXJECIX2FDEBVL/graph.json","fetch_events":"https://pith.science/api/pith-number/SRBB64H2OODKMXJECIX2FDEBVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRBB64H2OODKMXJECIX2FDEBVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRBB64H2OODKMXJECIX2FDEBVL/action/storage_attestation","attest_author":"https://pith.science/pith/SRBB64H2OODKMXJECIX2FDEBVL/action/author_attestation","sign_citation":"https://pith.science/pith/SRBB64H2OODKMXJECIX2FDEBVL/action/citation_signature","submit_replication":"https://pith.science/pith/SRBB64H2OODKMXJECIX2FDEBVL/action/replication_record"}},"created_at":"2026-07-05T09:29:27.977630+00:00","updated_at":"2026-07-05T09:29:27.977630+00:00"}