{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QAVZGJCNQBXJND2UXWXWFQQZ22","short_pith_number":"pith:QAVZGJCN","schema_version":"1.0","canonical_sha256":"802b93244d806e968f54bdaf62c219d69543bb76ac7f1a2bfbc1fe5a78823d68","source":{"kind":"arxiv","id":"2111.12128","version":3},"attestation_state":"computed","paper":{"title":"On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin Paul Chamberlain, Emanuele Rossi, Henry Kenlay, Maria I. Gorinova, Michael Bronstein, Xiaowen Dong","submitted_at":"2021-11-23T19:50:46Z","abstract_excerpt":"While Graph Neural Networks (GNNs) have recently become the de facto standard for modeling relational data, they impose a strong assumption on the availability of the node or edge features of the graph. In many real-world applications, however, features are only partially available; for example, in social networks, age and gender are available only for a small subset of users. We present a general approach for handling missing features in graph machine learning applications that is based on minimization of the Dirichlet energy and leads to a diffusion-type differential equation on the graph. T"},"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":"2111.12128","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-23T19:50:46Z","cross_cats_sorted":[],"title_canon_sha256":"6431fa556368ef8f6d8d02c24964b88405f701a86ca05459e01e5b744c1d55b6","abstract_canon_sha256":"34442e2b008466fc14dc79d935df5d10108c03b9dc5b08d632afbc03e3774f88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:35.003977Z","signature_b64":"4+reMlDOBb7ZNb8fSIGgwoDCIY/PRr9Q3zBhuZzrqJDwznAoTQGxG5DWigcM11HdWOzGamvnrA7KvVRubFszCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"802b93244d806e968f54bdaf62c219d69543bb76ac7f1a2bfbc1fe5a78823d68","last_reissued_at":"2026-07-05T04:25:35.003521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:35.003521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin Paul Chamberlain, Emanuele Rossi, Henry Kenlay, Maria I. Gorinova, Michael Bronstein, Xiaowen Dong","submitted_at":"2021-11-23T19:50:46Z","abstract_excerpt":"While Graph Neural Networks (GNNs) have recently become the de facto standard for modeling relational data, they impose a strong assumption on the availability of the node or edge features of the graph. In many real-world applications, however, features are only partially available; for example, in social networks, age and gender are available only for a small subset of users. We present a general approach for handling missing features in graph machine learning applications that is based on minimization of the Dirichlet energy and leads to a diffusion-type differential equation on the graph. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12128","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/2111.12128/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":"2111.12128","created_at":"2026-07-05T04:25:35.003576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.12128v3","created_at":"2026-07-05T04:25:35.003576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12128","created_at":"2026-07-05T04:25:35.003576+00:00"},{"alias_kind":"pith_short_12","alias_value":"QAVZGJCNQBXJ","created_at":"2026-07-05T04:25:35.003576+00:00"},{"alias_kind":"pith_short_16","alias_value":"QAVZGJCNQBXJND2U","created_at":"2026-07-05T04:25:35.003576+00:00"},{"alias_kind":"pith_short_8","alias_value":"QAVZGJCN","created_at":"2026-07-05T04:25:35.003576+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.02343","citing_title":"Toward General and Robust LLM-enhanced Text-attributed Graph Learning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QAVZGJCNQBXJND2UXWXWFQQZ22","json":"https://pith.science/pith/QAVZGJCNQBXJND2UXWXWFQQZ22.json","graph_json":"https://pith.science/api/pith-number/QAVZGJCNQBXJND2UXWXWFQQZ22/graph.json","events_json":"https://pith.science/api/pith-number/QAVZGJCNQBXJND2UXWXWFQQZ22/events.json","paper":"https://pith.science/paper/QAVZGJCN"},"agent_actions":{"view_html":"https://pith.science/pith/QAVZGJCNQBXJND2UXWXWFQQZ22","download_json":"https://pith.science/pith/QAVZGJCNQBXJND2UXWXWFQQZ22.json","view_paper":"https://pith.science/paper/QAVZGJCN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.12128&json=true","fetch_graph":"https://pith.science/api/pith-number/QAVZGJCNQBXJND2UXWXWFQQZ22/graph.json","fetch_events":"https://pith.science/api/pith-number/QAVZGJCNQBXJND2UXWXWFQQZ22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QAVZGJCNQBXJND2UXWXWFQQZ22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QAVZGJCNQBXJND2UXWXWFQQZ22/action/storage_attestation","attest_author":"https://pith.science/pith/QAVZGJCNQBXJND2UXWXWFQQZ22/action/author_attestation","sign_citation":"https://pith.science/pith/QAVZGJCNQBXJND2UXWXWFQQZ22/action/citation_signature","submit_replication":"https://pith.science/pith/QAVZGJCNQBXJND2UXWXWFQQZ22/action/replication_record"}},"created_at":"2026-07-05T04:25:35.003576+00:00","updated_at":"2026-07-05T04:25:35.003576+00:00"}