{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7YBJBALHDOGRKGXTVQ4JUH3ZQJ","short_pith_number":"pith:7YBJBALH","schema_version":"1.0","canonical_sha256":"fe029081671b8d151af3ac389a1f79825aa9929f22667a70b481d399a80ea73d","source":{"kind":"arxiv","id":"2202.00264","version":1},"attestation_state":"computed","paper":{"title":"Graph-based Neural Acceleration for Nonnegative Matrix Factorization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jens Sj\\\"olund, Maria B{\\aa}nkestad","submitted_at":"2022-02-01T07:52:01Z","abstract_excerpt":"We describe a graph-based neural acceleration technique for nonnegative matrix factorization that builds upon a connection between matrices and bipartite graphs that is well-known in certain fields, e.g., sparse linear algebra, but has not yet been exploited to design graph neural networks for matrix computations. We first consider low-rank factorization more broadly and propose a graph representation of the problem suited for graph neural networks. Then, we focus on the task of nonnegative matrix factorization and propose a graph neural network that interleaves bipartite self-attention layers"},"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":"2202.00264","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-01T07:52:01Z","cross_cats_sorted":["cs.NA","math.NA","math.OC","stat.ML"],"title_canon_sha256":"5828c338e32dd292a8a6f49f3bac4af54e508141695b8dfdc3ee215a60b5b31b","abstract_canon_sha256":"c10089c152c83b7456f1baec5367eca4192fcde47175b3677460be6615c9db0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:53:20.252258Z","signature_b64":"qQs+Ckr3N/Jl2WINib3Sk/nrU8kN1lBLVGlV3iI6WSAiuNnkI4zsYWjIWZgzOnRtO/ccTTAbU96bORN8+hFaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe029081671b8d151af3ac389a1f79825aa9929f22667a70b481d399a80ea73d","last_reissued_at":"2026-07-05T03:53:20.251790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:53:20.251790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-based Neural Acceleration for Nonnegative Matrix Factorization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NA","math.NA","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jens Sj\\\"olund, Maria B{\\aa}nkestad","submitted_at":"2022-02-01T07:52:01Z","abstract_excerpt":"We describe a graph-based neural acceleration technique for nonnegative matrix factorization that builds upon a connection between matrices and bipartite graphs that is well-known in certain fields, e.g., sparse linear algebra, but has not yet been exploited to design graph neural networks for matrix computations. We first consider low-rank factorization more broadly and propose a graph representation of the problem suited for graph neural networks. Then, we focus on the task of nonnegative matrix factorization and propose a graph neural network that interleaves bipartite self-attention layers"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00264","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/2202.00264/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":"2202.00264","created_at":"2026-07-05T03:53:20.251851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.00264v1","created_at":"2026-07-05T03:53:20.251851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00264","created_at":"2026-07-05T03:53:20.251851+00:00"},{"alias_kind":"pith_short_12","alias_value":"7YBJBALHDOGR","created_at":"2026-07-05T03:53:20.251851+00:00"},{"alias_kind":"pith_short_16","alias_value":"7YBJBALHDOGRKGXT","created_at":"2026-07-05T03:53:20.251851+00:00"},{"alias_kind":"pith_short_8","alias_value":"7YBJBALH","created_at":"2026-07-05T03:53:20.251851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.13174","citing_title":"Warm-starting active-set solvers using graph neural networks","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7YBJBALHDOGRKGXTVQ4JUH3ZQJ","json":"https://pith.science/pith/7YBJBALHDOGRKGXTVQ4JUH3ZQJ.json","graph_json":"https://pith.science/api/pith-number/7YBJBALHDOGRKGXTVQ4JUH3ZQJ/graph.json","events_json":"https://pith.science/api/pith-number/7YBJBALHDOGRKGXTVQ4JUH3ZQJ/events.json","paper":"https://pith.science/paper/7YBJBALH"},"agent_actions":{"view_html":"https://pith.science/pith/7YBJBALHDOGRKGXTVQ4JUH3ZQJ","download_json":"https://pith.science/pith/7YBJBALHDOGRKGXTVQ4JUH3ZQJ.json","view_paper":"https://pith.science/paper/7YBJBALH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.00264&json=true","fetch_graph":"https://pith.science/api/pith-number/7YBJBALHDOGRKGXTVQ4JUH3ZQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/7YBJBALHDOGRKGXTVQ4JUH3ZQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7YBJBALHDOGRKGXTVQ4JUH3ZQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7YBJBALHDOGRKGXTVQ4JUH3ZQJ/action/storage_attestation","attest_author":"https://pith.science/pith/7YBJBALHDOGRKGXTVQ4JUH3ZQJ/action/author_attestation","sign_citation":"https://pith.science/pith/7YBJBALHDOGRKGXTVQ4JUH3ZQJ/action/citation_signature","submit_replication":"https://pith.science/pith/7YBJBALHDOGRKGXTVQ4JUH3ZQJ/action/replication_record"}},"created_at":"2026-07-05T03:53:20.251851+00:00","updated_at":"2026-07-05T03:53:20.251851+00:00"}