{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MHSNO5WG57OYPLD6NZSQMUNGHA","short_pith_number":"pith:MHSNO5WG","schema_version":"1.0","canonical_sha256":"61e4d776c6efdd87ac7e6e650651a6382be42d7e4211b8772952f5f02b7a2ae2","source":{"kind":"arxiv","id":"2305.14065","version":3},"attestation_state":"computed","paper":{"title":"Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bei Yu, Haiqin Yang, Jiaqi Sun, Lin Zhang, Peng Xu, Xuanzhou Liu, Yue Zhao","submitted_at":"2023-05-23T13:44:04Z","abstract_excerpt":"Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures. However, these methods inherit issues from the conventional NAS methods, such as high computational cost and optimization difficulty. More importantly, previous NAS methods have ignored the uniqueness of GNNs, where GNNs possess expressive power without training. With the randomly-initialized weights, we can then seek the optimal architecture parameters via the sparse coding objective and derive a novel NAS-GNNs method, namely neural"},"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":"2305.14065","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-23T13:44:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"47c8cd30a54f86f0ca6b91dc402861f126ffb87f7a2cce120644edcc9c0545f1","abstract_canon_sha256":"268634e7d96eb609ec4aee2432f1d68e25bc13edccb50a37213e2851e619be91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:17.333935Z","signature_b64":"gOnXrZbTPZpptl3m6dWOn4zsgZCY0pBzrr0zHyQkfGyq7SWYJv397J2dCH+IIj0xfHAySsQDkTqQ2rTqjWpSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61e4d776c6efdd87ac7e6e650651a6382be42d7e4211b8772952f5f02b7a2ae2","last_reissued_at":"2026-07-05T06:21:17.333410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:17.333410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bei Yu, Haiqin Yang, Jiaqi Sun, Lin Zhang, Peng Xu, Xuanzhou Liu, Yue Zhao","submitted_at":"2023-05-23T13:44:04Z","abstract_excerpt":"Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures. However, these methods inherit issues from the conventional NAS methods, such as high computational cost and optimization difficulty. More importantly, previous NAS methods have ignored the uniqueness of GNNs, where GNNs possess expressive power without training. With the randomly-initialized weights, we can then seek the optimal architecture parameters via the sparse coding objective and derive a novel NAS-GNNs method, namely neural"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14065","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/2305.14065/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":"2305.14065","created_at":"2026-07-05T06:21:17.333477+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14065v3","created_at":"2026-07-05T06:21:17.333477+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14065","created_at":"2026-07-05T06:21:17.333477+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHSNO5WG57OY","created_at":"2026-07-05T06:21:17.333477+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHSNO5WG57OYPLD6","created_at":"2026-07-05T06:21:17.333477+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHSNO5WG","created_at":"2026-07-05T06:21:17.333477+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/MHSNO5WG57OYPLD6NZSQMUNGHA","json":"https://pith.science/pith/MHSNO5WG57OYPLD6NZSQMUNGHA.json","graph_json":"https://pith.science/api/pith-number/MHSNO5WG57OYPLD6NZSQMUNGHA/graph.json","events_json":"https://pith.science/api/pith-number/MHSNO5WG57OYPLD6NZSQMUNGHA/events.json","paper":"https://pith.science/paper/MHSNO5WG"},"agent_actions":{"view_html":"https://pith.science/pith/MHSNO5WG57OYPLD6NZSQMUNGHA","download_json":"https://pith.science/pith/MHSNO5WG57OYPLD6NZSQMUNGHA.json","view_paper":"https://pith.science/paper/MHSNO5WG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14065&json=true","fetch_graph":"https://pith.science/api/pith-number/MHSNO5WG57OYPLD6NZSQMUNGHA/graph.json","fetch_events":"https://pith.science/api/pith-number/MHSNO5WG57OYPLD6NZSQMUNGHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHSNO5WG57OYPLD6NZSQMUNGHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHSNO5WG57OYPLD6NZSQMUNGHA/action/storage_attestation","attest_author":"https://pith.science/pith/MHSNO5WG57OYPLD6NZSQMUNGHA/action/author_attestation","sign_citation":"https://pith.science/pith/MHSNO5WG57OYPLD6NZSQMUNGHA/action/citation_signature","submit_replication":"https://pith.science/pith/MHSNO5WG57OYPLD6NZSQMUNGHA/action/replication_record"}},"created_at":"2026-07-05T06:21:17.333477+00:00","updated_at":"2026-07-05T06:21:17.333477+00:00"}