{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UBAQXHIV2AZYY6ZVQQCWLLJPB4","short_pith_number":"pith:UBAQXHIV","schema_version":"1.0","canonical_sha256":"a0410b9d15d0338c7b35840565ad2f0f221f9347adccdd094e6b8c0af28fc6b9","source":{"kind":"arxiv","id":"2003.09676","version":1},"attestation_state":"computed","paper":{"title":"Probabilistic Dual Network Architecture Search on Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Duo Wang, Mateja Jamnik, Pietro Lio, Robert Mullins, Xitong Gao, Yiren Zhao","submitted_at":"2020-03-21T15:06:47Z","abstract_excerpt":"We present the first differentiable Network Architecture Search (NAS) for Graph Neural Networks (GNNs). GNNs show promising performance on a wide range of tasks, but require a large amount of architecture engineering. First, graphs are inherently a non-Euclidean and sophisticated data structure, leading to poor adaptivity of GNN architectures across different datasets. Second, a typical graph block contains numerous different components, such as aggregation and attention, generating a large combinatorial search space. To counter these problems, we propose a Probabilistic Dual Network Architect"},"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":"2003.09676","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-21T15:06:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d4ce1e481a442b99615407bf98a49943fb51e718031826c65676e4873f3ba0d1","abstract_canon_sha256":"b5d874f1e4b0230bc65b25640ed5a2fdc104356f6c48e57f3df974b6487be1b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:46.034681Z","signature_b64":"bSWfUBBa1sq9jx4ZJdQNFsixO38hEfQVWqrxLkKIRNmp+dOHPnsJZCJ6WSmt5zjsvdVb6zF81y/uZHHy9jedDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0410b9d15d0338c7b35840565ad2f0f221f9347adccdd094e6b8c0af28fc6b9","last_reissued_at":"2026-07-05T00:49:46.034285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:46.034285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Dual Network Architecture Search on Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Duo Wang, Mateja Jamnik, Pietro Lio, Robert Mullins, Xitong Gao, Yiren Zhao","submitted_at":"2020-03-21T15:06:47Z","abstract_excerpt":"We present the first differentiable Network Architecture Search (NAS) for Graph Neural Networks (GNNs). GNNs show promising performance on a wide range of tasks, but require a large amount of architecture engineering. First, graphs are inherently a non-Euclidean and sophisticated data structure, leading to poor adaptivity of GNN architectures across different datasets. Second, a typical graph block contains numerous different components, such as aggregation and attention, generating a large combinatorial search space. To counter these problems, we propose a Probabilistic Dual Network Architect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.09676","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/2003.09676/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":"2003.09676","created_at":"2026-07-05T00:49:46.034355+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.09676v1","created_at":"2026-07-05T00:49:46.034355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.09676","created_at":"2026-07-05T00:49:46.034355+00:00"},{"alias_kind":"pith_short_12","alias_value":"UBAQXHIV2AZY","created_at":"2026-07-05T00:49:46.034355+00:00"},{"alias_kind":"pith_short_16","alias_value":"UBAQXHIV2AZYY6ZV","created_at":"2026-07-05T00:49:46.034355+00:00"},{"alias_kind":"pith_short_8","alias_value":"UBAQXHIV","created_at":"2026-07-05T00:49:46.034355+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.17339","citing_title":"Knowledge-aware Evolutionary Graph Neural Architecture Search","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UBAQXHIV2AZYY6ZVQQCWLLJPB4","json":"https://pith.science/pith/UBAQXHIV2AZYY6ZVQQCWLLJPB4.json","graph_json":"https://pith.science/api/pith-number/UBAQXHIV2AZYY6ZVQQCWLLJPB4/graph.json","events_json":"https://pith.science/api/pith-number/UBAQXHIV2AZYY6ZVQQCWLLJPB4/events.json","paper":"https://pith.science/paper/UBAQXHIV"},"agent_actions":{"view_html":"https://pith.science/pith/UBAQXHIV2AZYY6ZVQQCWLLJPB4","download_json":"https://pith.science/pith/UBAQXHIV2AZYY6ZVQQCWLLJPB4.json","view_paper":"https://pith.science/paper/UBAQXHIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.09676&json=true","fetch_graph":"https://pith.science/api/pith-number/UBAQXHIV2AZYY6ZVQQCWLLJPB4/graph.json","fetch_events":"https://pith.science/api/pith-number/UBAQXHIV2AZYY6ZVQQCWLLJPB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UBAQXHIV2AZYY6ZVQQCWLLJPB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UBAQXHIV2AZYY6ZVQQCWLLJPB4/action/storage_attestation","attest_author":"https://pith.science/pith/UBAQXHIV2AZYY6ZVQQCWLLJPB4/action/author_attestation","sign_citation":"https://pith.science/pith/UBAQXHIV2AZYY6ZVQQCWLLJPB4/action/citation_signature","submit_replication":"https://pith.science/pith/UBAQXHIV2AZYY6ZVQQCWLLJPB4/action/replication_record"}},"created_at":"2026-07-05T00:49:46.034355+00:00","updated_at":"2026-07-05T00:49:46.034355+00:00"}