{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:A6VOX6GCJE6BW7QGKMTIHVFOOC","short_pith_number":"pith:A6VOX6GC","schema_version":"1.0","canonical_sha256":"07aaebf8c2493c1b7e06532683d4ae708824f3c995018f26e66f8d46e1923bf7","source":{"kind":"arxiv","id":"1904.09981","version":2},"attestation_state":"computed","paper":{"title":"GraphNAS: Graph Neural Architecture Search with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chuan Zhou, Hong Yang, Peng Zhang, Yang Gao, Yue Hu","submitted_at":"2019-04-22T07:13:10Z","abstract_excerpt":"Graph Neural Networks (GNNs) have been popularly used for analyzing non-Euclidean data such as social network data and biological data. Despite their success, the design of graph neural networks requires a lot of manual work and domain knowledge. In this paper, we propose a Graph Neural Architecture Search method (GraphNAS for short) that enables automatic search of the best graph neural architecture based on reinforcement learning. Specifically, GraphNAS first uses a recurrent network to generate variable-length strings that describe the architectures of graph neural networks, and then trains"},"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":"1904.09981","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-22T07:13:10Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"c20716e9386ef3231ebfe42b2c7a07f74ab34d72caa9fafec766c65a04d529ae","abstract_canon_sha256":"68e2334b042e357c193d3c6779861e3a43498264d30f91998a9835fea44248a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:05.287026Z","signature_b64":"b2eJsTXyhAAwaJYl+PXo7vVwqwKnblwhUnaBvsMFrsUxNT38UZakwyVloTM/XG0Mj7jrDmcnOeyqd1UtWIJmCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07aaebf8c2493c1b7e06532683d4ae708824f3c995018f26e66f8d46e1923bf7","last_reissued_at":"2026-07-05T01:48:05.286668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:05.286668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphNAS: Graph Neural Architecture Search with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chuan Zhou, Hong Yang, Peng Zhang, Yang Gao, Yue Hu","submitted_at":"2019-04-22T07:13:10Z","abstract_excerpt":"Graph Neural Networks (GNNs) have been popularly used for analyzing non-Euclidean data such as social network data and biological data. Despite their success, the design of graph neural networks requires a lot of manual work and domain knowledge. In this paper, we propose a Graph Neural Architecture Search method (GraphNAS for short) that enables automatic search of the best graph neural architecture based on reinforcement learning. Specifically, GraphNAS first uses a recurrent network to generate variable-length strings that describe the architectures of graph neural networks, and then trains"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.09981","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/1904.09981/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":"1904.09981","created_at":"2026-07-05T01:48:05.286725+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.09981v2","created_at":"2026-07-05T01:48:05.286725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.09981","created_at":"2026-07-05T01:48:05.286725+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6VOX6GCJE6B","created_at":"2026-07-05T01:48:05.286725+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6VOX6GCJE6BW7QG","created_at":"2026-07-05T01:48:05.286725+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6VOX6GC","created_at":"2026-07-05T01:48:05.286725+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29582","citing_title":"Bilevel Optimization for Neural Architecture Search","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05258","citing_title":"PARNESS: A Paper Harness for End-to-End Automated Scientific Research with Dynamic Workflows, Full-Text Indexing, and Cross-Run Knowledge Accumulation","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6VOX6GCJE6BW7QGKMTIHVFOOC","json":"https://pith.science/pith/A6VOX6GCJE6BW7QGKMTIHVFOOC.json","graph_json":"https://pith.science/api/pith-number/A6VOX6GCJE6BW7QGKMTIHVFOOC/graph.json","events_json":"https://pith.science/api/pith-number/A6VOX6GCJE6BW7QGKMTIHVFOOC/events.json","paper":"https://pith.science/paper/A6VOX6GC"},"agent_actions":{"view_html":"https://pith.science/pith/A6VOX6GCJE6BW7QGKMTIHVFOOC","download_json":"https://pith.science/pith/A6VOX6GCJE6BW7QGKMTIHVFOOC.json","view_paper":"https://pith.science/paper/A6VOX6GC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.09981&json=true","fetch_graph":"https://pith.science/api/pith-number/A6VOX6GCJE6BW7QGKMTIHVFOOC/graph.json","fetch_events":"https://pith.science/api/pith-number/A6VOX6GCJE6BW7QGKMTIHVFOOC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6VOX6GCJE6BW7QGKMTIHVFOOC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6VOX6GCJE6BW7QGKMTIHVFOOC/action/storage_attestation","attest_author":"https://pith.science/pith/A6VOX6GCJE6BW7QGKMTIHVFOOC/action/author_attestation","sign_citation":"https://pith.science/pith/A6VOX6GCJE6BW7QGKMTIHVFOOC/action/citation_signature","submit_replication":"https://pith.science/pith/A6VOX6GCJE6BW7QGKMTIHVFOOC/action/replication_record"}},"created_at":"2026-07-05T01:48:05.286725+00:00","updated_at":"2026-07-05T01:48:05.286725+00:00"}