{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7PU56322TROG7NMWKTKLMRQBNP","short_pith_number":"pith:7PU56322","schema_version":"1.0","canonical_sha256":"fbe9df6f5a9c5c6fb59654d4b646016bdc6ab68dbf3eab2dcf2f99531e15de27","source":{"kind":"arxiv","id":"2006.07556","version":2},"attestation_state":"computed","paper":{"title":"Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Binxin Ru, Michael Osborne, Xiaowen Dong, Xingchen Wan","submitted_at":"2020-06-13T04:10:34Z","abstract_excerpt":"Current neural architecture search (NAS) strategies focus only on finding a single, good, architecture. They offer little insight into why a specific network is performing well, or how we should modify the architecture if we want further improvements. We propose a Bayesian optimisation (BO) approach for NAS that combines the Weisfeiler-Lehman graph kernel with a Gaussian process surrogate. Our method optimises the architecture in a highly data-efficient manner: it is capable of capturing the topological structures of the architectures and is scalable to large graphs, thus making the high-dimen"},"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":"2006.07556","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-13T04:10:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6075815613ed1d5fc0e27cb263c2a7f41b1b451d802820723bf2c18fc4e797e5","abstract_canon_sha256":"83792dea80d33776503827f4e51a0d8736e2f751d805ec8a7e8f8f29d3652e8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:16:26.586432Z","signature_b64":"isD0vNw/BOI3psC7+ztQtmNzOYXZ30NTzNmXn8sRIZ044fe5p8xqLVdU/M7Xv8febc5YUefdojtjGwjaIpXqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbe9df6f5a9c5c6fb59654d4b646016bdc6ab68dbf3eab2dcf2f99531e15de27","last_reissued_at":"2026-07-05T02:16:26.586003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:16:26.586003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Binxin Ru, Michael Osborne, Xiaowen Dong, Xingchen Wan","submitted_at":"2020-06-13T04:10:34Z","abstract_excerpt":"Current neural architecture search (NAS) strategies focus only on finding a single, good, architecture. They offer little insight into why a specific network is performing well, or how we should modify the architecture if we want further improvements. We propose a Bayesian optimisation (BO) approach for NAS that combines the Weisfeiler-Lehman graph kernel with a Gaussian process surrogate. Our method optimises the architecture in a highly data-efficient manner: it is capable of capturing the topological structures of the architectures and is scalable to large graphs, thus making the high-dimen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07556","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/2006.07556/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":"2006.07556","created_at":"2026-07-05T02:16:26.586059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07556v2","created_at":"2026-07-05T02:16:26.586059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07556","created_at":"2026-07-05T02:16:26.586059+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PU56322TROG","created_at":"2026-07-05T02:16:26.586059+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PU56322TROG7NMW","created_at":"2026-07-05T02:16:26.586059+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PU56322","created_at":"2026-07-05T02:16:26.586059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.20307","citing_title":"FigBO: A Generalized Acquisition Function Framework with Look-Ahead Capability for Bayesian Optimization","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PU56322TROG7NMWKTKLMRQBNP","json":"https://pith.science/pith/7PU56322TROG7NMWKTKLMRQBNP.json","graph_json":"https://pith.science/api/pith-number/7PU56322TROG7NMWKTKLMRQBNP/graph.json","events_json":"https://pith.science/api/pith-number/7PU56322TROG7NMWKTKLMRQBNP/events.json","paper":"https://pith.science/paper/7PU56322"},"agent_actions":{"view_html":"https://pith.science/pith/7PU56322TROG7NMWKTKLMRQBNP","download_json":"https://pith.science/pith/7PU56322TROG7NMWKTKLMRQBNP.json","view_paper":"https://pith.science/paper/7PU56322","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07556&json=true","fetch_graph":"https://pith.science/api/pith-number/7PU56322TROG7NMWKTKLMRQBNP/graph.json","fetch_events":"https://pith.science/api/pith-number/7PU56322TROG7NMWKTKLMRQBNP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PU56322TROG7NMWKTKLMRQBNP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PU56322TROG7NMWKTKLMRQBNP/action/storage_attestation","attest_author":"https://pith.science/pith/7PU56322TROG7NMWKTKLMRQBNP/action/author_attestation","sign_citation":"https://pith.science/pith/7PU56322TROG7NMWKTKLMRQBNP/action/citation_signature","submit_replication":"https://pith.science/pith/7PU56322TROG7NMWKTKLMRQBNP/action/replication_record"}},"created_at":"2026-07-05T02:16:26.586059+00:00","updated_at":"2026-07-05T02:16:26.586059+00:00"}