{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IMWZHIVYIDCIW5LI5YDCJ7OENU","short_pith_number":"pith:IMWZHIVY","schema_version":"1.0","canonical_sha256":"432d93a2b840c48b7568ee0624fdc46d04882a7ef1df1671deef614c2bab8d82","source":{"kind":"arxiv","id":"2506.02623","version":1},"attestation_state":"computed","paper":{"title":"SiamNAS: Siamese Surrogate Model for Dominance Relation Prediction in Multi-objective Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Ferrante Neri, Ruibin Bai, Yew-Soon Ong, Yuyang Zhou","submitted_at":"2025-06-03T08:39:42Z","abstract_excerpt":"Modern neural architecture search (NAS) is inherently multi-objective, balancing trade-offs such as accuracy, parameter count, and computational cost. This complexity makes NAS computationally expensive and nearly impossible to solve without efficient approximations. To address this, we propose a novel surrogate modelling approach that leverages an ensemble of Siamese network blocks to predict dominance relationships between candidate architectures. Lightweight and easy to train, the surrogate achieves 92% accuracy and replaces the crowding distance calculation in the survivor selection strate"},"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":"2506.02623","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T08:39:42Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"2db12e5ee5302a39d333aeb27e57d7e7958ce3b5d9cb08d0c59d6b2a5ad6e82a","abstract_canon_sha256":"4f1d3fa8a1f51dd05122406693f186cd6a77c4c11913b83c491c88531411d288"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:05.573250Z","signature_b64":"85jDq3SEOO3lUZJtCN3XOTK4SV6pr6I64ttwyFxWLthbj22C0tnfl2sSCEEz5K5o7zH3jQbrgeS6qhDnXOxZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"432d93a2b840c48b7568ee0624fdc46d04882a7ef1df1671deef614c2bab8d82","last_reissued_at":"2026-07-05T11:15:05.572795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:05.572795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SiamNAS: Siamese Surrogate Model for Dominance Relation Prediction in Multi-objective Neural Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Ferrante Neri, Ruibin Bai, Yew-Soon Ong, Yuyang Zhou","submitted_at":"2025-06-03T08:39:42Z","abstract_excerpt":"Modern neural architecture search (NAS) is inherently multi-objective, balancing trade-offs such as accuracy, parameter count, and computational cost. This complexity makes NAS computationally expensive and nearly impossible to solve without efficient approximations. To address this, we propose a novel surrogate modelling approach that leverages an ensemble of Siamese network blocks to predict dominance relationships between candidate architectures. Lightweight and easy to train, the surrogate achieves 92% accuracy and replaces the crowding distance calculation in the survivor selection strate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02623","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/2506.02623/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":"2506.02623","created_at":"2026-07-05T11:15:05.572857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02623v1","created_at":"2026-07-05T11:15:05.572857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02623","created_at":"2026-07-05T11:15:05.572857+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMWZHIVYIDCI","created_at":"2026-07-05T11:15:05.572857+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMWZHIVYIDCIW5LI","created_at":"2026-07-05T11:15:05.572857+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMWZHIVY","created_at":"2026-07-05T11:15:05.572857+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/IMWZHIVYIDCIW5LI5YDCJ7OENU","json":"https://pith.science/pith/IMWZHIVYIDCIW5LI5YDCJ7OENU.json","graph_json":"https://pith.science/api/pith-number/IMWZHIVYIDCIW5LI5YDCJ7OENU/graph.json","events_json":"https://pith.science/api/pith-number/IMWZHIVYIDCIW5LI5YDCJ7OENU/events.json","paper":"https://pith.science/paper/IMWZHIVY"},"agent_actions":{"view_html":"https://pith.science/pith/IMWZHIVYIDCIW5LI5YDCJ7OENU","download_json":"https://pith.science/pith/IMWZHIVYIDCIW5LI5YDCJ7OENU.json","view_paper":"https://pith.science/paper/IMWZHIVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02623&json=true","fetch_graph":"https://pith.science/api/pith-number/IMWZHIVYIDCIW5LI5YDCJ7OENU/graph.json","fetch_events":"https://pith.science/api/pith-number/IMWZHIVYIDCIW5LI5YDCJ7OENU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMWZHIVYIDCIW5LI5YDCJ7OENU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMWZHIVYIDCIW5LI5YDCJ7OENU/action/storage_attestation","attest_author":"https://pith.science/pith/IMWZHIVYIDCIW5LI5YDCJ7OENU/action/author_attestation","sign_citation":"https://pith.science/pith/IMWZHIVYIDCIW5LI5YDCJ7OENU/action/citation_signature","submit_replication":"https://pith.science/pith/IMWZHIVYIDCIW5LI5YDCJ7OENU/action/replication_record"}},"created_at":"2026-07-05T11:15:05.572857+00:00","updated_at":"2026-07-05T11:15:05.572857+00:00"}