{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:E7JRMP3WEGPJ622H7R3WMCA4AE","short_pith_number":"pith:E7JRMP3W","schema_version":"1.0","canonical_sha256":"27d3163f76219e9f6b47fc7766081c010d5c1af29c231a5301fed67a4fc8502f","source":{"kind":"arxiv","id":"2305.16943","version":4},"attestation_state":"computed","paper":{"title":"DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hayeon Lee, Jaehyeong Jo, Seanie Lee, Sohyun An, Sung Ju Hwang","submitted_at":"2023-05-26T13:58:18Z","abstract_excerpt":"Existing NAS methods suffer from either an excessive amount of time for repetitive sampling and training of many task-irrelevant architectures. To tackle such limitations of existing NAS methods, we propose a paradigm shift from NAS to a novel conditional Neural Architecture Generation (NAG) framework based on diffusion models, dubbed DiffusionNAG. Specifically, we consider the neural architectures as directed graphs and propose a graph diffusion model for generating them. Moreover, with the guidance of parameterized predictors, DiffusionNAG can flexibly generate task-optimal architectures wit"},"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":"2305.16943","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T13:58:18Z","cross_cats_sorted":[],"title_canon_sha256":"f6b049a61b128289effec2264dfa16d57405407c33b36c403821e6317b7444f5","abstract_canon_sha256":"46fa3114c404b8317ad0aaf3414df1b47b6d0a1144147f4973a334318a7f311c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:50.827626Z","signature_b64":"MEUhb8FcpMP8TfC+r8dy01LwqUSBsc1aYIqn2E8jmxCs1SaHXq+0iAOMth7OHZTBO4TuWWoYJe5G69bb6SirDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27d3163f76219e9f6b47fc7766081c010d5c1af29c231a5301fed67a4fc8502f","last_reissued_at":"2026-07-05T07:59:50.827137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:50.827137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hayeon Lee, Jaehyeong Jo, Seanie Lee, Sohyun An, Sung Ju Hwang","submitted_at":"2023-05-26T13:58:18Z","abstract_excerpt":"Existing NAS methods suffer from either an excessive amount of time for repetitive sampling and training of many task-irrelevant architectures. To tackle such limitations of existing NAS methods, we propose a paradigm shift from NAS to a novel conditional Neural Architecture Generation (NAG) framework based on diffusion models, dubbed DiffusionNAG. Specifically, we consider the neural architectures as directed graphs and propose a graph diffusion model for generating them. Moreover, with the guidance of parameterized predictors, DiffusionNAG can flexibly generate task-optimal architectures wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16943","kind":"arxiv","version":4},"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/2305.16943/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":"2305.16943","created_at":"2026-07-05T07:59:50.827208+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16943v4","created_at":"2026-07-05T07:59:50.827208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16943","created_at":"2026-07-05T07:59:50.827208+00:00"},{"alias_kind":"pith_short_12","alias_value":"E7JRMP3WEGPJ","created_at":"2026-07-05T07:59:50.827208+00:00"},{"alias_kind":"pith_short_16","alias_value":"E7JRMP3WEGPJ622H","created_at":"2026-07-05T07:59:50.827208+00:00"},{"alias_kind":"pith_short_8","alias_value":"E7JRMP3W","created_at":"2026-07-05T07:59:50.827208+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05656","citing_title":"OptiProxy-NAS: Optimization Proxy based End-to-End Neural Architecture Search","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E7JRMP3WEGPJ622H7R3WMCA4AE","json":"https://pith.science/pith/E7JRMP3WEGPJ622H7R3WMCA4AE.json","graph_json":"https://pith.science/api/pith-number/E7JRMP3WEGPJ622H7R3WMCA4AE/graph.json","events_json":"https://pith.science/api/pith-number/E7JRMP3WEGPJ622H7R3WMCA4AE/events.json","paper":"https://pith.science/paper/E7JRMP3W"},"agent_actions":{"view_html":"https://pith.science/pith/E7JRMP3WEGPJ622H7R3WMCA4AE","download_json":"https://pith.science/pith/E7JRMP3WEGPJ622H7R3WMCA4AE.json","view_paper":"https://pith.science/paper/E7JRMP3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16943&json=true","fetch_graph":"https://pith.science/api/pith-number/E7JRMP3WEGPJ622H7R3WMCA4AE/graph.json","fetch_events":"https://pith.science/api/pith-number/E7JRMP3WEGPJ622H7R3WMCA4AE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E7JRMP3WEGPJ622H7R3WMCA4AE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E7JRMP3WEGPJ622H7R3WMCA4AE/action/storage_attestation","attest_author":"https://pith.science/pith/E7JRMP3WEGPJ622H7R3WMCA4AE/action/author_attestation","sign_citation":"https://pith.science/pith/E7JRMP3WEGPJ622H7R3WMCA4AE/action/citation_signature","submit_replication":"https://pith.science/pith/E7JRMP3WEGPJ622H7R3WMCA4AE/action/replication_record"}},"created_at":"2026-07-05T07:59:50.827208+00:00","updated_at":"2026-07-05T07:59:50.827208+00:00"}