{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZJGCQ5VJYAPDGLPVNXP6RJXBV6","short_pith_number":"pith:ZJGCQ5VJ","schema_version":"1.0","canonical_sha256":"ca4c2876a9c01e332df56ddfe8a6e1afa7c218b0025d46d6349eecf95d380113","source":{"kind":"arxiv","id":"2110.08710","version":3},"attestation_state":"computed","paper":{"title":"NeuralArTS: Structuring Neural Architecture Search with Type Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LO","cs.PL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Nayan Saxena, Robert Wu, Rohan Jain","submitted_at":"2021-10-17T03:28:27Z","abstract_excerpt":"Neural Architecture Search (NAS) algorithms automate the task of finding optimal deep learning architectures given an initial search space of possible operations. Developing these search spaces is usually a manual affair with pre-optimized search spaces being more efficient, rather than searching from scratch. In this paper we present a new framework called Neural Architecture Type System (NeuralArTS) that categorizes the infinite set of network operations in a structured type system. We further demonstrate how NeuralArTS can be applied to convolutional layers and propose several future direct"},"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":"2110.08710","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-17T03:28:27Z","cross_cats_sorted":["cs.LO","cs.PL","stat.ML"],"title_canon_sha256":"273294b1890c01826ae17bcd756dd793b3f0cb6f739512aca9e7279194f301b5","abstract_canon_sha256":"cea0aca8578b7909b1556bd7af9a531f72d389b7dcfc8378954ed5433aefa8fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:29:19.226120Z","signature_b64":"Rj5Q+2uqG5A/BkQJj03acRdlbhfJFYxT7uRQrn89HG4Xu8BJMXiqkBdx/udQu+uMTCvrYB9I+5r6VmLd9sZjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca4c2876a9c01e332df56ddfe8a6e1afa7c218b0025d46d6349eecf95d380113","last_reissued_at":"2026-07-05T03:29:19.225790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:29:19.225790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeuralArTS: Structuring Neural Architecture Search with Type Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LO","cs.PL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Nayan Saxena, Robert Wu, Rohan Jain","submitted_at":"2021-10-17T03:28:27Z","abstract_excerpt":"Neural Architecture Search (NAS) algorithms automate the task of finding optimal deep learning architectures given an initial search space of possible operations. Developing these search spaces is usually a manual affair with pre-optimized search spaces being more efficient, rather than searching from scratch. In this paper we present a new framework called Neural Architecture Type System (NeuralArTS) that categorizes the infinite set of network operations in a structured type system. We further demonstrate how NeuralArTS can be applied to convolutional layers and propose several future direct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08710","kind":"arxiv","version":3},"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/2110.08710/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":"2110.08710","created_at":"2026-07-05T03:29:19.225841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.08710v3","created_at":"2026-07-05T03:29:19.225841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08710","created_at":"2026-07-05T03:29:19.225841+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJGCQ5VJYAPD","created_at":"2026-07-05T03:29:19.225841+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJGCQ5VJYAPDGLPV","created_at":"2026-07-05T03:29:19.225841+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJGCQ5VJ","created_at":"2026-07-05T03:29:19.225841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20623","citing_title":"RSRCC: A Remote Sensing Regional Change Comprehension Benchmark Constructed via Retrieval-Augmented Best-of-N Ranking","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJGCQ5VJYAPDGLPVNXP6RJXBV6","json":"https://pith.science/pith/ZJGCQ5VJYAPDGLPVNXP6RJXBV6.json","graph_json":"https://pith.science/api/pith-number/ZJGCQ5VJYAPDGLPVNXP6RJXBV6/graph.json","events_json":"https://pith.science/api/pith-number/ZJGCQ5VJYAPDGLPVNXP6RJXBV6/events.json","paper":"https://pith.science/paper/ZJGCQ5VJ"},"agent_actions":{"view_html":"https://pith.science/pith/ZJGCQ5VJYAPDGLPVNXP6RJXBV6","download_json":"https://pith.science/pith/ZJGCQ5VJYAPDGLPVNXP6RJXBV6.json","view_paper":"https://pith.science/paper/ZJGCQ5VJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.08710&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJGCQ5VJYAPDGLPVNXP6RJXBV6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJGCQ5VJYAPDGLPVNXP6RJXBV6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJGCQ5VJYAPDGLPVNXP6RJXBV6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJGCQ5VJYAPDGLPVNXP6RJXBV6/action/storage_attestation","attest_author":"https://pith.science/pith/ZJGCQ5VJYAPDGLPVNXP6RJXBV6/action/author_attestation","sign_citation":"https://pith.science/pith/ZJGCQ5VJYAPDGLPVNXP6RJXBV6/action/citation_signature","submit_replication":"https://pith.science/pith/ZJGCQ5VJYAPDGLPVNXP6RJXBV6/action/replication_record"}},"created_at":"2026-07-05T03:29:19.225841+00:00","updated_at":"2026-07-05T03:29:19.225841+00:00"}