{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UPWTI5XMVTD6IHF5QDGDJJEGXA","short_pith_number":"pith:UPWTI5XM","schema_version":"1.0","canonical_sha256":"a3ed3476ecacc7e41cbd80cc34a486b83c75be55bb1394a1508cd5f0c93e674c","source":{"kind":"arxiv","id":"1909.13404","version":1},"attestation_state":"computed","paper":{"title":"Towards modular and programmable architecture search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Ferreira, Darshan Patil, Geoffrey Gordon, Matthew Gormley, Nghia Le, Renato Negrinho","submitted_at":"2019-09-30T00:18:56Z","abstract_excerpt":"Neural architecture search methods are able to find high performance deep learning architectures with minimal effort from an expert. However, current systems focus on specific use-cases (e.g. convolutional image classifiers and recurrent language models), making them unsuitable for general use-cases that an expert might wish to write. Hyperparameter optimization systems are general-purpose but lack the constructs needed for easy application to architecture search. In this work, we propose a formal language for encoding search spaces over general computational graphs. The language constructs al"},"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":"1909.13404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-30T00:18:56Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"294fd3b56b3109782fc8381759efaf089dafe869f877d7e423699733c7da1f2d","abstract_canon_sha256":"a8d21a113cbf768e2132282a0b59354a7d33b6cea1a3d1d9155ee4a52b1b3a68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:08:10.009416Z","signature_b64":"4omKEunZEQ7IP2py4IRXiwot7QYHzb5TfSh8JC1WXrFxrviTRnB8Q2RUVvhw2X3QGMjL/YM7KFONahaj63kfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3ed3476ecacc7e41cbd80cc34a486b83c75be55bb1394a1508cd5f0c93e674c","last_reissued_at":"2026-07-05T00:08:10.008968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:08:10.008968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards modular and programmable architecture search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Ferreira, Darshan Patil, Geoffrey Gordon, Matthew Gormley, Nghia Le, Renato Negrinho","submitted_at":"2019-09-30T00:18:56Z","abstract_excerpt":"Neural architecture search methods are able to find high performance deep learning architectures with minimal effort from an expert. However, current systems focus on specific use-cases (e.g. convolutional image classifiers and recurrent language models), making them unsuitable for general use-cases that an expert might wish to write. Hyperparameter optimization systems are general-purpose but lack the constructs needed for easy application to architecture search. In this work, we propose a formal language for encoding search spaces over general computational graphs. The language constructs al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.13404","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/1909.13404/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":"1909.13404","created_at":"2026-07-05T00:08:10.009025+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.13404v1","created_at":"2026-07-05T00:08:10.009025+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.13404","created_at":"2026-07-05T00:08:10.009025+00:00"},{"alias_kind":"pith_short_12","alias_value":"UPWTI5XMVTD6","created_at":"2026-07-05T00:08:10.009025+00:00"},{"alias_kind":"pith_short_16","alias_value":"UPWTI5XMVTD6IHF5","created_at":"2026-07-05T00:08:10.009025+00:00"},{"alias_kind":"pith_short_8","alias_value":"UPWTI5XM","created_at":"2026-07-05T00:08:10.009025+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/UPWTI5XMVTD6IHF5QDGDJJEGXA","json":"https://pith.science/pith/UPWTI5XMVTD6IHF5QDGDJJEGXA.json","graph_json":"https://pith.science/api/pith-number/UPWTI5XMVTD6IHF5QDGDJJEGXA/graph.json","events_json":"https://pith.science/api/pith-number/UPWTI5XMVTD6IHF5QDGDJJEGXA/events.json","paper":"https://pith.science/paper/UPWTI5XM"},"agent_actions":{"view_html":"https://pith.science/pith/UPWTI5XMVTD6IHF5QDGDJJEGXA","download_json":"https://pith.science/pith/UPWTI5XMVTD6IHF5QDGDJJEGXA.json","view_paper":"https://pith.science/paper/UPWTI5XM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.13404&json=true","fetch_graph":"https://pith.science/api/pith-number/UPWTI5XMVTD6IHF5QDGDJJEGXA/graph.json","fetch_events":"https://pith.science/api/pith-number/UPWTI5XMVTD6IHF5QDGDJJEGXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UPWTI5XMVTD6IHF5QDGDJJEGXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UPWTI5XMVTD6IHF5QDGDJJEGXA/action/storage_attestation","attest_author":"https://pith.science/pith/UPWTI5XMVTD6IHF5QDGDJJEGXA/action/author_attestation","sign_citation":"https://pith.science/pith/UPWTI5XMVTD6IHF5QDGDJJEGXA/action/citation_signature","submit_replication":"https://pith.science/pith/UPWTI5XMVTD6IHF5QDGDJJEGXA/action/replication_record"}},"created_at":"2026-07-05T00:08:10.009025+00:00","updated_at":"2026-07-05T00:08:10.009025+00:00"}