{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5HZLFV4FBSVRKXJSRTG7ZG7J75","short_pith_number":"pith:5HZLFV4F","schema_version":"1.0","canonical_sha256":"e9f2b2d7850cab155d328ccdfc9be9ff64529b468cb6d012e0b3dc61abee4d4f","source":{"kind":"arxiv","id":"1906.06832","version":2},"attestation_state":"computed","paper":{"title":"Sample-Efficient Neural Architecture Search by Learning Action Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Linnan Wang, Rodrigo Fonseca, Saining Xie, Teng Li, Yuandong Tian","submitted_at":"2019-06-17T03:50:25Z","abstract_excerpt":"Neural Architecture Search (NAS) has emerged as a promising technique for automatic neural network design. However, existing MCTS based NAS approaches often utilize manually designed action space, which is not directly related to the performance metric to be optimized (e.g., accuracy), leading to sample-inefficient explorations of architectures. To improve the sample efficiency, this paper proposes Latent Action Neural Architecture Search (LaNAS), which learns actions to recursively partition the search space into good or bad regions that contain networks with similar performance metrics. Duri"},"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":"1906.06832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-17T03:50:25Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"0796ee037002ca46905ad9dea2787393ea7d6f31dd0defb9fc59e7f0131a802f","abstract_canon_sha256":"19ee8841a8ab7343e6c895e6575dfaefaf1b9513f5e921127573321ee31c27b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:15.419764Z","signature_b64":"pYI7fffJ9hVT17GkzVX25PCkK7Z+gAV3GlX+/zZouekrtYH1nqTIJzBE+kndx2bmppkHp3OzfOv/MUm+BpU0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9f2b2d7850cab155d328ccdfc9be9ff64529b468cb6d012e0b3dc61abee4d4f","last_reissued_at":"2026-07-05T02:28:15.419284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:15.419284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample-Efficient Neural Architecture Search by Learning Action Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Linnan Wang, Rodrigo Fonseca, Saining Xie, Teng Li, Yuandong Tian","submitted_at":"2019-06-17T03:50:25Z","abstract_excerpt":"Neural Architecture Search (NAS) has emerged as a promising technique for automatic neural network design. However, existing MCTS based NAS approaches often utilize manually designed action space, which is not directly related to the performance metric to be optimized (e.g., accuracy), leading to sample-inefficient explorations of architectures. To improve the sample efficiency, this paper proposes Latent Action Neural Architecture Search (LaNAS), which learns actions to recursively partition the search space into good or bad regions that contain networks with similar performance metrics. Duri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06832","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/1906.06832/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":"1906.06832","created_at":"2026-07-05T02:28:15.419352+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.06832v2","created_at":"2026-07-05T02:28:15.419352+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06832","created_at":"2026-07-05T02:28:15.419352+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HZLFV4FBSVR","created_at":"2026-07-05T02:28:15.419352+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HZLFV4FBSVRKXJS","created_at":"2026-07-05T02:28:15.419352+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HZLFV4F","created_at":"2026-07-05T02:28:15.419352+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.07186","citing_title":"Monte Carlo Tree Search based Space Transfer for Black-box Optimization","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HZLFV4FBSVRKXJSRTG7ZG7J75","json":"https://pith.science/pith/5HZLFV4FBSVRKXJSRTG7ZG7J75.json","graph_json":"https://pith.science/api/pith-number/5HZLFV4FBSVRKXJSRTG7ZG7J75/graph.json","events_json":"https://pith.science/api/pith-number/5HZLFV4FBSVRKXJSRTG7ZG7J75/events.json","paper":"https://pith.science/paper/5HZLFV4F"},"agent_actions":{"view_html":"https://pith.science/pith/5HZLFV4FBSVRKXJSRTG7ZG7J75","download_json":"https://pith.science/pith/5HZLFV4FBSVRKXJSRTG7ZG7J75.json","view_paper":"https://pith.science/paper/5HZLFV4F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.06832&json=true","fetch_graph":"https://pith.science/api/pith-number/5HZLFV4FBSVRKXJSRTG7ZG7J75/graph.json","fetch_events":"https://pith.science/api/pith-number/5HZLFV4FBSVRKXJSRTG7ZG7J75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HZLFV4FBSVRKXJSRTG7ZG7J75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HZLFV4FBSVRKXJSRTG7ZG7J75/action/storage_attestation","attest_author":"https://pith.science/pith/5HZLFV4FBSVRKXJSRTG7ZG7J75/action/author_attestation","sign_citation":"https://pith.science/pith/5HZLFV4FBSVRKXJSRTG7ZG7J75/action/citation_signature","submit_replication":"https://pith.science/pith/5HZLFV4FBSVRKXJSRTG7ZG7J75/action/replication_record"}},"created_at":"2026-07-05T02:28:15.419352+00:00","updated_at":"2026-07-05T02:28:15.419352+00:00"}