{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6IUOJ4JHGMGNNNRXGSRIHRKMOH","short_pith_number":"pith:6IUOJ4JH","schema_version":"1.0","canonical_sha256":"f228e4f127330cd6b63734a283c54c71f0ea6b85e1713a6773612840f53771b7","source":{"kind":"arxiv","id":"1707.04873","version":2},"attestation_state":"computed","paper":{"title":"Efficient Architecture Search by Network Transformation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Han Cai, Jun Wang, Tianyao Chen, Weinan Zhang, Yong Yu","submitted_at":"2017-07-16T12:39:02Z","abstract_excerpt":"Techniques for automatically designing deep neural network architectures such as reinforcement learning based approaches have recently shown promising results. However, their success is based on vast computational resources (e.g. hundreds of GPUs), making them difficult to be widely used. A noticeable limitation is that they still design and train each network from scratch during the exploration of the architecture space, which is highly inefficient. In this paper, we propose a new framework toward efficient architecture search by exploring the architecture space based on the current network a"},"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":"1707.04873","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-07-16T12:39:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6a7a4b0ede30f7c8b9c12eaa841b75d2d68e627c0bcef65eca50a82603e58ca0","abstract_canon_sha256":"6c7224f0befe6f891ecfdc1f246f0486ab05443c59f8e418074e5aea7c80f4f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:01.360066Z","signature_b64":"aHY3a2Yfot1e9nSZ0qeS/fx8ZbJhj/mS0fxlzYdnZRX0j97vnp3l4nqNSrCRSJAo7Wbh9CfGzmBEqhvpagS4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f228e4f127330cd6b63734a283c54c71f0ea6b85e1713a6773612840f53771b7","last_reissued_at":"2026-05-18T00:30:01.359400Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:01.359400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Architecture Search by Network Transformation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Han Cai, Jun Wang, Tianyao Chen, Weinan Zhang, Yong Yu","submitted_at":"2017-07-16T12:39:02Z","abstract_excerpt":"Techniques for automatically designing deep neural network architectures such as reinforcement learning based approaches have recently shown promising results. However, their success is based on vast computational resources (e.g. hundreds of GPUs), making them difficult to be widely used. A noticeable limitation is that they still design and train each network from scratch during the exploration of the architecture space, which is highly inefficient. In this paper, we propose a new framework toward efficient architecture search by exploring the architecture space based on the current network a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.04873","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":""},"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":"1707.04873","created_at":"2026-05-18T00:30:01.359517+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.04873v2","created_at":"2026-05-18T00:30:01.359517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.04873","created_at":"2026-05-18T00:30:01.359517+00:00"},{"alias_kind":"pith_short_12","alias_value":"6IUOJ4JHGMGN","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"6IUOJ4JHGMGNNNRX","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"6IUOJ4JH","created_at":"2026-05-18T12:31:03.183658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1710.05941","citing_title":"Searching for Activation Functions","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6IUOJ4JHGMGNNNRXGSRIHRKMOH","json":"https://pith.science/pith/6IUOJ4JHGMGNNNRXGSRIHRKMOH.json","graph_json":"https://pith.science/api/pith-number/6IUOJ4JHGMGNNNRXGSRIHRKMOH/graph.json","events_json":"https://pith.science/api/pith-number/6IUOJ4JHGMGNNNRXGSRIHRKMOH/events.json","paper":"https://pith.science/paper/6IUOJ4JH"},"agent_actions":{"view_html":"https://pith.science/pith/6IUOJ4JHGMGNNNRXGSRIHRKMOH","download_json":"https://pith.science/pith/6IUOJ4JHGMGNNNRXGSRIHRKMOH.json","view_paper":"https://pith.science/paper/6IUOJ4JH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.04873&json=true","fetch_graph":"https://pith.science/api/pith-number/6IUOJ4JHGMGNNNRXGSRIHRKMOH/graph.json","fetch_events":"https://pith.science/api/pith-number/6IUOJ4JHGMGNNNRXGSRIHRKMOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6IUOJ4JHGMGNNNRXGSRIHRKMOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6IUOJ4JHGMGNNNRXGSRIHRKMOH/action/storage_attestation","attest_author":"https://pith.science/pith/6IUOJ4JHGMGNNNRXGSRIHRKMOH/action/author_attestation","sign_citation":"https://pith.science/pith/6IUOJ4JHGMGNNNRXGSRIHRKMOH/action/citation_signature","submit_replication":"https://pith.science/pith/6IUOJ4JHGMGNNNRXGSRIHRKMOH/action/replication_record"}},"created_at":"2026-05-18T00:30:01.359517+00:00","updated_at":"2026-05-18T00:30:01.359517+00:00"}