{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QJ7RAZ6VEJ4XWVG6YR233YOCCA","short_pith_number":"pith:QJ7RAZ6V","schema_version":"1.0","canonical_sha256":"827f1067d522797b54dec475bde1c21016d227e3a920c2fabd43442a6ed4fdaa","source":{"kind":"arxiv","id":"1907.05737","version":4},"attestation_state":"computed","paper":{"title":"PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Guo-jun Qi, Hongkai Xiong, Lingxi Xie, Qi Tian, Xiaopeng Zhang, Xin Chen, Yuhui Xu","submitted_at":"2019-07-12T13:26:09Z","abstract_excerpt":"Differentiable architecture search (DARTS) provided a fast solution in finding effective network architectures, but suffered from large memory and computing overheads in jointly training a super-network and searching for an optimal architecture. In this paper, we present a novel approach, namely, Partially-Connected DARTS, by sampling a small part of super-network to reduce the redundancy in exploring the network space, thereby performing a more efficient search without comprising the performance. In particular, we perform operation search in a subset of channels while bypassing the held out p"},"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":"1907.05737","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-12T13:26:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8dcb725e2fbaf8a82129b7e40cb5aff3018b017a60bf25b2d1ef0ef10e3695cd","abstract_canon_sha256":"2c3ef7def1a9f0a3ed23b9225e2b094ea70c9b5643ffb42f602888723a2d2bc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:53:06.876921Z","signature_b64":"MlW+8Yt4jr8yfCm5DhZfffxO3r37i+xtD83CegvLvzHDZ5S7Jkojehc6azpFfStIUHKhzZG23LdIEFB3cXE1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"827f1067d522797b54dec475bde1c21016d227e3a920c2fabd43442a6ed4fdaa","last_reissued_at":"2026-07-05T00:53:06.876441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:53:06.876441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Guo-jun Qi, Hongkai Xiong, Lingxi Xie, Qi Tian, Xiaopeng Zhang, Xin Chen, Yuhui Xu","submitted_at":"2019-07-12T13:26:09Z","abstract_excerpt":"Differentiable architecture search (DARTS) provided a fast solution in finding effective network architectures, but suffered from large memory and computing overheads in jointly training a super-network and searching for an optimal architecture. In this paper, we present a novel approach, namely, Partially-Connected DARTS, by sampling a small part of super-network to reduce the redundancy in exploring the network space, thereby performing a more efficient search without comprising the performance. In particular, we perform operation search in a subset of channels while bypassing the held out p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05737","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/1907.05737/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":"1907.05737","created_at":"2026-07-05T00:53:06.876497+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.05737v4","created_at":"2026-07-05T00:53:06.876497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05737","created_at":"2026-07-05T00:53:06.876497+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJ7RAZ6VEJ4X","created_at":"2026-07-05T00:53:06.876497+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJ7RAZ6VEJ4XWVG6","created_at":"2026-07-05T00:53:06.876497+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJ7RAZ6V","created_at":"2026-07-05T00:53:06.876497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01870","citing_title":"CamoNAS: Neural Architecture Search for Enhanced Camouflaged Object Detection","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29582","citing_title":"Bilevel Optimization for Neural Architecture Search","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21560","citing_title":"AutoMCU: Feasibility-First MCU Neural Network Customization via LLM-based Multi-Agent Systems","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QJ7RAZ6VEJ4XWVG6YR233YOCCA","json":"https://pith.science/pith/QJ7RAZ6VEJ4XWVG6YR233YOCCA.json","graph_json":"https://pith.science/api/pith-number/QJ7RAZ6VEJ4XWVG6YR233YOCCA/graph.json","events_json":"https://pith.science/api/pith-number/QJ7RAZ6VEJ4XWVG6YR233YOCCA/events.json","paper":"https://pith.science/paper/QJ7RAZ6V"},"agent_actions":{"view_html":"https://pith.science/pith/QJ7RAZ6VEJ4XWVG6YR233YOCCA","download_json":"https://pith.science/pith/QJ7RAZ6VEJ4XWVG6YR233YOCCA.json","view_paper":"https://pith.science/paper/QJ7RAZ6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.05737&json=true","fetch_graph":"https://pith.science/api/pith-number/QJ7RAZ6VEJ4XWVG6YR233YOCCA/graph.json","fetch_events":"https://pith.science/api/pith-number/QJ7RAZ6VEJ4XWVG6YR233YOCCA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJ7RAZ6VEJ4XWVG6YR233YOCCA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJ7RAZ6VEJ4XWVG6YR233YOCCA/action/storage_attestation","attest_author":"https://pith.science/pith/QJ7RAZ6VEJ4XWVG6YR233YOCCA/action/author_attestation","sign_citation":"https://pith.science/pith/QJ7RAZ6VEJ4XWVG6YR233YOCCA/action/citation_signature","submit_replication":"https://pith.science/pith/QJ7RAZ6VEJ4XWVG6YR233YOCCA/action/replication_record"}},"created_at":"2026-07-05T00:53:06.876497+00:00","updated_at":"2026-07-05T00:53:06.876497+00:00"}