{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:EM2AABGJYOOKAY7ZJKK3CSMF35","short_pith_number":"pith:EM2AABGJ","schema_version":"1.0","canonical_sha256":"23340004c9c39ca063f94a95b14985df6717f214dc126468bcc1a7f24b4aafa8","source":{"kind":"arxiv","id":"2207.05420","version":2},"attestation_state":"computed","paper":{"title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guanglu Song, Hongsheng Li, Jihao Liu, Xin Huang, Yu Liu","submitted_at":"2022-07-12T09:30:58Z","abstract_excerpt":"Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks. However, how to effectively combine those operators to form high-performance hybrid visual architectures still remains a challenge. In this work, we study the learnable combination of convolution, transformer, and MLP by proposing a novel unified architecture search approach. Our approach contains two key designs to achieve the search for high-performance networks. First, we model the very different searchable operators in a unified form, and thus enable the operators "},"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":"2207.05420","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-07-12T09:30:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2e4ad0773e2ecef95bfcb39fe6c6ce14e11b35bb10c578c52c5950358e9d5fdc","abstract_canon_sha256":"9d2906158ca08b9ca607d1c2a54a31fd16bb8c3f918b8efa2438a0b008fb3500"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:56:18.757103Z","signature_b64":"KrL/MaOqKV6nTtQ0CkXpkPvbykFrvTOL3XwqGpXZY0Xf9Ai9bblu+n2g4bsQVMa8MBqLnuICL9SitLyPtoDwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23340004c9c39ca063f94a95b14985df6717f214dc126468bcc1a7f24b4aafa8","last_reissued_at":"2026-07-05T04:56:18.756722Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:56:18.756722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniNet: Unified Architecture Search with Convolution, Transformer, and MLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guanglu Song, Hongsheng Li, Jihao Liu, Xin Huang, Yu Liu","submitted_at":"2022-07-12T09:30:58Z","abstract_excerpt":"Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks. However, how to effectively combine those operators to form high-performance hybrid visual architectures still remains a challenge. In this work, we study the learnable combination of convolution, transformer, and MLP by proposing a novel unified architecture search approach. Our approach contains two key designs to achieve the search for high-performance networks. First, we model the very different searchable operators in a unified form, and thus enable the operators "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.05420","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/2207.05420/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":"2207.05420","created_at":"2026-07-05T04:56:18.756779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.05420v2","created_at":"2026-07-05T04:56:18.756779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.05420","created_at":"2026-07-05T04:56:18.756779+00:00"},{"alias_kind":"pith_short_12","alias_value":"EM2AABGJYOOK","created_at":"2026-07-05T04:56:18.756779+00:00"},{"alias_kind":"pith_short_16","alias_value":"EM2AABGJYOOKAY7Z","created_at":"2026-07-05T04:56:18.756779+00:00"},{"alias_kind":"pith_short_8","alias_value":"EM2AABGJ","created_at":"2026-07-05T04:56:18.756779+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/EM2AABGJYOOKAY7ZJKK3CSMF35","json":"https://pith.science/pith/EM2AABGJYOOKAY7ZJKK3CSMF35.json","graph_json":"https://pith.science/api/pith-number/EM2AABGJYOOKAY7ZJKK3CSMF35/graph.json","events_json":"https://pith.science/api/pith-number/EM2AABGJYOOKAY7ZJKK3CSMF35/events.json","paper":"https://pith.science/paper/EM2AABGJ"},"agent_actions":{"view_html":"https://pith.science/pith/EM2AABGJYOOKAY7ZJKK3CSMF35","download_json":"https://pith.science/pith/EM2AABGJYOOKAY7ZJKK3CSMF35.json","view_paper":"https://pith.science/paper/EM2AABGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.05420&json=true","fetch_graph":"https://pith.science/api/pith-number/EM2AABGJYOOKAY7ZJKK3CSMF35/graph.json","fetch_events":"https://pith.science/api/pith-number/EM2AABGJYOOKAY7ZJKK3CSMF35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EM2AABGJYOOKAY7ZJKK3CSMF35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EM2AABGJYOOKAY7ZJKK3CSMF35/action/storage_attestation","attest_author":"https://pith.science/pith/EM2AABGJYOOKAY7ZJKK3CSMF35/action/author_attestation","sign_citation":"https://pith.science/pith/EM2AABGJYOOKAY7ZJKK3CSMF35/action/citation_signature","submit_replication":"https://pith.science/pith/EM2AABGJYOOKAY7ZJKK3CSMF35/action/replication_record"}},"created_at":"2026-07-05T04:56:18.756779+00:00","updated_at":"2026-07-05T04:56:18.756779+00:00"}