{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YIS77JEHY2264M24SQM7BHAFII","short_pith_number":"pith:YIS77JEH","schema_version":"1.0","canonical_sha256":"c225ffa487c6b5ee335c9419f09c05423ba7888b5cd541b41e6b823bbc487ec3","source":{"kind":"arxiv","id":"2104.00298","version":3},"attestation_state":"computed","paper":{"title":"EfficientNetV2: Smaller Models and Faster Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mingxing Tan, Quoc V. Le","submitted_at":"2021-04-01T07:08:36Z","abstract_excerpt":"This paper introduces EfficientNetV2, a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models. To develop this family of models, we use a combination of training-aware neural architecture search and scaling, to jointly optimize training speed and parameter efficiency. The models were searched from the search space enriched with new ops such as Fused-MBConv. Our experiments show that EfficientNetV2 models train much faster than state-of-the-art models while being up to 6.8x smaller.\n  Our training can be further sped up by prog"},"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":"2104.00298","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-04-01T07:08:36Z","cross_cats_sorted":[],"title_canon_sha256":"8ee9bc7d3aaa78789ddaebf1706ab04de4ee0fbc13aeee12ce1f22a11f10d72d","abstract_canon_sha256":"4a3e7074ed83f2325fee2715d482c53a3fd9f6b580717c170212549d841e5caa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:02.097755Z","signature_b64":"bL2jCKXc8nQP2zHa1whm/0FmEqizY697WElLZHDFjHZr0VGQ2QhvEroPm/Xu1TE9rMg9ziNcMOIFVLhRywiwAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c225ffa487c6b5ee335c9419f09c05423ba7888b5cd541b41e6b823bbc487ec3","last_reissued_at":"2026-07-05T02:52:02.097269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:02.097269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EfficientNetV2: Smaller Models and Faster Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mingxing Tan, Quoc V. Le","submitted_at":"2021-04-01T07:08:36Z","abstract_excerpt":"This paper introduces EfficientNetV2, a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models. To develop this family of models, we use a combination of training-aware neural architecture search and scaling, to jointly optimize training speed and parameter efficiency. The models were searched from the search space enriched with new ops such as Fused-MBConv. Our experiments show that EfficientNetV2 models train much faster than state-of-the-art models while being up to 6.8x smaller.\n  Our training can be further sped up by prog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00298","kind":"arxiv","version":3},"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/2104.00298/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":"2104.00298","created_at":"2026-07-05T02:52:02.097341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.00298v3","created_at":"2026-07-05T02:52:02.097341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00298","created_at":"2026-07-05T02:52:02.097341+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIS77JEHY226","created_at":"2026-07-05T02:52:02.097341+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIS77JEHY2264M24","created_at":"2026-07-05T02:52:02.097341+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIS77JEH","created_at":"2026-07-05T02:52:02.097341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10372","citing_title":"ClinReadNet: A clinical reading-inspired network for low-dose abdominal CT image quality assessment","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26370","citing_title":"Joint Instance Segmentation and Geometric Attribute Regression for Roof Structures in Aerial Imagery","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19856","citing_title":"StableGrad: Backward Scale Control without Batch Normalization","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15484","citing_title":"When Does Sparse MoE Help in Vision? The Role of Backbone Compute Leverage in Sparse Routing","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2507.23315","citing_title":"Analysis of Hyperparameter Optimization Effects on Lightweight Deep Models for Real-Time Image Classification","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20028","citing_title":"Descriptor: Parasitoid Wasps and Associated Hymenoptera Dataset (DAPWH)","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03203","citing_title":"PR3DICTR: A modular AI framework for medical 3D image-based detection and outcome prediction","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01075","citing_title":"Neighbor2Inverse: Self-Supervised Denoising for Low-Dose Region-of-Interest Phase Contrast CT","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02614","citing_title":"Validation of an AI-based end-to-end model for prostate pathology using long-term archived routine samples","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YIS77JEHY2264M24SQM7BHAFII","json":"https://pith.science/pith/YIS77JEHY2264M24SQM7BHAFII.json","graph_json":"https://pith.science/api/pith-number/YIS77JEHY2264M24SQM7BHAFII/graph.json","events_json":"https://pith.science/api/pith-number/YIS77JEHY2264M24SQM7BHAFII/events.json","paper":"https://pith.science/paper/YIS77JEH"},"agent_actions":{"view_html":"https://pith.science/pith/YIS77JEHY2264M24SQM7BHAFII","download_json":"https://pith.science/pith/YIS77JEHY2264M24SQM7BHAFII.json","view_paper":"https://pith.science/paper/YIS77JEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.00298&json=true","fetch_graph":"https://pith.science/api/pith-number/YIS77JEHY2264M24SQM7BHAFII/graph.json","fetch_events":"https://pith.science/api/pith-number/YIS77JEHY2264M24SQM7BHAFII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIS77JEHY2264M24SQM7BHAFII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIS77JEHY2264M24SQM7BHAFII/action/storage_attestation","attest_author":"https://pith.science/pith/YIS77JEHY2264M24SQM7BHAFII/action/author_attestation","sign_citation":"https://pith.science/pith/YIS77JEHY2264M24SQM7BHAFII/action/citation_signature","submit_replication":"https://pith.science/pith/YIS77JEHY2264M24SQM7BHAFII/action/replication_record"}},"created_at":"2026-07-05T02:52:02.097341+00:00","updated_at":"2026-07-05T02:52:02.097341+00:00"}