{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:4I2PZIAMPVN2G3EZS5HWV4OKMK","short_pith_number":"pith:4I2PZIAM","schema_version":"1.0","canonical_sha256":"e234fca00c7d5ba36c99974f6af1ca62bc6c37a07aad56234acc933afc2dcb25","source":{"kind":"arxiv","id":"2108.00177","version":3},"attestation_state":"computed","paper":{"title":"Greedy Network Enlarging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"An Xiao, Chuanjian Liu, Chunjing Xu, Kai Han, Wei Zhang, Yiping Deng, Yunhe Wang","submitted_at":"2021-07-31T08:36:30Z","abstract_excerpt":"Recent studies on deep convolutional neural networks present a simple paradigm of architecture design, i.e., models with more MACs typically achieve better accuracy, such as EfficientNet and RegNet. These works try to enlarge all the stages in the model with one unified rule by sampling and statistical methods. However, we observe that some network architectures have similar MACs and accuracies, but their allocations on computations for different stages are quite different. In this paper, we propose to enlarge the capacity of CNN models by improving their width, depth and resolution on stage l"},"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":"2108.00177","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-07-31T08:36:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"89742166a40572f11d2de8f93ff5d75bac3cef0ee5fdca2e614ccaf745301204","abstract_canon_sha256":"eccd71d3aa244d84356b781054b40842d2ec26f627ac729bf25d5d32fb889090"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:12.163125Z","signature_b64":"Ovre54wJ66BmcB+qzhou7lNBxOC7G9HkDIf/94n/rpX7WBLPXe+zvyfw9/m5tJWaPkED8vXRwM1SMzjL2SqCAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e234fca00c7d5ba36c99974f6af1ca62bc6c37a07aad56234acc933afc2dcb25","last_reissued_at":"2026-07-05T03:35:12.162666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:12.162666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Greedy Network Enlarging","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"An Xiao, Chuanjian Liu, Chunjing Xu, Kai Han, Wei Zhang, Yiping Deng, Yunhe Wang","submitted_at":"2021-07-31T08:36:30Z","abstract_excerpt":"Recent studies on deep convolutional neural networks present a simple paradigm of architecture design, i.e., models with more MACs typically achieve better accuracy, such as EfficientNet and RegNet. These works try to enlarge all the stages in the model with one unified rule by sampling and statistical methods. However, we observe that some network architectures have similar MACs and accuracies, but their allocations on computations for different stages are quite different. In this paper, we propose to enlarge the capacity of CNN models by improving their width, depth and resolution on stage l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.00177","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/2108.00177/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":"2108.00177","created_at":"2026-07-05T03:35:12.162729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.00177v3","created_at":"2026-07-05T03:35:12.162729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.00177","created_at":"2026-07-05T03:35:12.162729+00:00"},{"alias_kind":"pith_short_12","alias_value":"4I2PZIAMPVN2","created_at":"2026-07-05T03:35:12.162729+00:00"},{"alias_kind":"pith_short_16","alias_value":"4I2PZIAMPVN2G3EZ","created_at":"2026-07-05T03:35:12.162729+00:00"},{"alias_kind":"pith_short_8","alias_value":"4I2PZIAM","created_at":"2026-07-05T03:35:12.162729+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/4I2PZIAMPVN2G3EZS5HWV4OKMK","json":"https://pith.science/pith/4I2PZIAMPVN2G3EZS5HWV4OKMK.json","graph_json":"https://pith.science/api/pith-number/4I2PZIAMPVN2G3EZS5HWV4OKMK/graph.json","events_json":"https://pith.science/api/pith-number/4I2PZIAMPVN2G3EZS5HWV4OKMK/events.json","paper":"https://pith.science/paper/4I2PZIAM"},"agent_actions":{"view_html":"https://pith.science/pith/4I2PZIAMPVN2G3EZS5HWV4OKMK","download_json":"https://pith.science/pith/4I2PZIAMPVN2G3EZS5HWV4OKMK.json","view_paper":"https://pith.science/paper/4I2PZIAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.00177&json=true","fetch_graph":"https://pith.science/api/pith-number/4I2PZIAMPVN2G3EZS5HWV4OKMK/graph.json","fetch_events":"https://pith.science/api/pith-number/4I2PZIAMPVN2G3EZS5HWV4OKMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4I2PZIAMPVN2G3EZS5HWV4OKMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4I2PZIAMPVN2G3EZS5HWV4OKMK/action/storage_attestation","attest_author":"https://pith.science/pith/4I2PZIAMPVN2G3EZS5HWV4OKMK/action/author_attestation","sign_citation":"https://pith.science/pith/4I2PZIAMPVN2G3EZS5HWV4OKMK/action/citation_signature","submit_replication":"https://pith.science/pith/4I2PZIAMPVN2G3EZS5HWV4OKMK/action/replication_record"}},"created_at":"2026-07-05T03:35:12.162729+00:00","updated_at":"2026-07-05T03:35:12.162729+00:00"}