{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:BFJVFVSL3O4H476ZT7LPXDGXVX","short_pith_number":"pith:BFJVFVSL","schema_version":"1.0","canonical_sha256":"095352d64bdbb87e7fd99fd6fb8cd7adf8cd8efec5c16bc063d1f38b7c721a1a","source":{"kind":"arxiv","id":"2103.07579","version":1},"attestation_state":"computed","paper":{"title":"Revisiting ResNets: Improved Training and Scaling Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aravind Srinivas, Barret Zoph, Ekin D. Cubuk, Irwan Bello, Jonathon Shlens, Tsung-Yi Lin, William Fedus, Xianzhi Du","submitted_at":"2021-03-13T00:18:19Z","abstract_excerpt":"Novel computer vision architectures monopolize the spotlight, but the impact of the model architecture is often conflated with simultaneous changes to training methodology and scaling strategies. Our work revisits the canonical ResNet (He et al., 2015) and studies these three aspects in an effort to disentangle them. Perhaps surprisingly, we find that training and scaling strategies may matter more than architectural changes, and further, that the resulting ResNets match recent state-of-the-art models. We show that the best performing scaling strategy depends on the training regime and offer t"},"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":"2103.07579","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-13T00:18:19Z","cross_cats_sorted":[],"title_canon_sha256":"f5ca7e87b5507536f657503e49a16e2a822b0fb9964f06c300939521c7a25f61","abstract_canon_sha256":"13822bd2dcfd2c5f2b0534992a79f92209deb8fc72c9e1fddfea649e5e792de2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:22:42.778770Z","signature_b64":"JmWDX4fDZyZymnpt4GUc6Z+gvGO6j/nQyIQsFxmQpgUXuXgcYRmjsqqIN+URiSmd63JEK4ctOyxLnQfje6bMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"095352d64bdbb87e7fd99fd6fb8cd7adf8cd8efec5c16bc063d1f38b7c721a1a","last_reissued_at":"2026-07-05T02:22:42.778428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:22:42.778428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting ResNets: Improved Training and Scaling Strategies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aravind Srinivas, Barret Zoph, Ekin D. Cubuk, Irwan Bello, Jonathon Shlens, Tsung-Yi Lin, William Fedus, Xianzhi Du","submitted_at":"2021-03-13T00:18:19Z","abstract_excerpt":"Novel computer vision architectures monopolize the spotlight, but the impact of the model architecture is often conflated with simultaneous changes to training methodology and scaling strategies. Our work revisits the canonical ResNet (He et al., 2015) and studies these three aspects in an effort to disentangle them. Perhaps surprisingly, we find that training and scaling strategies may matter more than architectural changes, and further, that the resulting ResNets match recent state-of-the-art models. We show that the best performing scaling strategy depends on the training regime and offer t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.07579","kind":"arxiv","version":1},"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/2103.07579/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":"2103.07579","created_at":"2026-07-05T02:22:42.778489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.07579v1","created_at":"2026-07-05T02:22:42.778489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.07579","created_at":"2026-07-05T02:22:42.778489+00:00"},{"alias_kind":"pith_short_12","alias_value":"BFJVFVSL3O4H","created_at":"2026-07-05T02:22:42.778489+00:00"},{"alias_kind":"pith_short_16","alias_value":"BFJVFVSL3O4H476Z","created_at":"2026-07-05T02:22:42.778489+00:00"},{"alias_kind":"pith_short_8","alias_value":"BFJVFVSL","created_at":"2026-07-05T02:22:42.778489+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/BFJVFVSL3O4H476ZT7LPXDGXVX","json":"https://pith.science/pith/BFJVFVSL3O4H476ZT7LPXDGXVX.json","graph_json":"https://pith.science/api/pith-number/BFJVFVSL3O4H476ZT7LPXDGXVX/graph.json","events_json":"https://pith.science/api/pith-number/BFJVFVSL3O4H476ZT7LPXDGXVX/events.json","paper":"https://pith.science/paper/BFJVFVSL"},"agent_actions":{"view_html":"https://pith.science/pith/BFJVFVSL3O4H476ZT7LPXDGXVX","download_json":"https://pith.science/pith/BFJVFVSL3O4H476ZT7LPXDGXVX.json","view_paper":"https://pith.science/paper/BFJVFVSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.07579&json=true","fetch_graph":"https://pith.science/api/pith-number/BFJVFVSL3O4H476ZT7LPXDGXVX/graph.json","fetch_events":"https://pith.science/api/pith-number/BFJVFVSL3O4H476ZT7LPXDGXVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BFJVFVSL3O4H476ZT7LPXDGXVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BFJVFVSL3O4H476ZT7LPXDGXVX/action/storage_attestation","attest_author":"https://pith.science/pith/BFJVFVSL3O4H476ZT7LPXDGXVX/action/author_attestation","sign_citation":"https://pith.science/pith/BFJVFVSL3O4H476ZT7LPXDGXVX/action/citation_signature","submit_replication":"https://pith.science/pith/BFJVFVSL3O4H476ZT7LPXDGXVX/action/replication_record"}},"created_at":"2026-07-05T02:22:42.778489+00:00","updated_at":"2026-07-05T02:22:42.778489+00:00"}