{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:O27WSXLLRRCIQ6QF3SQ4KOP4P3","short_pith_number":"pith:O27WSXLL","schema_version":"1.0","canonical_sha256":"76bf695d6b8c44887a05dca1c539fc7ef0b4b0e7ccdd204bf52dfcebf063ce1e","source":{"kind":"arxiv","id":"2110.00476","version":1},"attestation_state":"computed","paper":{"title":"ResNet strikes back: An improved training procedure in timm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Herv\\'e J\\'egou, Hugo Touvron, Ross Wightman","submitted_at":"2021-10-01T15:09:22Z","abstract_excerpt":"The influential Residual Networks designed by He et al. remain the gold-standard architecture in numerous scientific publications. They typically serve as the default architecture in studies, or as baselines when new architectures are proposed. Yet there has been significant progress on best practices for training neural networks since the inception of the ResNet architecture in 2015. Novel optimization & data-augmentation have increased the effectiveness of the training recipes. In this paper, we re-evaluate the performance of the vanilla ResNet-50 when trained with a procedure that integrate"},"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":"2110.00476","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-01T15:09:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"785725effbfb4462768c82bf819fa149cac93f3822c393bb0dc232e44e76624c","abstract_canon_sha256":"b84952aaa4f745f1f3b4fe979645eece3acac111c5b7673d7c644f5aec6c3eb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:19:29.797278Z","signature_b64":"hK5g1EOYtGSy6VcFDBH4aLZ0fJAnst6QsztdBhB16xsiGoPD9F68U+kb4hfemg0XRTTM2VXhfIV0Sajqmt5/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76bf695d6b8c44887a05dca1c539fc7ef0b4b0e7ccdd204bf52dfcebf063ce1e","last_reissued_at":"2026-07-05T03:19:29.796936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:19:29.796936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ResNet strikes back: An improved training procedure in timm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Herv\\'e J\\'egou, Hugo Touvron, Ross Wightman","submitted_at":"2021-10-01T15:09:22Z","abstract_excerpt":"The influential Residual Networks designed by He et al. remain the gold-standard architecture in numerous scientific publications. They typically serve as the default architecture in studies, or as baselines when new architectures are proposed. Yet there has been significant progress on best practices for training neural networks since the inception of the ResNet architecture in 2015. Novel optimization & data-augmentation have increased the effectiveness of the training recipes. In this paper, we re-evaluate the performance of the vanilla ResNet-50 when trained with a procedure that integrate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00476","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/2110.00476/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":"2110.00476","created_at":"2026-07-05T03:19:29.796991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.00476v1","created_at":"2026-07-05T03:19:29.796991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00476","created_at":"2026-07-05T03:19:29.796991+00:00"},{"alias_kind":"pith_short_12","alias_value":"O27WSXLLRRCI","created_at":"2026-07-05T03:19:29.796991+00:00"},{"alias_kind":"pith_short_16","alias_value":"O27WSXLLRRCIQ6QF","created_at":"2026-07-05T03:19:29.796991+00:00"},{"alias_kind":"pith_short_8","alias_value":"O27WSXLL","created_at":"2026-07-05T03:19:29.796991+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02927","citing_title":"SaluNet: Enabling Total Plasticity in Normalization-Free Deep Networks","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02134","citing_title":"Rethinking Evaluation Paradigms in IBP-based Certified Training","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01412","citing_title":"GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2503.23947","citing_title":"Spectral-Adaptive Modulation Networks for Visual Perception","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2506.16950","citing_title":"LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2303.15343","citing_title":"Sigmoid Loss for Language Image Pre-Training","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2312.17090","citing_title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16588","citing_title":"Vision Transformers Need Registers","ref_index":287,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15451","citing_title":"Weak-to-Strong Knowledge Distillation Accelerates Visual Learning","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O27WSXLLRRCIQ6QF3SQ4KOP4P3","json":"https://pith.science/pith/O27WSXLLRRCIQ6QF3SQ4KOP4P3.json","graph_json":"https://pith.science/api/pith-number/O27WSXLLRRCIQ6QF3SQ4KOP4P3/graph.json","events_json":"https://pith.science/api/pith-number/O27WSXLLRRCIQ6QF3SQ4KOP4P3/events.json","paper":"https://pith.science/paper/O27WSXLL"},"agent_actions":{"view_html":"https://pith.science/pith/O27WSXLLRRCIQ6QF3SQ4KOP4P3","download_json":"https://pith.science/pith/O27WSXLLRRCIQ6QF3SQ4KOP4P3.json","view_paper":"https://pith.science/paper/O27WSXLL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.00476&json=true","fetch_graph":"https://pith.science/api/pith-number/O27WSXLLRRCIQ6QF3SQ4KOP4P3/graph.json","fetch_events":"https://pith.science/api/pith-number/O27WSXLLRRCIQ6QF3SQ4KOP4P3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O27WSXLLRRCIQ6QF3SQ4KOP4P3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O27WSXLLRRCIQ6QF3SQ4KOP4P3/action/storage_attestation","attest_author":"https://pith.science/pith/O27WSXLLRRCIQ6QF3SQ4KOP4P3/action/author_attestation","sign_citation":"https://pith.science/pith/O27WSXLLRRCIQ6QF3SQ4KOP4P3/action/citation_signature","submit_replication":"https://pith.science/pith/O27WSXLLRRCIQ6QF3SQ4KOP4P3/action/replication_record"}},"created_at":"2026-07-05T03:19:29.796991+00:00","updated_at":"2026-07-05T03:19:29.796991+00:00"}