{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7DS5SMLSJH2YKVQN4GQRWGGH6W","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"56e0bbc74ef3ba1286cba10bf8118543d3fa04f91e423f1e86ff2aca7d86045b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T17:58:39Z","title_canon_sha256":"1dce7147772e326f18bca9435b1a390da3ff3b070532883c251c7bd9ffc7f4d6"},"schema_version":"1.0","source":{"id":"2403.13043","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13043","created_at":"2026-07-05T08:45:26Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13043v2","created_at":"2026-07-05T08:45:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13043","created_at":"2026-07-05T08:45:26Z"},{"alias_kind":"pith_short_12","alias_value":"7DS5SMLSJH2Y","created_at":"2026-07-05T08:45:26Z"},{"alias_kind":"pith_short_16","alias_value":"7DS5SMLSJH2YKVQN","created_at":"2026-07-05T08:45:26Z"},{"alias_kind":"pith_short_8","alias_value":"7DS5SMLS","created_at":"2026-07-05T08:45:26Z"}],"graph_snapshots":[{"event_id":"sha256:e77b76d0f2c86652679e5f91486e9151afc83493fccb3a474e9c07b8538e90d6","target":"graph","created_at":"2026-07-05T08:45:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.13043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling up the size of vision models has been the de facto standard to obtain more powerful visual representations. In this work, we discuss the point beyond which larger vision models are not necessary. First, we demonstrate the power of Scaling on Scales (S$^2$), whereby a pre-trained and frozen smaller vision model (e.g., ViT-B or ViT-L), run over multiple image scales, can outperform larger models (e.g., ViT-H or ViT-G) on classification, segmentation, depth estimation, Multimodal LLM (MLLM) benchmarks, and robotic manipulation. Notably, S$^2$ achieves state-of-the-art performance in detai","authors_text":"Baifeng Shi, Maolin Mao, Trevor Darrell, Xin Wang, Ziyang Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T17:58:39Z","title":"When Do We Not Need Larger Vision Models?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13043","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7785600c0a61f0da7c54d872e54e1d748414ea82db99198042afe6ee898037ea","target":"record","created_at":"2026-07-05T08:45:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"56e0bbc74ef3ba1286cba10bf8118543d3fa04f91e423f1e86ff2aca7d86045b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-19T17:58:39Z","title_canon_sha256":"1dce7147772e326f18bca9435b1a390da3ff3b070532883c251c7bd9ffc7f4d6"},"schema_version":"1.0","source":{"id":"2403.13043","kind":"arxiv","version":2}},"canonical_sha256":"f8e5d9317249f585560de1a11b18c7f589f34284fb971513d3bd51f61c8d3cdc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8e5d9317249f585560de1a11b18c7f589f34284fb971513d3bd51f61c8d3cdc","first_computed_at":"2026-07-05T08:45:26.459005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:26.459005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2OU+lBBRClzwDI6+TDioVnezm4G+axN4xJgXmOvdRhHCfkqrZ9hJ9K33BZaNZmoLbNqhf7mc34Lz9xAknt96Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:26.459455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.13043","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7785600c0a61f0da7c54d872e54e1d748414ea82db99198042afe6ee898037ea","sha256:e77b76d0f2c86652679e5f91486e9151afc83493fccb3a474e9c07b8538e90d6"],"state_sha256":"81008ff2535fdf2df4fcc62d17f603ab35f9de7c4e7db7d1f66c6f453425b711"}