{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VQKI4TRE5F3UEETFKW7RYSPVYL","short_pith_number":"pith:VQKI4TRE","schema_version":"1.0","canonical_sha256":"ac148e4e24e97742126555bf1c49f5c2da92fa008240a72aae38bca4be782733","source":{"kind":"arxiv","id":"2404.02132","version":2},"attestation_state":"computed","paper":{"title":"ViTamin: Designing Scalable Vision Models in the Vision-Language Era","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Jieneng Chen, Liang-Chieh Chen, Qihang Yu, Xiaohui Shen","submitted_at":"2024-04-02T17:40:29Z","abstract_excerpt":"Recent breakthroughs in vision-language models (VLMs) start a new page in the vision community. The VLMs provide stronger and more generalizable feature embeddings compared to those from ImageNet-pretrained models, thanks to the training on the large-scale Internet image-text pairs. However, despite the amazing achievement from the VLMs, vanilla Vision Transformers (ViTs) remain the default choice for the image encoder. Although pure transformer proves its effectiveness in the text encoding area, it remains questionable whether it is also the case for image encoding, especially considering tha"},"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":"2404.02132","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T17:40:29Z","cross_cats_sorted":[],"title_canon_sha256":"7f84bdaf322ce90011b212a2cd3a29ec0d7f517ced40c8bdadeddea4f5940a64","abstract_canon_sha256":"b58a1183228bddb673a24dd0a5cc7abcb3ebb3d6ad82e9f6d2106b16b65558f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:19.919206Z","signature_b64":"mbaPwitnvyhN9Ddplk0LZ5Sq+ZjA1Q6NOfqBgNz6xu/gFtBYH5MOQHay6sVTrXFmT029XCJT493y56Uam7mOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac148e4e24e97742126555bf1c49f5c2da92fa008240a72aae38bca4be782733","last_reissued_at":"2026-07-05T08:04:19.918749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:19.918749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViTamin: Designing Scalable Vision Models in the Vision-Language Era","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Jieneng Chen, Liang-Chieh Chen, Qihang Yu, Xiaohui Shen","submitted_at":"2024-04-02T17:40:29Z","abstract_excerpt":"Recent breakthroughs in vision-language models (VLMs) start a new page in the vision community. The VLMs provide stronger and more generalizable feature embeddings compared to those from ImageNet-pretrained models, thanks to the training on the large-scale Internet image-text pairs. However, despite the amazing achievement from the VLMs, vanilla Vision Transformers (ViTs) remain the default choice for the image encoder. Although pure transformer proves its effectiveness in the text encoding area, it remains questionable whether it is also the case for image encoding, especially considering tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02132","kind":"arxiv","version":2},"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/2404.02132/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":"2404.02132","created_at":"2026-07-05T08:04:19.918803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02132v2","created_at":"2026-07-05T08:04:19.918803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02132","created_at":"2026-07-05T08:04:19.918803+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQKI4TRE5F3U","created_at":"2026-07-05T08:04:19.918803+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQKI4TRE5F3UEETF","created_at":"2026-07-05T08:04:19.918803+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQKI4TRE","created_at":"2026-07-05T08:04:19.918803+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/VQKI4TRE5F3UEETFKW7RYSPVYL","json":"https://pith.science/pith/VQKI4TRE5F3UEETFKW7RYSPVYL.json","graph_json":"https://pith.science/api/pith-number/VQKI4TRE5F3UEETFKW7RYSPVYL/graph.json","events_json":"https://pith.science/api/pith-number/VQKI4TRE5F3UEETFKW7RYSPVYL/events.json","paper":"https://pith.science/paper/VQKI4TRE"},"agent_actions":{"view_html":"https://pith.science/pith/VQKI4TRE5F3UEETFKW7RYSPVYL","download_json":"https://pith.science/pith/VQKI4TRE5F3UEETFKW7RYSPVYL.json","view_paper":"https://pith.science/paper/VQKI4TRE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02132&json=true","fetch_graph":"https://pith.science/api/pith-number/VQKI4TRE5F3UEETFKW7RYSPVYL/graph.json","fetch_events":"https://pith.science/api/pith-number/VQKI4TRE5F3UEETFKW7RYSPVYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQKI4TRE5F3UEETFKW7RYSPVYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQKI4TRE5F3UEETFKW7RYSPVYL/action/storage_attestation","attest_author":"https://pith.science/pith/VQKI4TRE5F3UEETFKW7RYSPVYL/action/author_attestation","sign_citation":"https://pith.science/pith/VQKI4TRE5F3UEETFKW7RYSPVYL/action/citation_signature","submit_replication":"https://pith.science/pith/VQKI4TRE5F3UEETFKW7RYSPVYL/action/replication_record"}},"created_at":"2026-07-05T08:04:19.918803+00:00","updated_at":"2026-07-05T08:04:19.918803+00:00"}