{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q4FTJ4M2KHZUSXK3CO7W43DUJW","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":"ebb6b6093c9ba83527174263c54670944e8ada73b2e95c0ac1fd57010b0c808f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T20:09:55Z","title_canon_sha256":"34545dd496aab646fb487441ba9e478cad614275def6fab5c937f6a93014dda3"},"schema_version":"1.0","source":{"id":"2412.13303","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13303","created_at":"2026-07-05T11:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13303v2","created_at":"2026-07-05T11:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13303","created_at":"2026-07-05T11:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"Q4FTJ4M2KHZU","created_at":"2026-07-05T11:03:54Z"},{"alias_kind":"pith_short_16","alias_value":"Q4FTJ4M2KHZUSXK3","created_at":"2026-07-05T11:03:54Z"},{"alias_kind":"pith_short_8","alias_value":"Q4FTJ4M2","created_at":"2026-07-05T11:03:54Z"}],"graph_snapshots":[{"event_id":"sha256:d4284d93760d21df79a8e0a187cf37831a584503153d014cf5524496f1bd4af4","target":"graph","created_at":"2026-07-05T11:03:54Z","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/2412.13303/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling the input image resolution is essential for enhancing the performance of Vision Language Models (VLMs), particularly in text-rich image understanding tasks. However, popular visual encoders such as ViTs become inefficient at high resolutions due to the large number of tokens and high encoding latency caused by stacked self-attention layers. At different operational resolutions, the vision encoder of a VLM can be optimized along two axes: reducing encoding latency and minimizing the number of visual tokens passed to the LLM, thereby lowering overall latency. Based on a comprehensive eff","authors_text":"Albert Antony, Cem Koc, Chun-Liang Li, Fartash Faghri, Gokul Santhanam, Hadi Pouransari, James Gabriel, Nate True, Oncel Tuzel, Pavan Kumar Anasosalu Vasu, Peter Grasch","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T20:09:55Z","title":"FastVLM: Efficient Vision Encoding for Vision Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13303","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:e151367e1bbc2ca7b65d67087a2fc655c7bd8541a1a1ec3288355dc0e46efbc0","target":"record","created_at":"2026-07-05T11:03:54Z","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":"ebb6b6093c9ba83527174263c54670944e8ada73b2e95c0ac1fd57010b0c808f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T20:09:55Z","title_canon_sha256":"34545dd496aab646fb487441ba9e478cad614275def6fab5c937f6a93014dda3"},"schema_version":"1.0","source":{"id":"2412.13303","kind":"arxiv","version":2}},"canonical_sha256":"870b34f19a51f3495d5b13bf6e6c744dade9fb2a02ad5ae07cd1a7cfd4bad8fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"870b34f19a51f3495d5b13bf6e6c744dade9fb2a02ad5ae07cd1a7cfd4bad8fe","first_computed_at":"2026-07-05T11:03:54.909288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:54.909288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WGVqiyLNSIbIRuYY4QXX1w/9WXtVvFS+IykJy9UvSVVHban9N7RVtQpk7XhkVUDRLHAsl/KV8QpZbrR7vEabDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:54.909860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13303","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e151367e1bbc2ca7b65d67087a2fc655c7bd8541a1a1ec3288355dc0e46efbc0","sha256:d4284d93760d21df79a8e0a187cf37831a584503153d014cf5524496f1bd4af4"],"state_sha256":"9914e3032db36a4d2f5d53fc1d06ef44a7b9fe0af242402be19b6e4a5c494903"}