{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:355AJ4ZNHNWAWT7ZZTUK3WCJB4","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":"3bcd4766c78a6fd16e3c3a5c4e3ea669d3c34aa06dbc15ce793491ee82b7e54a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T17:58:57Z","title_canon_sha256":"d281dae08aa4969be657e8a3ff770cd8f3c4032d204b69c776f27511ffd01e09"},"schema_version":"1.0","source":{"id":"2503.15485","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15485","created_at":"2026-07-05T10:46:02Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15485v2","created_at":"2026-07-05T10:46:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15485","created_at":"2026-07-05T10:46:02Z"},{"alias_kind":"pith_short_12","alias_value":"355AJ4ZNHNWA","created_at":"2026-07-05T10:46:02Z"},{"alias_kind":"pith_short_16","alias_value":"355AJ4ZNHNWAWT7Z","created_at":"2026-07-05T10:46:02Z"},{"alias_kind":"pith_short_8","alias_value":"355AJ4ZN","created_at":"2026-07-05T10:46:02Z"}],"graph_snapshots":[{"event_id":"sha256:198fe1d9fbb034ef2492c6de94dd04fb2c619d915401cd484ebc1bf4cb44f9a7","target":"graph","created_at":"2026-07-05T10:46:02Z","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/2503.15485/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the recent success of image-text contrastive models like CLIP and SigLIP, these models often struggle with vision-centric tasks that demand high-fidelity image understanding, such as counting, depth estimation, and fine-grained object recognition. These models, by performing language alignment, tend to prioritize high-level semantics over visual understanding, weakening their image understanding. On the other hand, vision-focused models are great at processing visual information but struggle to understand language, limiting their flexibility for language-driven tasks. In this work, we ","authors_text":"Adam Yala, Alane Suhr, David M. Chan, Long Lian, Roei Herzig, Seun Eisape, Trevor Darrell, Xudong Wang, Zineng Tang","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T17:58:57Z","title":"TULIP: Towards Unified Language-Image Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15485","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:da7ce979b1d5437d31a66dc5247649eba992130f3fe06005ebce98d5db24aa76","target":"record","created_at":"2026-07-05T10:46:02Z","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":"3bcd4766c78a6fd16e3c3a5c4e3ea669d3c34aa06dbc15ce793491ee82b7e54a","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T17:58:57Z","title_canon_sha256":"d281dae08aa4969be657e8a3ff770cd8f3c4032d204b69c776f27511ffd01e09"},"schema_version":"1.0","source":{"id":"2503.15485","kind":"arxiv","version":2}},"canonical_sha256":"df7a04f32d3b6c0b4ff9cce8add8490f241ca83714e1634c2e7f689b32585394","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df7a04f32d3b6c0b4ff9cce8add8490f241ca83714e1634c2e7f689b32585394","first_computed_at":"2026-07-05T10:46:02.858847Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:46:02.858847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6LBsfTEFMTDqQWbCdAyPKorrgouLK8k+enVCGlXo2wJ0ydhOfNcgvL36MoHl51JXeMOOBEsRSOk1RFdUFcj3Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:46:02.859385Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15485","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da7ce979b1d5437d31a66dc5247649eba992130f3fe06005ebce98d5db24aa76","sha256:198fe1d9fbb034ef2492c6de94dd04fb2c619d915401cd484ebc1bf4cb44f9a7"],"state_sha256":"1cfb1e73ded3b89ba34a019c65f856377852870eb42be4a86ff8cab1ccec2bd0"}