{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K7VE3ENFJDTPGKGLMO6UCJGTC2","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":"05c9d1672d1ecc18b8d5422bb5288ca6150a3c0938b12f197b630b2628cffbf9","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-12T18:21:14Z","title_canon_sha256":"473d58a7dd8750113f8e0432dedb05ca4e92151b5f05c448772edd38cb0aae89"},"schema_version":"1.0","source":{"id":"2402.07865","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07865","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07865v2","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07865","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"pith_short_12","alias_value":"K7VE3ENFJDTP","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"pith_short_16","alias_value":"K7VE3ENFJDTPGKGL","created_at":"2026-07-05T08:25:00Z"},{"alias_kind":"pith_short_8","alias_value":"K7VE3ENF","created_at":"2026-07-05T08:25:00Z"}],"graph_snapshots":[{"event_id":"sha256:75d96e1fe6697f029dd80e6e1c1e6a76d037cb2a38108591baf08a3a9a878054","target":"graph","created_at":"2026-07-05T08:25:00Z","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/2402.07865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visually-conditioned language models (VLMs) have seen growing adoption in applications such as visual dialogue, scene understanding, and robotic task planning; adoption that has fueled a wealth of new models such as LLaVa, InstructBLIP, and PaLI-3. Despite the volume of new releases, key design decisions around image preprocessing, architecture, and optimization are under-explored, making it challenging to understand what factors account for model performance $-$ a challenge further complicated by the lack of objective, consistent evaluations. To address these gaps, we first compile a suite of","authors_text":"Ashwin Balakrishna, Dorsa Sadigh, Percy Liang, Siddharth Karamcheti, Suraj Nair, Thomas Kollar","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-12T18:21:14Z","title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07865","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":"sha256:4ec2fb7829394f989a43701d75e8a4e11b79da682a801b138bb1725c3646cf6f","target":"record","created_at":"2026-07-05T08:25:00Z","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":"05c9d1672d1ecc18b8d5422bb5288ca6150a3c0938b12f197b630b2628cffbf9","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-12T18:21:14Z","title_canon_sha256":"473d58a7dd8750113f8e0432dedb05ca4e92151b5f05c448772edd38cb0aae89"},"schema_version":"1.0","source":{"id":"2402.07865","kind":"arxiv","version":2}},"canonical_sha256":"57ea4d91a548e6f328cb63bd4124d316b1e14287157106df488ab3455d53a4ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57ea4d91a548e6f328cb63bd4124d316b1e14287157106df488ab3455d53a4ae","first_computed_at":"2026-07-05T08:25:00.498500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:00.498500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q5mcy3YHC3MYUoGECuDBu6AiFMHxP13TBlrml5OXl41rRY3KzAkSTWMfOt9otD9Q3iYmwIW1z+HlmkSZ1A3kBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:00.498962Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07865","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ec2fb7829394f989a43701d75e8a4e11b79da682a801b138bb1725c3646cf6f","sha256:75d96e1fe6697f029dd80e6e1c1e6a76d037cb2a38108591baf08a3a9a878054"],"state_sha256":"cc88cdf7a9a4067ad2795b19f89a753229e1e2350d49ec37b3a072be8153cb42"}