{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:K7VE3ENFJDTPGKGLMO6UCJGTC2","short_pith_number":"pith:K7VE3ENF","schema_version":"1.0","canonical_sha256":"57ea4d91a548e6f328cb63bd4124d316b1e14287157106df488ab3455d53a4ae","source":{"kind":"arxiv","id":"2402.07865","version":2},"attestation_state":"computed","paper":{"title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ashwin Balakrishna, Dorsa Sadigh, Percy Liang, Siddharth Karamcheti, Suraj Nair, Thomas Kollar","submitted_at":"2024-02-12T18:21:14Z","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"},"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":"2402.07865","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-12T18:21:14Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"473d58a7dd8750113f8e0432dedb05ca4e92151b5f05c448772edd38cb0aae89","abstract_canon_sha256":"05c9d1672d1ecc18b8d5422bb5288ca6150a3c0938b12f197b630b2628cffbf9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:00.498962Z","signature_b64":"q5mcy3YHC3MYUoGECuDBu6AiFMHxP13TBlrml5OXl41rRY3KzAkSTWMfOt9otD9Q3iYmwIW1z+HlmkSZ1A3kBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57ea4d91a548e6f328cb63bd4124d316b1e14287157106df488ab3455d53a4ae","last_reissued_at":"2026-07-05T08:25:00.498500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:00.498500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ashwin Balakrishna, Dorsa Sadigh, Percy Liang, Siddharth Karamcheti, Suraj Nair, Thomas Kollar","submitted_at":"2024-02-12T18:21:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07865","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/2402.07865/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":"2402.07865","created_at":"2026-07-05T08:25:00.498556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07865v2","created_at":"2026-07-05T08:25:00.498556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07865","created_at":"2026-07-05T08:25:00.498556+00:00"},{"alias_kind":"pith_short_12","alias_value":"K7VE3ENFJDTP","created_at":"2026-07-05T08:25:00.498556+00:00"},{"alias_kind":"pith_short_16","alias_value":"K7VE3ENFJDTPGKGL","created_at":"2026-07-05T08:25:00.498556+00:00"},{"alias_kind":"pith_short_8","alias_value":"K7VE3ENF","created_at":"2026-07-05T08:25:00.498556+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08448","citing_title":"Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21139","citing_title":"PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03392","citing_title":"OpenEAI-Platform: An Open-source Embodied Artificial Intelligence Hardware-Software Unified Platform","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03879","citing_title":"Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29247","citing_title":"SurgVLA-Bench: Towards Evaluating Vision-Language-Action Models for Laparoscopic Surgical Robotics","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17486","citing_title":"DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2505.03233","citing_title":"GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2511.17411","citing_title":"SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14164","citing_title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","ref_index":202,"is_internal_anchor":false},{"citing_arxiv_id":"2406.16860","citing_title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04447","citing_title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2503.22020","citing_title":"CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2503.10631","citing_title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2412.03555","citing_title":"PaliGemma 2: A Family of Versatile VLMs for Transfer","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2409.17146","citing_title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28192","citing_title":"LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2411.19650","citing_title":"CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28192","citing_title":"LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24380","citing_title":"Structural Pruning of Large Vision Language Models: A Comprehensive Study on Pruning Dynamics, Recovery, and Data Efficiency","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2407.07726","citing_title":"PaliGemma: A versatile 3B VLM for transfer","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2502.19645","citing_title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2406.09246","citing_title":"OpenVLA: An Open-Source Vision-Language-Action Model","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K7VE3ENFJDTPGKGLMO6UCJGTC2","json":"https://pith.science/pith/K7VE3ENFJDTPGKGLMO6UCJGTC2.json","graph_json":"https://pith.science/api/pith-number/K7VE3ENFJDTPGKGLMO6UCJGTC2/graph.json","events_json":"https://pith.science/api/pith-number/K7VE3ENFJDTPGKGLMO6UCJGTC2/events.json","paper":"https://pith.science/paper/K7VE3ENF"},"agent_actions":{"view_html":"https://pith.science/pith/K7VE3ENFJDTPGKGLMO6UCJGTC2","download_json":"https://pith.science/pith/K7VE3ENFJDTPGKGLMO6UCJGTC2.json","view_paper":"https://pith.science/paper/K7VE3ENF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07865&json=true","fetch_graph":"https://pith.science/api/pith-number/K7VE3ENFJDTPGKGLMO6UCJGTC2/graph.json","fetch_events":"https://pith.science/api/pith-number/K7VE3ENFJDTPGKGLMO6UCJGTC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K7VE3ENFJDTPGKGLMO6UCJGTC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K7VE3ENFJDTPGKGLMO6UCJGTC2/action/storage_attestation","attest_author":"https://pith.science/pith/K7VE3ENFJDTPGKGLMO6UCJGTC2/action/author_attestation","sign_citation":"https://pith.science/pith/K7VE3ENFJDTPGKGLMO6UCJGTC2/action/citation_signature","submit_replication":"https://pith.science/pith/K7VE3ENFJDTPGKGLMO6UCJGTC2/action/replication_record"}},"created_at":"2026-07-05T08:25:00.498556+00:00","updated_at":"2026-07-05T08:25:00.498556+00:00"}