{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y6RQ3DSEO5GRVDQUIZPKY2FERD","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":"e606524b7628f142fb6b777e632ce4b174a53d3a5b787f99489108f1eefefe8a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T15:01:23Z","title_canon_sha256":"b1c86ce28c9c76844e22aeede00264b2a1acb768f895f524fb633a563026fe13"},"schema_version":"1.0","source":{"id":"2405.17247","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17247","created_at":"2026-07-05T08:23:41Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17247v1","created_at":"2026-07-05T08:23:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17247","created_at":"2026-07-05T08:23:41Z"},{"alias_kind":"pith_short_12","alias_value":"Y6RQ3DSEO5GR","created_at":"2026-07-05T08:23:41Z"},{"alias_kind":"pith_short_16","alias_value":"Y6RQ3DSEO5GRVDQU","created_at":"2026-07-05T08:23:41Z"},{"alias_kind":"pith_short_8","alias_value":"Y6RQ3DSE","created_at":"2026-07-05T08:23:41Z"}],"graph_snapshots":[{"event_id":"sha256:c03d9f697ea35acb650ec03819d2495fa386d7dc2f133b66e1d472debbc4d0ec","target":"graph","created_at":"2026-07-05T08:23:41Z","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/2405.17247/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Following the recent popularity of Large Language Models (LLMs), several attempts have been made to extend them to the visual domain. From having a visual assistant that could guide us through unfamiliar environments to generative models that produce images using only a high-level text description, the vision-language model (VLM) applications will significantly impact our relationship with technology. However, there are many challenges that need to be addressed to improve the reliability of those models. While language is discrete, vision evolves in a much higher dimensional space in which con","authors_text":"Adrien Bardes, Aishwarya Agrawal, Alexander C. Li, Anas Mahmoud, Anurag Ajay, Arjang Talattof, Asli Celikyilmaz, Bargav Jayaraman, Candace Ross, Chuan Guo, Diane Bouchacourt, Florian Bordes, Haider Al-Tahan, Hu Xu, Jonathan Lebensold, Jun Chen, Kamalika Chaudhuri, Karen Ullrich, Karthik Padthe, Kate Saenko, Kushal Tirumala, Mark Ibrahim, Mazda Moayeri, Megan Richards, Melissa Hall, Oscar Ma\\~nas, Pietro Astolfi, Quentin Garrido, Reyhane Askari Hemmat, Richard Yuanzhe Pang, Rim Assouel, Samuel Lavoie, Srihari Jayakumar, Suzanne Petryk, Vasu Sharma, Vikas Chandra, Xiaoqing Ellen Tan, Xilun Chen, Yunyang Xiong, Zechun Liu, Zhiqiu Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T15:01:23Z","title":"An Introduction to Vision-Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17247","kind":"arxiv","version":1},"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":"sha256:2b3e1145a6adb621ab0b718807ab229194f9a7321f9d04b98557ed1382fb59d7","target":"record","created_at":"2026-07-05T08:23:41Z","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":"e606524b7628f142fb6b777e632ce4b174a53d3a5b787f99489108f1eefefe8a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-27T15:01:23Z","title_canon_sha256":"b1c86ce28c9c76844e22aeede00264b2a1acb768f895f524fb633a563026fe13"},"schema_version":"1.0","source":{"id":"2405.17247","kind":"arxiv","version":1}},"canonical_sha256":"c7a30d8e44774d1a8e14465eac68a488ffa391f8085a09122c8f05c2dfdd2daf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7a30d8e44774d1a8e14465eac68a488ffa391f8085a09122c8f05c2dfdd2daf","first_computed_at":"2026-07-05T08:23:41.938664Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:41.938664Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q0UXTjtBdgDUIfH0g9+XjIVODzq9E9syKFs1zjhWbUQi9sc6eSTvDlwGk+HLs1qGs9vnUFIYJ5Mfdti/bMQVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:41.939163Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17247","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b3e1145a6adb621ab0b718807ab229194f9a7321f9d04b98557ed1382fb59d7","sha256:c03d9f697ea35acb650ec03819d2495fa386d7dc2f133b66e1d472debbc4d0ec"],"state_sha256":"eadbb834939515552729892350ab8ccf14378edf8760db4393d544614e7cfca3"}