{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ONHBQAABWPFC4TBGYXZ4BOS3FZ","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":"e0dc0a1ee166e404aab9294b7e02ec7549bdcb27824d6adaba3d17eefb767817","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-22T17:47:24Z","title_canon_sha256":"e201cedace8d47459abe3112ecf76917b2f929fb08c4ec934374491fd4921e2f"},"schema_version":"1.0","source":{"id":"2408.12637","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.12637","created_at":"2026-07-05T08:58:27Z"},{"alias_kind":"arxiv_version","alias_value":"2408.12637v1","created_at":"2026-07-05T08:58:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12637","created_at":"2026-07-05T08:58:27Z"},{"alias_kind":"pith_short_12","alias_value":"ONHBQAABWPFC","created_at":"2026-07-05T08:58:27Z"},{"alias_kind":"pith_short_16","alias_value":"ONHBQAABWPFC4TBG","created_at":"2026-07-05T08:58:27Z"},{"alias_kind":"pith_short_8","alias_value":"ONHBQAAB","created_at":"2026-07-05T08:58:27Z"}],"graph_snapshots":[{"event_id":"sha256:bf22d2a9738ea4bd308b7caa069a1e4066e072b67d96a7b880a5f7e23acdb581","target":"graph","created_at":"2026-07-05T08:58:27Z","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/2408.12637/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The field of vision-language models (VLMs), which take images and texts as inputs and output texts, is rapidly evolving and has yet to reach consensus on several key aspects of the development pipeline, including data, architecture, and training methods. This paper can be seen as a tutorial for building a VLM. We begin by providing a comprehensive overview of the current state-of-the-art approaches, highlighting the strengths and weaknesses of each, addressing the major challenges in the field, and suggesting promising research directions for underexplored areas. We then walk through the pract","authors_text":"Andr\\'es Marafioti, Hugo Lauren\\c{c}on, L\\'eo Tronchon, Victor Sanh","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-22T17:47:24Z","title":"Building and better understanding vision-language models: insights and future directions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12637","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:d1e3e395319fd7f8a901e50ef1157fde845b25f1ca67018933bb87440523ea77","target":"record","created_at":"2026-07-05T08:58:27Z","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":"e0dc0a1ee166e404aab9294b7e02ec7549bdcb27824d6adaba3d17eefb767817","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-22T17:47:24Z","title_canon_sha256":"e201cedace8d47459abe3112ecf76917b2f929fb08c4ec934374491fd4921e2f"},"schema_version":"1.0","source":{"id":"2408.12637","kind":"arxiv","version":1}},"canonical_sha256":"734e180001b3ca2e4c26c5f3c0ba5b2e441fdc35706399dc056a127c6d52b3cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"734e180001b3ca2e4c26c5f3c0ba5b2e441fdc35706399dc056a127c6d52b3cd","first_computed_at":"2026-07-05T08:58:27.702117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:58:27.702117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b81TWq2dIivQ6lbUB5/yCGAUhySMrSZuuZFPahdalQtSfYktv+vMM5pmHRHujKrlZ9L9V+GHMSams0J6c3M5BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:58:27.702635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.12637","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1e3e395319fd7f8a901e50ef1157fde845b25f1ca67018933bb87440523ea77","sha256:bf22d2a9738ea4bd308b7caa069a1e4066e072b67d96a7b880a5f7e23acdb581"],"state_sha256":"eb0c177109ef6c74dce748ca9feb536110804a2ea075c8da19efd9b8b0f8edc4"}