{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DVMEE3ZAXOBQLFEHS6KRXUBJTC","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":"cfb7d6b97e406d8588e73373a5daa0dfd704dcfcd6c7f93161d8f1b266bc1e16","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-07T17:59:40Z","title_canon_sha256":"f73394151975a448c6347dbaae35632008ffe249d36db2c29a1d94abbce275f3"},"schema_version":"1.0","source":{"id":"2408.03940","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03940","created_at":"2026-07-05T08:53:13Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03940v1","created_at":"2026-07-05T08:53:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03940","created_at":"2026-07-05T08:53:13Z"},{"alias_kind":"pith_short_12","alias_value":"DVMEE3ZAXOBQ","created_at":"2026-07-05T08:53:13Z"},{"alias_kind":"pith_short_16","alias_value":"DVMEE3ZAXOBQLFEH","created_at":"2026-07-05T08:53:13Z"},{"alias_kind":"pith_short_8","alias_value":"DVMEE3ZA","created_at":"2026-07-05T08:53:13Z"}],"graph_snapshots":[{"event_id":"sha256:bb83c3e6b68fbc6028f8c9cc35374051420705fc9f9fe25488d40f03754d4ddb","target":"graph","created_at":"2026-07-05T08:53:13Z","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/2408.03940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model-based Vision-Language Models (LLM-based VLMs) have demonstrated impressive results in various vision-language understanding tasks. However, how well these VLMs can see image detail beyond the semantic level remains unclear. In our study, we introduce a pixel value prediction task (PVP) to explore \"How Well Can Vision Language Models See Image Details?\" and to assist VLMs in perceiving more details. Typically, these models comprise a frozen CLIP visual encoder, a large language model, and a connecting module. After fine-tuning VLMs on the PVP task, we find: 1) existing VLMs","authors_text":"Abdulwahab Felemban, Chenhui Gou, Deyao Zhu, Faizan Farooq Khan, Hamid Rezatofighi, Jianfei Cai, Mohamed Elhoseiny","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-07T17:59:40Z","title":"How Well Can Vision Language Models See Image Details?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03940","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":"sha256:1809fc9b6cd27895f338a3d2e2fa7a6c8d42ddd82515e859f3a6b114cb80a9fb","target":"record","created_at":"2026-07-05T08:53:13Z","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":"cfb7d6b97e406d8588e73373a5daa0dfd704dcfcd6c7f93161d8f1b266bc1e16","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-07T17:59:40Z","title_canon_sha256":"f73394151975a448c6347dbaae35632008ffe249d36db2c29a1d94abbce275f3"},"schema_version":"1.0","source":{"id":"2408.03940","kind":"arxiv","version":1}},"canonical_sha256":"1d58426f20bb8305948797951bd02998be8335aa5afefd30bd8a3ab1355f9377","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d58426f20bb8305948797951bd02998be8335aa5afefd30bd8a3ab1355f9377","first_computed_at":"2026-07-05T08:53:13.336761Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:13.336761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5QYWyVx09Jd6k9u62rc3NwMCBooZu5BXkzaN8Yk2LEt+aK0kKWeKsSHGV1h9kb+YF1SiVHCX0GUFNt+AOePTBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:13.337159Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.03940","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1809fc9b6cd27895f338a3d2e2fa7a6c8d42ddd82515e859f3a6b114cb80a9fb","sha256:bb83c3e6b68fbc6028f8c9cc35374051420705fc9f9fe25488d40f03754d4ddb"],"state_sha256":"2021d5ea13d85bb60fce8aa152b31643f88ff5aa7dacb9696f0f9796ffa91873"}