{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MTBGRQZLUFYWPFJWIPB36N2TDW","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":"401c35af612204e1adfe29d517abb2967c21a4632ec9ef4d7df4ceaffd42f4d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-17T11:03:02Z","title_canon_sha256":"a4d034a2729a7af223f0994b9c4fc173824139c687970797d36302415a7f3347"},"schema_version":"1.0","source":{"id":"2402.11248","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11248","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11248v4","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11248","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"pith_short_12","alias_value":"MTBGRQZLUFYW","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"pith_short_16","alias_value":"MTBGRQZLUFYWPFJW","created_at":"2026-07-05T08:26:19Z"},{"alias_kind":"pith_short_8","alias_value":"MTBGRQZL","created_at":"2026-07-05T08:26:19Z"}],"graph_snapshots":[{"event_id":"sha256:5d63a60817928f5e8fc278437f6fa2e458e9c6ffc57ff6df8d47cd269925b6a1","target":"graph","created_at":"2026-07-05T08:26:19Z","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/2402.11248/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The remarkable success of Large Language Models (LLMs) and instruction tuning drives the evolution of Vision Language Models (VLMs) towards a versatile general-purpose model. Yet, it remains unexplored whether current VLMs genuinely possess quality object-level image understanding capabilities determined from 'what objects are in the image?' or 'which object corresponds to a specified bounding box?'. Our findings reveal that the image understanding capabilities of current VLMs are strongly correlated with their zero-shot performance on vision language (VL) tasks. This suggests that prioritizin","authors_text":"Beomchan Park, Byung-Kwan Lee, Chae Won Kim, Yong Man Ro","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-17T11:03:02Z","title":"CoLLaVO: Crayon Large Language and Vision mOdel"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11248","kind":"arxiv","version":4},"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:aa6f169a0dc0c76de26c5ab5247a3e191fa0021c4153b2b2e852e012d5274b23","target":"record","created_at":"2026-07-05T08:26:19Z","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":"401c35af612204e1adfe29d517abb2967c21a4632ec9ef4d7df4ceaffd42f4d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-17T11:03:02Z","title_canon_sha256":"a4d034a2729a7af223f0994b9c4fc173824139c687970797d36302415a7f3347"},"schema_version":"1.0","source":{"id":"2402.11248","kind":"arxiv","version":4}},"canonical_sha256":"64c268c32ba17167953643c3bf37531d87f51bd0d7b6433fd5093038bddc5f70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64c268c32ba17167953643c3bf37531d87f51bd0d7b6433fd5093038bddc5f70","first_computed_at":"2026-07-05T08:26:19.869110Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:19.869110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+OgzFnYO+Euj9dzvBlIM+OcJji7UOb1RQrySAnIvahuCnakrV1a5BJXBq2IOpTaroMHGnyYXXbr4tAojmTI1Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:19.869592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11248","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa6f169a0dc0c76de26c5ab5247a3e191fa0021c4153b2b2e852e012d5274b23","sha256:5d63a60817928f5e8fc278437f6fa2e458e9c6ffc57ff6df8d47cd269925b6a1"],"state_sha256":"e712452070d0b8e778c00ecd8b6de2f03dd76bcec523a6da71a1c62acb1f9fa0"}