{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MTBGRQZLUFYWPFJWIPB36N2TDW","short_pith_number":"pith:MTBGRQZL","schema_version":"1.0","canonical_sha256":"64c268c32ba17167953643c3bf37531d87f51bd0d7b6433fd5093038bddc5f70","source":{"kind":"arxiv","id":"2402.11248","version":4},"attestation_state":"computed","paper":{"title":"CoLLaVO: Crayon Large Language and Vision mOdel","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beomchan Park, Byung-Kwan Lee, Chae Won Kim, Yong Man Ro","submitted_at":"2024-02-17T11:03:02Z","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"},"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":"2402.11248","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-17T11:03:02Z","cross_cats_sorted":[],"title_canon_sha256":"a4d034a2729a7af223f0994b9c4fc173824139c687970797d36302415a7f3347","abstract_canon_sha256":"401c35af612204e1adfe29d517abb2967c21a4632ec9ef4d7df4ceaffd42f4d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:19.869592Z","signature_b64":"+OgzFnYO+Euj9dzvBlIM+OcJji7UOb1RQrySAnIvahuCnakrV1a5BJXBq2IOpTaroMHGnyYXXbr4tAojmTI1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64c268c32ba17167953643c3bf37531d87f51bd0d7b6433fd5093038bddc5f70","last_reissued_at":"2026-07-05T08:26:19.869110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:19.869110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoLLaVO: Crayon Large Language and Vision mOdel","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beomchan Park, Byung-Kwan Lee, Chae Won Kim, Yong Man Ro","submitted_at":"2024-02-17T11:03:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11248","kind":"arxiv","version":4},"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/2402.11248/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":"2402.11248","created_at":"2026-07-05T08:26:19.869169+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11248v4","created_at":"2026-07-05T08:26:19.869169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11248","created_at":"2026-07-05T08:26:19.869169+00:00"},{"alias_kind":"pith_short_12","alias_value":"MTBGRQZLUFYW","created_at":"2026-07-05T08:26:19.869169+00:00"},{"alias_kind":"pith_short_16","alias_value":"MTBGRQZLUFYWPFJW","created_at":"2026-07-05T08:26:19.869169+00:00"},{"alias_kind":"pith_short_8","alias_value":"MTBGRQZL","created_at":"2026-07-05T08:26:19.869169+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25886","citing_title":"MarkIt: Training-Free Visual Markers for Precise Video Temporal Grounding","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25886","citing_title":"MarkIt: Training-Free Visual Markers for Precise Video Temporal Grounding","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MTBGRQZLUFYWPFJWIPB36N2TDW","json":"https://pith.science/pith/MTBGRQZLUFYWPFJWIPB36N2TDW.json","graph_json":"https://pith.science/api/pith-number/MTBGRQZLUFYWPFJWIPB36N2TDW/graph.json","events_json":"https://pith.science/api/pith-number/MTBGRQZLUFYWPFJWIPB36N2TDW/events.json","paper":"https://pith.science/paper/MTBGRQZL"},"agent_actions":{"view_html":"https://pith.science/pith/MTBGRQZLUFYWPFJWIPB36N2TDW","download_json":"https://pith.science/pith/MTBGRQZLUFYWPFJWIPB36N2TDW.json","view_paper":"https://pith.science/paper/MTBGRQZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11248&json=true","fetch_graph":"https://pith.science/api/pith-number/MTBGRQZLUFYWPFJWIPB36N2TDW/graph.json","fetch_events":"https://pith.science/api/pith-number/MTBGRQZLUFYWPFJWIPB36N2TDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MTBGRQZLUFYWPFJWIPB36N2TDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MTBGRQZLUFYWPFJWIPB36N2TDW/action/storage_attestation","attest_author":"https://pith.science/pith/MTBGRQZLUFYWPFJWIPB36N2TDW/action/author_attestation","sign_citation":"https://pith.science/pith/MTBGRQZLUFYWPFJWIPB36N2TDW/action/citation_signature","submit_replication":"https://pith.science/pith/MTBGRQZLUFYWPFJWIPB36N2TDW/action/replication_record"}},"created_at":"2026-07-05T08:26:19.869169+00:00","updated_at":"2026-07-05T08:26:19.869169+00:00"}