{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WISWEJMM6CPKXUJCMYXFZ7PZPZ","short_pith_number":"pith:WISWEJMM","schema_version":"1.0","canonical_sha256":"b22562258cf09eabd122662e5cfdf97e42fdc230e3080152a92a8d24c7737cac","source":{"kind":"arxiv","id":"2405.11850","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Overlooked Aspects in Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Le Tian, Xiao Zhou, Yuan Liu","submitted_at":"2024-05-20T07:53:41Z","abstract_excerpt":"Recent advancements in large vision-language models (LVLMs), such as GPT4-V and LLaVA, have been substantial. LLaVA's modular architecture, in particular, offers a blend of simplicity and efficiency. Recent works mainly focus on introducing more pre-training and instruction tuning data to improve model's performance. This paper delves into the often-neglected aspects of data efficiency during pre-training and the selection process for instruction tuning datasets. Our research indicates that merely increasing the size of pre-training data does not guarantee improved performance and may, in fact"},"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":"2405.11850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T07:53:41Z","cross_cats_sorted":[],"title_canon_sha256":"80fbb29128f5a665c323c0c51c7eae14cbf2191ddbd47ddef4659d375fb884dd","abstract_canon_sha256":"026aa67f8cd3dc00fa4e0ace2f9e12635d11abe23e9310b6ab67900c35caaeff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:56.860200Z","signature_b64":"20pvSY738g9zQTXmqDKTdPRpvX5on/4nDSp7rMQAWN3hz+Qf9biDbLCtNvPqbrOxY9QQq6gH9T+JBJGFs0FKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b22562258cf09eabd122662e5cfdf97e42fdc230e3080152a92a8d24c7737cac","last_reissued_at":"2026-07-05T08:20:56.859766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:56.859766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Overlooked Aspects in Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Le Tian, Xiao Zhou, Yuan Liu","submitted_at":"2024-05-20T07:53:41Z","abstract_excerpt":"Recent advancements in large vision-language models (LVLMs), such as GPT4-V and LLaVA, have been substantial. LLaVA's modular architecture, in particular, offers a blend of simplicity and efficiency. Recent works mainly focus on introducing more pre-training and instruction tuning data to improve model's performance. This paper delves into the often-neglected aspects of data efficiency during pre-training and the selection process for instruction tuning datasets. Our research indicates that merely increasing the size of pre-training data does not guarantee improved performance and may, in fact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11850","kind":"arxiv","version":1},"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/2405.11850/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":"2405.11850","created_at":"2026-07-05T08:20:56.859829+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11850v1","created_at":"2026-07-05T08:20:56.859829+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11850","created_at":"2026-07-05T08:20:56.859829+00:00"},{"alias_kind":"pith_short_12","alias_value":"WISWEJMM6CPK","created_at":"2026-07-05T08:20:56.859829+00:00"},{"alias_kind":"pith_short_16","alias_value":"WISWEJMM6CPKXUJC","created_at":"2026-07-05T08:20:56.859829+00:00"},{"alias_kind":"pith_short_8","alias_value":"WISWEJMM","created_at":"2026-07-05T08:20:56.859829+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.08443","citing_title":"POINTS1.5: Building a Vision-Language Model towards Real World Applications","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ","json":"https://pith.science/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ.json","graph_json":"https://pith.science/api/pith-number/WISWEJMM6CPKXUJCMYXFZ7PZPZ/graph.json","events_json":"https://pith.science/api/pith-number/WISWEJMM6CPKXUJCMYXFZ7PZPZ/events.json","paper":"https://pith.science/paper/WISWEJMM"},"agent_actions":{"view_html":"https://pith.science/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ","download_json":"https://pith.science/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ.json","view_paper":"https://pith.science/paper/WISWEJMM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11850&json=true","fetch_graph":"https://pith.science/api/pith-number/WISWEJMM6CPKXUJCMYXFZ7PZPZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WISWEJMM6CPKXUJCMYXFZ7PZPZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ/action/storage_attestation","attest_author":"https://pith.science/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ/action/author_attestation","sign_citation":"https://pith.science/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ/action/citation_signature","submit_replication":"https://pith.science/pith/WISWEJMM6CPKXUJCMYXFZ7PZPZ/action/replication_record"}},"created_at":"2026-07-05T08:20:56.859829+00:00","updated_at":"2026-07-05T08:20:56.859829+00:00"}