{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YMRDBEDMMNCEHDMYHLB2AXLRXY","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":"b9fe87f797d685fdcad77dd4f6d8ced98e5d83468de301632e28f0f98bc75239","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T17:30:46Z","title_canon_sha256":"2567e7dedbef3a20c7e8bac2b28ec009be7db053543f68c9887658072614d6bb"},"schema_version":"1.0","source":{"id":"2309.09958","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.09958","created_at":"2026-07-05T06:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"2309.09958v1","created_at":"2026-07-05T06:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09958","created_at":"2026-07-05T06:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"YMRDBEDMMNCE","created_at":"2026-07-05T06:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"YMRDBEDMMNCEHDMY","created_at":"2026-07-05T06:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"YMRDBEDM","created_at":"2026-07-05T06:51:47Z"}],"graph_snapshots":[{"event_id":"sha256:ae68be38b097e966b6df724cbea0669264b5494859dda4344559363e45518b1a","target":"graph","created_at":"2026-07-05T06:51:47Z","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/2309.09958/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual instruction tuning has recently shown encouraging progress with open-source large multimodal models (LMM) such as LLaVA and MiniGPT-4. However, most existing studies of open-source LMM are performed using models with 13B parameters or smaller. In this paper we present an empirical study of scaling LLaVA up to 33B and 65B/70B, and share our findings from our explorations in image resolution, data mixing and parameter-efficient training methods such as LoRA/QLoRA. These are evaluated by their impact on the multi-modal and language capabilities when completing real-world tasks in the wild.","authors_text":"Chunyuan Li, Haotian Liu, Jianfeng Gao, Jianwei Yang, Yadong Lu, Yelong Shen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T17:30:46Z","title":"An Empirical Study of Scaling Instruct-Tuned Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09958","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:c0246e1b2c72d7114381919be12ecd9541bff1ced8603528abe41adafb7225f3","target":"record","created_at":"2026-07-05T06:51:47Z","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":"b9fe87f797d685fdcad77dd4f6d8ced98e5d83468de301632e28f0f98bc75239","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-18T17:30:46Z","title_canon_sha256":"2567e7dedbef3a20c7e8bac2b28ec009be7db053543f68c9887658072614d6bb"},"schema_version":"1.0","source":{"id":"2309.09958","kind":"arxiv","version":1}},"canonical_sha256":"c32230906c6344438d983ac3a05d71be0f2e2ad22fa5cc72c108aac40a86e30a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c32230906c6344438d983ac3a05d71be0f2e2ad22fa5cc72c108aac40a86e30a","first_computed_at":"2026-07-05T06:51:47.144925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:47.144925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"70q/xT12SyQD+6cEM2JgEll69YzHfrHHcLoDRERH8r0mWlK7NvkM8vw/FbWJLAtqsspiFBxYhCJPILS+hoPpBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:47.145438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.09958","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0246e1b2c72d7114381919be12ecd9541bff1ced8603528abe41adafb7225f3","sha256:ae68be38b097e966b6df724cbea0669264b5494859dda4344559363e45518b1a"],"state_sha256":"4b9f1959afd004be43273da162e4eb287047e4ef91329988f69b00536b597fec"}