{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SSID7XFHTPXL72RAMN3E3FUST5","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":"0c6cb9fdc170a7050b7b8ec7bc3d6151e8dba42bc2c46b98ee10fa0faf928717","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T21:32:50Z","title_canon_sha256":"ece7926f4ba35072305a06afd828b7f004302787eec1b0bffa2756b2966a557b"},"schema_version":"1.0","source":{"id":"2404.01331","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01331","created_at":"2026-07-05T08:29:46Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01331v2","created_at":"2026-07-05T08:29:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01331","created_at":"2026-07-05T08:29:46Z"},{"alias_kind":"pith_short_12","alias_value":"SSID7XFHTPXL","created_at":"2026-07-05T08:29:46Z"},{"alias_kind":"pith_short_16","alias_value":"SSID7XFHTPXL72RA","created_at":"2026-07-05T08:29:46Z"},{"alias_kind":"pith_short_8","alias_value":"SSID7XFH","created_at":"2026-07-05T08:29:46Z"}],"graph_snapshots":[{"event_id":"sha256:67eeff208f46c6017ed6d12d831b2023fd8a20cf3699945f94cebed304319b61","target":"graph","created_at":"2026-07-05T08:29:46Z","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/2404.01331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We train a suite of multimodal foundation models (MMFM) using the popular LLaVA framework with the recently released Gemma family of large language models (LLMs). Of particular interest is the 2B parameter Gemma model, which provides opportunities to construct capable small-scale MMFMs. In line with findings from other papers in this space, we test the effect of ablating three design features: pretraining the connector, utilizing a more powerful image backbone, and increasing the size of the language backbone. The resulting models, which we call LLaVA-Gemma, exhibit moderate performance on an ","authors_text":"David Cobbley, Matthew L. Olson, Musashi Hinck, Shao-Yen Tseng, Vasudev Lal","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T21:32:50Z","title":"LLaVA-Gemma: Accelerating Multimodal Foundation Models with a Compact Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01331","kind":"arxiv","version":2},"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":"sha256:4d1cebf03c9c40f2c96526efca00e283940f7f0789bbe393863db78e5ad9d691","target":"record","created_at":"2026-07-05T08:29:46Z","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":"0c6cb9fdc170a7050b7b8ec7bc3d6151e8dba42bc2c46b98ee10fa0faf928717","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-29T21:32:50Z","title_canon_sha256":"ece7926f4ba35072305a06afd828b7f004302787eec1b0bffa2756b2966a557b"},"schema_version":"1.0","source":{"id":"2404.01331","kind":"arxiv","version":2}},"canonical_sha256":"94903fdca79beebfea2063764d96929f7773275817bb171776ec4aabd494af10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94903fdca79beebfea2063764d96929f7773275817bb171776ec4aabd494af10","first_computed_at":"2026-07-05T08:29:46.238168Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:46.238168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vjk1edFF1Ve9gQ10k1amYclwd2RFMAHUhKD927FCm8ryVQnDOkO+2uHYjyhYjiJpIEF4dQS4T2sWn5pu3LrzCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:46.238608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01331","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d1cebf03c9c40f2c96526efca00e283940f7f0789bbe393863db78e5ad9d691","sha256:67eeff208f46c6017ed6d12d831b2023fd8a20cf3699945f94cebed304319b61"],"state_sha256":"cec1d53dc0bc505ee0842efa2cb56237f1399c0b77ce15a9c6fe71ebdf4cfbcf"}