{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3CP656FB2HN4P7KMMELZSLJ64E","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":"fc4cf16552b03bc02bbc94af188512ab424850486619667a87d0d535af8236f4","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T17:59:06Z","title_canon_sha256":"5f1da939f70d02022e64e508e9adcf52e2429a5a27874e065946169bdcdf8752"},"schema_version":"1.0","source":{"id":"2409.11402","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.11402","created_at":"2026-07-05T09:24:18Z"},{"alias_kind":"arxiv_version","alias_value":"2409.11402v2","created_at":"2026-07-05T09:24:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11402","created_at":"2026-07-05T09:24:18Z"},{"alias_kind":"pith_short_12","alias_value":"3CP656FB2HN4","created_at":"2026-07-05T09:24:18Z"},{"alias_kind":"pith_short_16","alias_value":"3CP656FB2HN4P7KM","created_at":"2026-07-05T09:24:18Z"},{"alias_kind":"pith_short_8","alias_value":"3CP656FB","created_at":"2026-07-05T09:24:18Z"}],"graph_snapshots":[{"event_id":"sha256:ece9fbc29b972ac70341937ae2d76d2f645d48ff8bb5b8e4a4325113edba279d","target":"graph","created_at":"2026-07-05T09:24:18Z","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/2409.11402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce NVLM 1.0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary models (e.g., GPT-4o) and open-access models (e.g., Llama 3-V 405B and InternVL 2). Remarkably, NVLM 1.0 shows improved text-only performance over its LLM backbone after multimodal training. In terms of model design, we perform a comprehensive comparison between decoder-only multimodal LLMs (e.g., LLaVA) and cross-attention-based models (e.g., Flamingo). Based on the strengths and weaknesses of both approaches","authors_text":"Boxin Wang, Bryan Catanzaro, Jon Barker, Mohammad Shoeybi, Nayeon Lee, Tuomas Rintamaki, Wei Ping, Wenliang Dai, Zhuolin Yang, Zihan Liu","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T17:59:06Z","title":"NVLM: Open Frontier-Class Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11402","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":"sha256:2a0f7b461edc3985ffe7a44a47dc702e45cada5e584ecc5143941f176ff31d05","target":"record","created_at":"2026-07-05T09:24:18Z","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":"fc4cf16552b03bc02bbc94af188512ab424850486619667a87d0d535af8236f4","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T17:59:06Z","title_canon_sha256":"5f1da939f70d02022e64e508e9adcf52e2429a5a27874e065946169bdcdf8752"},"schema_version":"1.0","source":{"id":"2409.11402","kind":"arxiv","version":2}},"canonical_sha256":"d89feef8a1d1dbc7fd4c6117992d3ee13bdb63913a269bdbace276206787b790","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d89feef8a1d1dbc7fd4c6117992d3ee13bdb63913a269bdbace276206787b790","first_computed_at":"2026-07-05T09:24:18.279748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:18.279748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tz3ukTFS+qZfZCgNnb5Od8VygSUWiBBtYh0c5w/BQVy+H8q1WTcR2n7OdbZNxMYz7Cfyq9AQwa+MXrfcUEYRDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:18.280287Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.11402","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2a0f7b461edc3985ffe7a44a47dc702e45cada5e584ecc5143941f176ff31d05","sha256:ece9fbc29b972ac70341937ae2d76d2f645d48ff8bb5b8e4a4325113edba279d"],"state_sha256":"22244b927e55c1d463653c7c1cab3858c90c8bfb34e1d98fa6bd54115dea1fa9"}