{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ELLKTRLVF3W7A5GPIBZZEZVGLC","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":"69388b2a99f8bc303f0660c99c304fb5dab5cd2ff52fd2031379d52c75d4d1de","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-15T09:47:59Z","title_canon_sha256":"43fc3f8dcb57e45c3790b41e9eb4ee487212e4d01ebf99a6d59eaf0f0e02b3c3"},"schema_version":"1.0","source":{"id":"2405.09215","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.09215","created_at":"2026-07-05T08:34:18Z"},{"alias_kind":"arxiv_version","alias_value":"2405.09215v3","created_at":"2026-07-05T08:34:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.09215","created_at":"2026-07-05T08:34:18Z"},{"alias_kind":"pith_short_12","alias_value":"ELLKTRLVF3W7","created_at":"2026-07-05T08:34:18Z"},{"alias_kind":"pith_short_16","alias_value":"ELLKTRLVF3W7A5GP","created_at":"2026-07-05T08:34:18Z"},{"alias_kind":"pith_short_8","alias_value":"ELLKTRLV","created_at":"2026-07-05T08:34:18Z"}],"graph_snapshots":[{"event_id":"sha256:9b2a6518d406fc56e23be47bb05a1f4375c4acf48b4f3a276deb2174c71e0930","target":"graph","created_at":"2026-07-05T08:34:18Z","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/2405.09215/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Xmodel-VLM, a cutting-edge multimodal vision language model. It is designed for efficient deployment on consumer GPU servers. Our work directly confronts a pivotal industry issue by grappling with the prohibitive service costs that hinder the broad adoption of large-scale multimodal systems. Through rigorous training, we have developed a 1B-scale language model from the ground up, employing the LLaVA paradigm for modal alignment. The result, which we call Xmodel-VLM, is a lightweight yet powerful multimodal vision language model. Extensive testing across numerous classic multimoda","authors_text":"Langping He, Ling Jiang, Wanting Xu, Xucheng Huang, Yang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-15T09:47:59Z","title":"Xmodel-VLM: A Simple Baseline for Multimodal Vision Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.09215","kind":"arxiv","version":3},"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:ae230c55bda5f28f5fe766b5979232ed269d43e44173e71ce50dc88807c3d080","target":"record","created_at":"2026-07-05T08:34:18Z","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":"69388b2a99f8bc303f0660c99c304fb5dab5cd2ff52fd2031379d52c75d4d1de","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-15T09:47:59Z","title_canon_sha256":"43fc3f8dcb57e45c3790b41e9eb4ee487212e4d01ebf99a6d59eaf0f0e02b3c3"},"schema_version":"1.0","source":{"id":"2405.09215","kind":"arxiv","version":3}},"canonical_sha256":"22d6a9c5752eedf074cf40739266a65895d63ccd9ca957bc16ad8bc817118c2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22d6a9c5752eedf074cf40739266a65895d63ccd9ca957bc16ad8bc817118c2d","first_computed_at":"2026-07-05T08:34:18.961011Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:18.961011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jtM1Bwa1gQGs2QOjxVq59TOb0Rhri5dWBx/DgMJ0wHfXPtIrPBWNGpBNdZ68vokB4/SzMfU3wjDrdvwgd9MtCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:18.961458Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.09215","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae230c55bda5f28f5fe766b5979232ed269d43e44173e71ce50dc88807c3d080","sha256:9b2a6518d406fc56e23be47bb05a1f4375c4acf48b4f3a276deb2174c71e0930"],"state_sha256":"857e831c53ef2c1e44bfa47525ce9e8d94f4e49dd3f711e5ff75546fc3dbfc74"}