{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZQ2HYQJJJTSBIXGPFTWINYARAW","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":"47bfd7e0f9ca14f7b1f96a7eaaf9aa5422cdfeca8f0f8584f13af2779e8c5be6","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T22:40:15Z","title_canon_sha256":"3dce8376d2af5df0d1f178d48941e54f93ab27d0cda121525c38c7d08da6983c"},"schema_version":"1.0","source":{"id":"2407.06438","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.06438","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"arxiv_version","alias_value":"2407.06438v3","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06438","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"pith_short_12","alias_value":"ZQ2HYQJJJTSB","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZQ2HYQJJJTSBIXGP","created_at":"2026-07-05T09:49:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZQ2HYQJJ","created_at":"2026-07-05T09:49:07Z"}],"graph_snapshots":[{"event_id":"sha256:fdcdab62ec8f4858206678af24d9057f9a463614796be29cbd7e92e60d2915c1","target":"graph","created_at":"2026-07-05T09:49:07Z","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/2407.06438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present SOLO, a single transformer for Scalable visiOn-Language mOdeling. Current large vision-language models (LVLMs) such as LLaVA mostly employ heterogeneous architectures that connect pre-trained visual encoders with large language models (LLMs) to facilitate visual recognition and complex reasoning. Although achieving remarkable performance with relatively lightweight training, we identify four primary scalability limitations: (1) The visual capacity is constrained by pre-trained visual encoders, which are typically an order of magnitude smaller than LLMs. (2) The heterogeneous archite","authors_text":"Hao Peng, Heng Ji, Xingyao Wang, Yangyi Chen","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T22:40:15Z","title":"SOLO: A Single Transformer for Scalable Vision-Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06438","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":"sha256:14e544a7c9045c7cd1c47db03f932c9de60a50150135f5b67120253211301a16","target":"record","created_at":"2026-07-05T09:49:07Z","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":"47bfd7e0f9ca14f7b1f96a7eaaf9aa5422cdfeca8f0f8584f13af2779e8c5be6","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T22:40:15Z","title_canon_sha256":"3dce8376d2af5df0d1f178d48941e54f93ab27d0cda121525c38c7d08da6983c"},"schema_version":"1.0","source":{"id":"2407.06438","kind":"arxiv","version":3}},"canonical_sha256":"cc347c41294ce4145ccf2cec86e01105b77ffc3a89e132f9a07db240d3b47938","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc347c41294ce4145ccf2cec86e01105b77ffc3a89e132f9a07db240d3b47938","first_computed_at":"2026-07-05T09:49:07.574782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:07.574782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u+y3rmdXOfrvgpYtfeE8yYIJrBlRtFiJOvLQyY5AceRGq20YPj+cDQ8jVfrBQEjfqDb5DVjKrh8OqKqcA7clCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:07.575301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.06438","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14e544a7c9045c7cd1c47db03f932c9de60a50150135f5b67120253211301a16","sha256:fdcdab62ec8f4858206678af24d9057f9a463614796be29cbd7e92e60d2915c1"],"state_sha256":"171d7255752c3d8028e7a962df6e86c174c08f1802f04c9d2b830bda7ef4328d"}