{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LZAGGJODNSLDREKRL3HYBW5T4D","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":"95bc10c360683a1bf768ce4f996504a6bc35a16c46d59086a0033ec75f80f867","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T18:59:19Z","title_canon_sha256":"614e0d573a49adf8956b3daf60915fab2304e8932db5476dc92d76c6397cad28"},"schema_version":"1.0","source":{"id":"2312.03700","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.03700","created_at":"2026-07-05T09:58:57Z"},{"alias_kind":"arxiv_version","alias_value":"2312.03700v2","created_at":"2026-07-05T09:58:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03700","created_at":"2026-07-05T09:58:57Z"},{"alias_kind":"pith_short_12","alias_value":"LZAGGJODNSLD","created_at":"2026-07-05T09:58:57Z"},{"alias_kind":"pith_short_16","alias_value":"LZAGGJODNSLDREKR","created_at":"2026-07-05T09:58:57Z"},{"alias_kind":"pith_short_8","alias_value":"LZAGGJOD","created_at":"2026-07-05T09:58:57Z"}],"graph_snapshots":[{"event_id":"sha256:7247f8f3b76a05a56e76ce9f328b97f2f02303de5546a39444905125ff300999","target":"graph","created_at":"2026-07-05T09:58:57Z","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/2312.03700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have gained significant attention due to their strong multimodal understanding capability. However, existing works rely heavily on modality-specific encoders, which usually differ in architecture and are limited to common modalities. In this paper, we present OneLLM, an MLLM that aligns eight modalities to language using a unified framework. We achieve this through a unified multimodal encoder and a progressive multimodal alignment pipeline. In detail, we first train an image projection module to connect a vision encoder with LLM. Then, we build a unive","authors_text":"Dahua Lin, Jiaming Han, Jiaqi Wang, Kaipeng Zhang, Kaixiong Gong, Peng Gao, Xiangyu Yue, Yiyuan Zhang, Yu Qiao","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T18:59:19Z","title":"OneLLM: One Framework to Align All Modalities with Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03700","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:e8179806c9cf35e521f78ffd0c0cdc53acc8c007a5dc5af910b820b98a87dece","target":"record","created_at":"2026-07-05T09:58:57Z","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":"95bc10c360683a1bf768ce4f996504a6bc35a16c46d59086a0033ec75f80f867","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-06T18:59:19Z","title_canon_sha256":"614e0d573a49adf8956b3daf60915fab2304e8932db5476dc92d76c6397cad28"},"schema_version":"1.0","source":{"id":"2312.03700","kind":"arxiv","version":2}},"canonical_sha256":"5e406325c36c963891515ecf80dbb3e0c52bb774d5e733d3497f101dbb425489","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e406325c36c963891515ecf80dbb3e0c52bb774d5e733d3497f101dbb425489","first_computed_at":"2026-07-05T09:58:57.127764Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:57.127764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xXEoUSj5l5q9ct9SBYoZ1k1datmRIA5WR7XUuOmybriRJTHWSFRAqQv2D5RZKNSR6zFD+FOSNDEhVYdMeqJEBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:57.128263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.03700","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8179806c9cf35e521f78ffd0c0cdc53acc8c007a5dc5af910b820b98a87dece","sha256:7247f8f3b76a05a56e76ce9f328b97f2f02303de5546a39444905125ff300999"],"state_sha256":"4d2419d61b165b8f498fc3b9ad0283323766fc8080f00e8ed58a1ade262b8a77"}