{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F3FI3CYARB77BBLD5LOVUNXJFB","short_pith_number":"pith:F3FI3CYA","schema_version":"1.0","canonical_sha256":"2eca8d8b00887ff08563eadd5a36e9287434d8c2d62ca0011a16cbada18b7fe3","source":{"kind":"arxiv","id":"2405.10140","version":1},"attestation_state":"computed","paper":{"title":"Libra: Building Decoupled Vision System on Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Xiaoshan Yang, Yaguang Song, Yifan Xu","submitted_at":"2024-05-16T14:34:44Z","abstract_excerpt":"In this work, we introduce Libra, a prototype model with a decoupled vision system on a large language model (LLM). The decoupled vision system decouples inner-modal modeling and cross-modal interaction, yielding unique visual information modeling and effective cross-modal comprehension. Libra is trained through discrete auto-regressive modeling on both vision and language inputs. Specifically, we incorporate a routed visual expert with a cross-modal bridge module into a pretrained LLM to route the vision and language flows during attention computing to enable different attention patterns in i"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.10140","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-16T14:34:44Z","cross_cats_sorted":[],"title_canon_sha256":"1e9cda93298d22af92ebb6fb2e6af2ed17aa1d37dc614964aa98aba494c54fd1","abstract_canon_sha256":"0789fad6b9a04697e27079e33fbd44e1f2742d9e181a0e20498ead3f28ecba8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:53.542896Z","signature_b64":"tk+trLl8mH7axUwHQCtp2IEK5xxWzHwJA7YkJmwwamJFEZteFtcubpMGt9nrdf7TvxJ0M/1SolnSvIqsE2wiCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2eca8d8b00887ff08563eadd5a36e9287434d8c2d62ca0011a16cbada18b7fe3","last_reissued_at":"2026-07-05T08:19:53.542457Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:53.542457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Libra: Building Decoupled Vision System on Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Xiaoshan Yang, Yaguang Song, Yifan Xu","submitted_at":"2024-05-16T14:34:44Z","abstract_excerpt":"In this work, we introduce Libra, a prototype model with a decoupled vision system on a large language model (LLM). The decoupled vision system decouples inner-modal modeling and cross-modal interaction, yielding unique visual information modeling and effective cross-modal comprehension. Libra is trained through discrete auto-regressive modeling on both vision and language inputs. Specifically, we incorporate a routed visual expert with a cross-modal bridge module into a pretrained LLM to route the vision and language flows during attention computing to enable different attention patterns in i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10140","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.10140/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.10140","created_at":"2026-07-05T08:19:53.542514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10140v1","created_at":"2026-07-05T08:19:53.542514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10140","created_at":"2026-07-05T08:19:53.542514+00:00"},{"alias_kind":"pith_short_12","alias_value":"F3FI3CYARB77","created_at":"2026-07-05T08:19:53.542514+00:00"},{"alias_kind":"pith_short_16","alias_value":"F3FI3CYARB77BBLD","created_at":"2026-07-05T08:19:53.542514+00:00"},{"alias_kind":"pith_short_8","alias_value":"F3FI3CYA","created_at":"2026-07-05T08:19:53.542514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F3FI3CYARB77BBLD5LOVUNXJFB","json":"https://pith.science/pith/F3FI3CYARB77BBLD5LOVUNXJFB.json","graph_json":"https://pith.science/api/pith-number/F3FI3CYARB77BBLD5LOVUNXJFB/graph.json","events_json":"https://pith.science/api/pith-number/F3FI3CYARB77BBLD5LOVUNXJFB/events.json","paper":"https://pith.science/paper/F3FI3CYA"},"agent_actions":{"view_html":"https://pith.science/pith/F3FI3CYARB77BBLD5LOVUNXJFB","download_json":"https://pith.science/pith/F3FI3CYARB77BBLD5LOVUNXJFB.json","view_paper":"https://pith.science/paper/F3FI3CYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10140&json=true","fetch_graph":"https://pith.science/api/pith-number/F3FI3CYARB77BBLD5LOVUNXJFB/graph.json","fetch_events":"https://pith.science/api/pith-number/F3FI3CYARB77BBLD5LOVUNXJFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F3FI3CYARB77BBLD5LOVUNXJFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F3FI3CYARB77BBLD5LOVUNXJFB/action/storage_attestation","attest_author":"https://pith.science/pith/F3FI3CYARB77BBLD5LOVUNXJFB/action/author_attestation","sign_citation":"https://pith.science/pith/F3FI3CYARB77BBLD5LOVUNXJFB/action/citation_signature","submit_replication":"https://pith.science/pith/F3FI3CYARB77BBLD5LOVUNXJFB/action/replication_record"}},"created_at":"2026-07-05T08:19:53.542514+00:00","updated_at":"2026-07-05T08:19:53.542514+00:00"}