{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:G3FZ7YF6OOSIL6ZYIXLMOGHD6O","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":"b7764f13297334c44f152765f2bf59bdfa576c1f9aef86a94ea12f33c5d3cd71","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:59:22Z","title_canon_sha256":"b074599496c59ba779bf2bf060c97b98b95e671f4815a8ea1b54f2e367bcc3f3"},"schema_version":"1.0","source":{"id":"2410.08202","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08202","created_at":"2026-07-05T10:30:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08202v3","created_at":"2026-07-05T10:30:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08202","created_at":"2026-07-05T10:30:24Z"},{"alias_kind":"pith_short_12","alias_value":"G3FZ7YF6OOSI","created_at":"2026-07-05T10:30:24Z"},{"alias_kind":"pith_short_16","alias_value":"G3FZ7YF6OOSIL6ZY","created_at":"2026-07-05T10:30:24Z"},{"alias_kind":"pith_short_8","alias_value":"G3FZ7YF6","created_at":"2026-07-05T10:30:24Z"}],"graph_snapshots":[{"event_id":"sha256:7c3cfa926799327c000e846c70756b074263846d40b775b4fd8686299938cd1a","target":"graph","created_at":"2026-07-05T10:30:24Z","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/2410.08202/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we focus on monolithic Multimodal Large Language Models (MLLMs) that integrate visual encoding and language decoding into a single LLM. In particular, we identify that existing pre-training strategies for monolithic MLLMs often suffer from unstable optimization or catastrophic forgetting. To address this issue, our core idea is to embed a new visual parameter space into a pre-trained LLM, thereby stably learning visual knowledge from noisy data while freezing the LLM. Based on this principle, we present Mono-InternVL, a novel monolithic MLLM that seamlessly integrates a set of v","authors_text":"Gen Luo, Jiawen Liu, Jifeng Dai, Wenhan Dou, Xizhou Zhu, Xue Yang, Yu Qiao, Zhaokai Wang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:59:22Z","title":"Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08202","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":"sha256:3d0718a11f5620eada777f6cb84710538f7a17f4c91aa20dd3324fc3a2afc130","target":"record","created_at":"2026-07-05T10:30:24Z","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":"b7764f13297334c44f152765f2bf59bdfa576c1f9aef86a94ea12f33c5d3cd71","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T17:59:22Z","title_canon_sha256":"b074599496c59ba779bf2bf060c97b98b95e671f4815a8ea1b54f2e367bcc3f3"},"schema_version":"1.0","source":{"id":"2410.08202","kind":"arxiv","version":3}},"canonical_sha256":"36cb9fe0be73a485fb3845d6c718e3f3b1a99860ae0a5673636404eaba007f9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36cb9fe0be73a485fb3845d6c718e3f3b1a99860ae0a5673636404eaba007f9d","first_computed_at":"2026-07-05T10:30:24.387582Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:24.387582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VuFXV0Gra0LhsVz17WQtFK/qUXlp3jcENJraQ2tmuxxRXeQjc6LFQ51I6Br6+rmT9wdgeRMm/qJSQ6RU0i5KCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:24.388472Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08202","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d0718a11f5620eada777f6cb84710538f7a17f4c91aa20dd3324fc3a2afc130","sha256:7c3cfa926799327c000e846c70756b074263846d40b775b4fd8686299938cd1a"],"state_sha256":"ebcf2cf9fb3409a39e6b996c0e1aa6fd0c8f24f3967779bad60294e60d4770fd"}