{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HSI22V325PJGXVNDHOUBHICDAF","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":"9e76357a37841322b716276737ba39fb37983ae8981b1d919715d9791188a765","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T18:59:59Z","title_canon_sha256":"83f300339f24c975e74e2a722cb68fc5f669e5d2fdb2e2d0b0f2988238c7c31b"},"schema_version":"1.0","source":{"id":"2412.16158","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16158","created_at":"2026-07-05T10:11:30Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16158v2","created_at":"2026-07-05T10:11:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16158","created_at":"2026-07-05T10:11:30Z"},{"alias_kind":"pith_short_12","alias_value":"HSI22V325PJG","created_at":"2026-07-05T10:11:30Z"},{"alias_kind":"pith_short_16","alias_value":"HSI22V325PJGXVND","created_at":"2026-07-05T10:11:30Z"},{"alias_kind":"pith_short_8","alias_value":"HSI22V32","created_at":"2026-07-05T10:11:30Z"}],"graph_snapshots":[{"event_id":"sha256:3b999fb1d035b30fea1563094f7f9b1922444e20cd4f9ce1192c83d4b016b0f4","target":"graph","created_at":"2026-07-05T10:11:30Z","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/2412.16158/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid advance of Large Language Models (LLMs) has catalyzed the development of Vision-Language Models (VLMs). Monolithic VLMs, which avoid modality-specific encoders, offer a promising alternative to the compositional ones but face the challenge of inferior performance. Most existing monolithic VLMs require tuning pre-trained LLMs to acquire vision abilities, which may degrade their language capabilities. To address this dilemma, this paper presents a novel high-performance monolithic VLM named HoVLE. We note that LLMs have been shown capable of interpreting images, when image embeddings a","authors_text":"Chenxin Tao, Chenyu Zhang, Gao Huang, Jiawen Liu, Jifeng Dai, Lewei Lu, Shiqian Su, Wenhai Wang, Xizhou Zhu, Yu Qiao, Zhe Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T18:59:59Z","title":"HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16158","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":"sha256:886f7a9e2c876b1910782f638a1fa3c0230b00acb803bad8071bf0b845e56f1c","target":"record","created_at":"2026-07-05T10:11:30Z","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":"9e76357a37841322b716276737ba39fb37983ae8981b1d919715d9791188a765","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-20T18:59:59Z","title_canon_sha256":"83f300339f24c975e74e2a722cb68fc5f669e5d2fdb2e2d0b0f2988238c7c31b"},"schema_version":"1.0","source":{"id":"2412.16158","kind":"arxiv","version":2}},"canonical_sha256":"3c91ad577aebd26bd5a33ba813a0430151c59239b038019001ec5eb4c9872b1f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c91ad577aebd26bd5a33ba813a0430151c59239b038019001ec5eb4c9872b1f","first_computed_at":"2026-07-05T10:11:30.646027Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:30.646027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WZdvxprNlgV5nFnh6CtHi85cV4N99FaZRO0zwyX1aQNC6MU0IfBoHpcaYo2Zvg1ItBmZHslVWTzqLserCvRmBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:30.646545Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16158","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:886f7a9e2c876b1910782f638a1fa3c0230b00acb803bad8071bf0b845e56f1c","sha256:3b999fb1d035b30fea1563094f7f9b1922444e20cd4f9ce1192c83d4b016b0f4"],"state_sha256":"3d304afa5bc399a568b184762666be9d0d0e17b8639c082d78a3c8baa9d5a679"}