{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QZC3UH5JBJ3XKV2VBIHEMH7BXG","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":"17794eee8fb6d39abdf8b34c56d116aeca43905186cf7c3cec537c6f1e3bea2d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-13T02:41:55Z","title_canon_sha256":"a1aed792fe6f650563d925e68bb2a2864444798a2bf569a276ea98dc51a279c3"},"schema_version":"1.0","source":{"id":"2310.08825","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.08825","created_at":"2026-07-05T07:53:31Z"},{"alias_kind":"arxiv_version","alias_value":"2310.08825v3","created_at":"2026-07-05T07:53:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08825","created_at":"2026-07-05T07:53:31Z"},{"alias_kind":"pith_short_12","alias_value":"QZC3UH5JBJ3X","created_at":"2026-07-05T07:53:31Z"},{"alias_kind":"pith_short_16","alias_value":"QZC3UH5JBJ3XKV2V","created_at":"2026-07-05T07:53:31Z"},{"alias_kind":"pith_short_8","alias_value":"QZC3UH5J","created_at":"2026-07-05T07:53:31Z"}],"graph_snapshots":[{"event_id":"sha256:a65f8f8cc7eb89d491d897198a47a45ba2b848130e78f7b7526bff72a1d4833b","target":"graph","created_at":"2026-07-05T07:53:31Z","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/2310.08825/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal Large Language Models (MLLMs) have made significant strides in expanding the capabilities of Large Language Models (LLMs) through the incorporation of visual perception interfaces. Despite the emergence of exciting applications and the availability of diverse instruction tuning data, existing approaches often rely on CLIP or its variants as the visual branch, and merely extract features from the deep layers. However, these methods lack a comprehensive analysis of the visual encoders in MLLMs. In this paper, we conduct an extensive investigation into the effectiveness of different v","authors_text":"Dongsheng Jiang, Hao Zhang, Hongkai Xiong, Jin'e Zhao, Jin Li, Songlin Liu, Xiaopeng Zhang, Yuchen Liu, Zhen Gao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-13T02:41:55Z","title":"From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08825","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":"sha256:42bc6d2edca68537944dd5b6c67e0224198c3518022a11b1ab1975d5f081a774","target":"record","created_at":"2026-07-05T07:53:31Z","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":"17794eee8fb6d39abdf8b34c56d116aeca43905186cf7c3cec537c6f1e3bea2d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-13T02:41:55Z","title_canon_sha256":"a1aed792fe6f650563d925e68bb2a2864444798a2bf569a276ea98dc51a279c3"},"schema_version":"1.0","source":{"id":"2310.08825","kind":"arxiv","version":3}},"canonical_sha256":"8645ba1fa90a777557550a0e461fe1b9b3f09d902938f72b022d4aed903e1b80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8645ba1fa90a777557550a0e461fe1b9b3f09d902938f72b022d4aed903e1b80","first_computed_at":"2026-07-05T07:53:31.519140Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:53:31.519140Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kZfGvQ/E962MkbHH+OdTWzckFM3UKlq13sI9My6XJb+kXG05gHc4x/eQ7jEZmZO9vq0HKUoiQ/KwDX169vs8Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T07:53:31.519583Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.08825","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42bc6d2edca68537944dd5b6c67e0224198c3518022a11b1ab1975d5f081a774","sha256:a65f8f8cc7eb89d491d897198a47a45ba2b848130e78f7b7526bff72a1d4833b"],"state_sha256":"b4463bb5a0abe193738f84d8a8e6df0edc4f34ad6d0e8237215908fbd6b74d26"}