{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R7U2U6CUBPS4TDJXLWSG7FMU57","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":"03716aac4c4934237a81f7efaa2178e8bc8ffcc82586ffa6a03557ad11b7b1ed","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T17:59:04Z","title_canon_sha256":"b09921d542a161fadef1e37c63375c25721f87590e2500124a8f268f02ac5f2d"},"schema_version":"1.0","source":{"id":"2410.07167","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07167","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07167v2","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07167","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"pith_short_12","alias_value":"R7U2U6CUBPS4","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"pith_short_16","alias_value":"R7U2U6CUBPS4TDJX","created_at":"2026-07-05T09:21:08Z"},{"alias_kind":"pith_short_8","alias_value":"R7U2U6CU","created_at":"2026-07-05T09:21:08Z"}],"graph_snapshots":[{"event_id":"sha256:e9ef631fc5dee99840b33c95f0f3662ce3f6fb562129494f2f70d55950581687","target":"graph","created_at":"2026-07-05T09:21:08Z","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/2410.07167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the Modality Integration Rate (MIR), an effective, robust, and generalized metric to indicate the multi-modal pre-training quality of Large Vision Language Models (LVLMs). Large-scale pre-training plays a critical role in building capable LVLMs, while evaluating its training quality without the costly supervised fine-tuning stage is under-explored. Loss, perplexity, and in-context evaluation results are commonly used pre-training metrics for Large Language Models (LLMs), while we observed that these metrics are less indicative when aligning a well-trained LLM with a new modality. Du","authors_text":"Dahua Lin, Jiaqi Wang, Nenghai Yu, Pan Zhang, Qidong Huang, Weiming Zhang, Xiaoyi Dong, Yuhang Cao, Yuhang Zang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T17:59:04Z","title":"Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07167","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:ff1928feaf0cfc085dcbeb447fe72310d36aa92d8591dbcffda63ac3b739b5a7","target":"record","created_at":"2026-07-05T09:21:08Z","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":"03716aac4c4934237a81f7efaa2178e8bc8ffcc82586ffa6a03557ad11b7b1ed","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T17:59:04Z","title_canon_sha256":"b09921d542a161fadef1e37c63375c25721f87590e2500124a8f268f02ac5f2d"},"schema_version":"1.0","source":{"id":"2410.07167","kind":"arxiv","version":2}},"canonical_sha256":"8fe9aa78540be5c98d375da46f9594efcacd28046f004b96a729b9e4909c960a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fe9aa78540be5c98d375da46f9594efcacd28046f004b96a729b9e4909c960a","first_computed_at":"2026-07-05T09:21:08.071049Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:08.071049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"quVYo2e/lITroWiLQhzER4zAzuCUalO6+47oA+4ujLqKyirLVRFgqpRIqfE1u/Zk/zjetO0vv1XF1kzqwQBABw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:08.071470Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07167","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff1928feaf0cfc085dcbeb447fe72310d36aa92d8591dbcffda63ac3b739b5a7","sha256:e9ef631fc5dee99840b33c95f0f3662ce3f6fb562129494f2f70d55950581687"],"state_sha256":"37a77e78fc3145410b4cdff762742980af746da44ba1509e0939917cb233f74a"}