{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BZWRFG6H6FNDEH2EXWQLFEBMEE","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":"63c4c8f16550393adb75b24004d1c5fa375993e95fc25fc3e43c14e64fb04714","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T17:58:02Z","title_canon_sha256":"379e37cb5da8919dbc57226a2d266f8afff67d2fe9753a66ca5c79649a44de4c"},"schema_version":"1.0","source":{"id":"2408.11813","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11813","created_at":"2026-07-05T12:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11813v2","created_at":"2026-07-05T12:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11813","created_at":"2026-07-05T12:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"BZWRFG6H6FND","created_at":"2026-07-05T12:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"BZWRFG6H6FNDEH2E","created_at":"2026-07-05T12:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"BZWRFG6H","created_at":"2026-07-05T12:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:5c715f7fd4f51e57be164028845da49e4af97a398088155abeae53476ab8b1a1","target":"graph","created_at":"2026-07-05T12:05:09Z","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/2408.11813/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual inputs, yet modality alignment remains one of the most challenging aspects. Current MLLMs typically rely on simple adapter architectures and pretraining approaches to bridge vision encoders with large language models (LLM), guided by image-level supervision. We identify this paradigm often leads to suboptimal alignment between modalities, significantly constraining the LLM's ability to properly interpret and reason with visual features particularly for smaller language models. T","authors_text":"Feng Zhao, Jiahao Wang, Ke Lin, Pengfei Wan, Wentao Zhang, Xin Tao, Yajie Zhang, Yaqi Zhao, Yuanxing Zhang, Yuanyang Yin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T17:58:02Z","title":"SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11813","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":"sha256:845069b6b32a81d2ca69b9703052371c0e31a660ebe3ef685f2d45727210e9c4","target":"record","created_at":"2026-07-05T12:05:09Z","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":"63c4c8f16550393adb75b24004d1c5fa375993e95fc25fc3e43c14e64fb04714","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-21T17:58:02Z","title_canon_sha256":"379e37cb5da8919dbc57226a2d266f8afff67d2fe9753a66ca5c79649a44de4c"},"schema_version":"1.0","source":{"id":"2408.11813","kind":"arxiv","version":2}},"canonical_sha256":"0e6d129bc7f15a321f44bda0b2902c2134f11aed848fc73300092775277df0ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e6d129bc7f15a321f44bda0b2902c2134f11aed848fc73300092775277df0ac","first_computed_at":"2026-07-05T12:05:09.851780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:09.851780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5DLjFBLAMe87NgNhaeSBaoiwXmt3xqbCyAVwAi7G1EIhllMxZIKFoBvHuhsFNiUR73Kkwl6kSYAClnHv0CSRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:09.852325Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11813","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:845069b6b32a81d2ca69b9703052371c0e31a660ebe3ef685f2d45727210e9c4","sha256:5c715f7fd4f51e57be164028845da49e4af97a398088155abeae53476ab8b1a1"],"state_sha256":"492c8dad03f70fc92222dd43004c3fbaac26f96d94238ee309ba3a59ca7b178d"}