{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QAJKZ4KFTFXCKPWCUM6UWXDPRB","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":"99e6219d44db068f2133f2982ed19b3cc09da01bebbba983356c90c8a48948d5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-09T09:00:45Z","title_canon_sha256":"615927a139fa4d37cae42b73a17d36a92d9054ee9d10bcfc7e916dd4fb2e931a"},"schema_version":"1.0","source":{"id":"2508.06895","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.06895","created_at":"2026-07-05T11:51:37Z"},{"alias_kind":"arxiv_version","alias_value":"2508.06895v1","created_at":"2026-07-05T11:51:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06895","created_at":"2026-07-05T11:51:37Z"},{"alias_kind":"pith_short_12","alias_value":"QAJKZ4KFTFXC","created_at":"2026-07-05T11:51:37Z"},{"alias_kind":"pith_short_16","alias_value":"QAJKZ4KFTFXCKPWC","created_at":"2026-07-05T11:51:37Z"},{"alias_kind":"pith_short_8","alias_value":"QAJKZ4KF","created_at":"2026-07-05T11:51:37Z"}],"graph_snapshots":[{"event_id":"sha256:36407c4fceb2403ebc9fb7d1658a2792d8028d1c54795b528b857c0a38443951","target":"graph","created_at":"2026-07-05T11:51:37Z","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/2508.06895/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mainstream Multimodal Large Language Models (MLLMs) achieve visual understanding by using a vision projector to bridge well-pretrained vision encoders and large language models (LLMs). The inherent gap between visual and textual modalities makes the embeddings from the vision projector critical for visual comprehension. However, current alignment approaches treat visual embeddings as contextual cues and merely apply auto-regressive supervision to textual outputs, neglecting the necessity of introducing equivalent direct visual supervision, which hinders the potential finer alignment of visual ","authors_text":"Haoyu Cao, Jianting Tang, Linli Xu, Yubo Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-09T09:00:45Z","title":"BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06895","kind":"arxiv","version":1},"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:c714f6fc6a34c99a5ece3b49c3f43870ed23a44f79967b9c0b3b62b615092af3","target":"record","created_at":"2026-07-05T11:51:37Z","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":"99e6219d44db068f2133f2982ed19b3cc09da01bebbba983356c90c8a48948d5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-09T09:00:45Z","title_canon_sha256":"615927a139fa4d37cae42b73a17d36a92d9054ee9d10bcfc7e916dd4fb2e931a"},"schema_version":"1.0","source":{"id":"2508.06895","kind":"arxiv","version":1}},"canonical_sha256":"8012acf145996e253ec2a33d4b5c6f884d41d58775dcaece4da4de30600e15e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8012acf145996e253ec2a33d4b5c6f884d41d58775dcaece4da4de30600e15e5","first_computed_at":"2026-07-05T11:51:37.241482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:37.241482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UayIS+ZnUbIjOYNbCaxfCy81TGLs4ndf5WX042yzsOJgtIrX0ia/+RJkoM7bYA2c3fYoogdGYQFLLm1Na5LaCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:37.241975Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.06895","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c714f6fc6a34c99a5ece3b49c3f43870ed23a44f79967b9c0b3b62b615092af3","sha256:36407c4fceb2403ebc9fb7d1658a2792d8028d1c54795b528b857c0a38443951"],"state_sha256":"41684d681a0982eb9670bb34df2c3ec6b84f846a503463ea5c1410fc302ab8dc"}