{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ERDUQ2TTXYJ27K22NOWPYNJL54","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":"0e8e00a3fbcc59554791febbb3a30bb56cc0a7f42e17e6732c2b4e86ba6366cd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T12:17:23Z","title_canon_sha256":"33f1b7c7feced658fe6a27af2f1872206110f81e5741c0c5e7506a30e22ee010"},"schema_version":"1.0","source":{"id":"2507.01643","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.01643","created_at":"2026-07-05T11:30:52Z"},{"alias_kind":"arxiv_version","alias_value":"2507.01643v1","created_at":"2026-07-05T11:30:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01643","created_at":"2026-07-05T11:30:52Z"},{"alias_kind":"pith_short_12","alias_value":"ERDUQ2TTXYJ2","created_at":"2026-07-05T11:30:52Z"},{"alias_kind":"pith_short_16","alias_value":"ERDUQ2TTXYJ27K22","created_at":"2026-07-05T11:30:52Z"},{"alias_kind":"pith_short_8","alias_value":"ERDUQ2TT","created_at":"2026-07-05T11:30:52Z"}],"graph_snapshots":[{"event_id":"sha256:0d330c7ca112fda80c6534909ea1132ebc3c4f81f349481966bc22e5eafcae8e","target":"graph","created_at":"2026-07-05T11:30:52Z","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/2507.01643/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Transformers (ViTs) are essential as foundation backbones in establishing the visual comprehension capabilities of Multimodal Large Language Models (MLLMs). Although most ViTs achieve impressive performance through image-text pair-based contrastive learning or self-supervised mechanisms, they struggle to engage in connector-based co-training directly with LLMs due to potential parameter initialization conflicts and modality semantic gaps. To address the above challenges, this paper proposes SAILViT, a gradual feature learning-enhanced ViT for facilitating MLLMs to break through performa","authors_text":"Chao Feng, Dingkang Yang, Hongyuan Dong, Jiacong Wang, Jiao Ran, Weijie Yin, Xiao Liang, Zijian Kang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T12:17:23Z","title":"SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01643","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:b187d6475985bbd272fdbe6f4926274a1ed9d6126331ad1dff0544922ae7f7d4","target":"record","created_at":"2026-07-05T11:30:52Z","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":"0e8e00a3fbcc59554791febbb3a30bb56cc0a7f42e17e6732c2b4e86ba6366cd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T12:17:23Z","title_canon_sha256":"33f1b7c7feced658fe6a27af2f1872206110f81e5741c0c5e7506a30e22ee010"},"schema_version":"1.0","source":{"id":"2507.01643","kind":"arxiv","version":1}},"canonical_sha256":"2447486a73be13afab5a6bacfc352bef2a6e0fa127d530e2da5b812f526fdb19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2447486a73be13afab5a6bacfc352bef2a6e0fa127d530e2da5b812f526fdb19","first_computed_at":"2026-07-05T11:30:52.451387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:52.451387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u3Pzep6vwD7l6tHXTqKqXr4yBvrl/SGAXPgYW+kG7io5s2QUSc4s7R9m9OkPsG7nCjrNQZaUemTEP505NNGZDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:52.451867Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.01643","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b187d6475985bbd272fdbe6f4926274a1ed9d6126331ad1dff0544922ae7f7d4","sha256:0d330c7ca112fda80c6534909ea1132ebc3c4f81f349481966bc22e5eafcae8e"],"state_sha256":"91e4da2790cfa1db20cb31bbe759d4158dca7438bd64cc5beca264292bcbbc07"}