{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ERDUQ2TTXYJ27K22NOWPYNJL54","short_pith_number":"pith:ERDUQ2TT","schema_version":"1.0","canonical_sha256":"2447486a73be13afab5a6bacfc352bef2a6e0fa127d530e2da5b812f526fdb19","source":{"kind":"arxiv","id":"2507.01643","version":1},"attestation_state":"computed","paper":{"title":"SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Feng, Dingkang Yang, Hongyuan Dong, Jiacong Wang, Jiao Ran, Weijie Yin, Xiao Liang, Zijian Kang","submitted_at":"2025-07-02T12:17:23Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.01643","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-02T12:17:23Z","cross_cats_sorted":[],"title_canon_sha256":"33f1b7c7feced658fe6a27af2f1872206110f81e5741c0c5e7506a30e22ee010","abstract_canon_sha256":"0e8e00a3fbcc59554791febbb3a30bb56cc0a7f42e17e6732c2b4e86ba6366cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:52.451867Z","signature_b64":"u3Pzep6vwD7l6tHXTqKqXr4yBvrl/SGAXPgYW+kG7io5s2QUSc4s7R9m9OkPsG7nCjrNQZaUemTEP505NNGZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2447486a73be13afab5a6bacfc352bef2a6e0fa127d530e2da5b812f526fdb19","last_reissued_at":"2026-07-05T11:30:52.451387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:52.451387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAILViT: Towards Robust and Generalizable Visual Backbones for MLLMs via Gradual Feature Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Feng, Dingkang Yang, Hongyuan Dong, Jiacong Wang, Jiao Ran, Weijie Yin, Xiao Liang, Zijian Kang","submitted_at":"2025-07-02T12:17:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.01643","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.01643/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.01643","created_at":"2026-07-05T11:30:52.451455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.01643v1","created_at":"2026-07-05T11:30:52.451455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.01643","created_at":"2026-07-05T11:30:52.451455+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERDUQ2TTXYJ2","created_at":"2026-07-05T11:30:52.451455+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERDUQ2TTXYJ27K22","created_at":"2026-07-05T11:30:52.451455+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERDUQ2TT","created_at":"2026-07-05T11:30:52.451455+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERDUQ2TTXYJ27K22NOWPYNJL54","json":"https://pith.science/pith/ERDUQ2TTXYJ27K22NOWPYNJL54.json","graph_json":"https://pith.science/api/pith-number/ERDUQ2TTXYJ27K22NOWPYNJL54/graph.json","events_json":"https://pith.science/api/pith-number/ERDUQ2TTXYJ27K22NOWPYNJL54/events.json","paper":"https://pith.science/paper/ERDUQ2TT"},"agent_actions":{"view_html":"https://pith.science/pith/ERDUQ2TTXYJ27K22NOWPYNJL54","download_json":"https://pith.science/pith/ERDUQ2TTXYJ27K22NOWPYNJL54.json","view_paper":"https://pith.science/paper/ERDUQ2TT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.01643&json=true","fetch_graph":"https://pith.science/api/pith-number/ERDUQ2TTXYJ27K22NOWPYNJL54/graph.json","fetch_events":"https://pith.science/api/pith-number/ERDUQ2TTXYJ27K22NOWPYNJL54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERDUQ2TTXYJ27K22NOWPYNJL54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERDUQ2TTXYJ27K22NOWPYNJL54/action/storage_attestation","attest_author":"https://pith.science/pith/ERDUQ2TTXYJ27K22NOWPYNJL54/action/author_attestation","sign_citation":"https://pith.science/pith/ERDUQ2TTXYJ27K22NOWPYNJL54/action/citation_signature","submit_replication":"https://pith.science/pith/ERDUQ2TTXYJ27K22NOWPYNJL54/action/replication_record"}},"created_at":"2026-07-05T11:30:52.451455+00:00","updated_at":"2026-07-05T11:30:52.451455+00:00"}