{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7AWBXT4TG2NH4V5S2VY5MOVMBP","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":"dc597ee9f3bad9b192f6c5537f72ef6f3e0f02de6caf89a8774d5116a32c1cd3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T05:41:31Z","title_canon_sha256":"3ae6630c5b457009c44e0401272112b1438e1f324193dee49a15b88a145afa7b"},"schema_version":"1.0","source":{"id":"2501.08443","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08443","created_at":"2026-07-05T10:02:09Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08443v3","created_at":"2026-07-05T10:02:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08443","created_at":"2026-07-05T10:02:09Z"},{"alias_kind":"pith_short_12","alias_value":"7AWBXT4TG2NH","created_at":"2026-07-05T10:02:09Z"},{"alias_kind":"pith_short_16","alias_value":"7AWBXT4TG2NH4V5S","created_at":"2026-07-05T10:02:09Z"},{"alias_kind":"pith_short_8","alias_value":"7AWBXT4T","created_at":"2026-07-05T10:02:09Z"}],"graph_snapshots":[{"event_id":"sha256:fb9773899623891d26147352407a45b4b86e32324a71d537d76a8252205e7246","target":"graph","created_at":"2026-07-05T10:02:09Z","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/2501.08443/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Vision-Language Models (LVLMs) have achieved remarkable success in a wide range of multimodal tasks by integrating pre-trained vision encoders and large language models. However, current LVLMs primarily rely on visual features extracted from the final layers of the vision encoder, overlooking the complementary information available in shallower layers. While recent approaches have explored the use of multilayer visual features in LVLMs, they tend to be task-agnostic and fail to examine the dependencies of hierarchical visual features on specific tasks. To address these gaps, we systemati","authors_text":"Bin Li, Chenghang Lai, Haotian Chen, Xiangyang Xue, Xiaolei Chen, Xu Li, Yi Zheng, Yuxuan Liang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T05:41:31Z","title":"Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08443","kind":"arxiv","version":3},"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":"sha256:61d5a3db386a9ed1b20cdc3142162e87c14cc3299f57da1cc006e1b36b26ba64","target":"record","created_at":"2026-07-05T10:02:09Z","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":"dc597ee9f3bad9b192f6c5537f72ef6f3e0f02de6caf89a8774d5116a32c1cd3","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-26T05:41:31Z","title_canon_sha256":"3ae6630c5b457009c44e0401272112b1438e1f324193dee49a15b88a145afa7b"},"schema_version":"1.0","source":{"id":"2501.08443","kind":"arxiv","version":3}},"canonical_sha256":"f82c1bcf93369a7e57b2d571d63aac0bd9d0b55772c6a7ad0cfe4d241d28ce49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f82c1bcf93369a7e57b2d571d63aac0bd9d0b55772c6a7ad0cfe4d241d28ce49","first_computed_at":"2026-07-05T10:02:09.931594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:09.931594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mJQ84pJmQOULaATxoJF/YYLyFBA10Iv05ioBUEndlxCupWXStHWvPvU8yp0+sQTiiZAzBPKBqLhJuX6kMijTAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:09.932040Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.08443","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61d5a3db386a9ed1b20cdc3142162e87c14cc3299f57da1cc006e1b36b26ba64","sha256:fb9773899623891d26147352407a45b4b86e32324a71d537d76a8252205e7246"],"state_sha256":"02c96c14d8b3f4f79d7fe0f6aa887d54565a5fea05b374f3e0c279c621095991"}