{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ALITAD7IVCNTFGOPY7T7H4CIXO","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":"76507746de1af7501e9ba3eba05d2ab504f6918dae272ae4c4d93887960acb7a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T01:24:04Z","title_canon_sha256":"d45bc3a4fb22060fc8a4b803d493d0b130c09a498d2603c7bd46234cce9fe301"},"schema_version":"1.0","source":{"id":"2410.06456","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06456","created_at":"2026-07-05T09:18:01Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06456v1","created_at":"2026-07-05T09:18:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06456","created_at":"2026-07-05T09:18:01Z"},{"alias_kind":"pith_short_12","alias_value":"ALITAD7IVCNT","created_at":"2026-07-05T09:18:01Z"},{"alias_kind":"pith_short_16","alias_value":"ALITAD7IVCNTFGOP","created_at":"2026-07-05T09:18:01Z"},{"alias_kind":"pith_short_8","alias_value":"ALITAD7I","created_at":"2026-07-05T09:18:01Z"}],"graph_snapshots":[{"event_id":"sha256:03360f9795acb3dfd404adc68bbcd2a7502420099be681b594d2bd50da826d74","target":"graph","created_at":"2026-07-05T09:18:01Z","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/2410.06456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision language models (VLMs) combine large language models with vision encoders, demonstrating promise across various tasks. However, they often underperform in task-specific applications due to domain gaps between pre-training and fine-tuning. We introduce VITask, a novel framework that enhances task-specific adaptability of VLMs by integrating task-specific models (TSMs). VITask employs three key strategies: exemplar prompting (EP), response distribution alignment (RDA), and contrastive response tuning (CRT) to improve the task-specific performance of VLMs by adjusting their response ","authors_text":"Daniel Shu Wei Ting, Jun Zhou, Rick Siow Mong Goh, Yang Bai, Yang Zhou, Yong Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T01:24:04Z","title":"From Generalist to Specialist: Adapting Vision Language Models via Task-Specific Visual Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06456","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:c7903206e76ed531c3321ddb93d3ad9d314d2459534bf6b9f83df87ba5fadeb4","target":"record","created_at":"2026-07-05T09:18:01Z","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":"76507746de1af7501e9ba3eba05d2ab504f6918dae272ae4c4d93887960acb7a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T01:24:04Z","title_canon_sha256":"d45bc3a4fb22060fc8a4b803d493d0b130c09a498d2603c7bd46234cce9fe301"},"schema_version":"1.0","source":{"id":"2410.06456","kind":"arxiv","version":1}},"canonical_sha256":"02d1300fe8a89b3299cfc7e7f3f048bb8d6d000e95f71592c146ddd0715c16ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02d1300fe8a89b3299cfc7e7f3f048bb8d6d000e95f71592c146ddd0715c16ff","first_computed_at":"2026-07-05T09:18:01.945658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:01.945658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y19xcAfKKmQdFx9+ICAAIlHWZKP6umeJoAR4qKP1+mX6c/2ZkgOXBCiSEl/Cr27/xI6BOdi1et8zm3ZxaXm4AA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:01.946143Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06456","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7903206e76ed531c3321ddb93d3ad9d314d2459534bf6b9f83df87ba5fadeb4","sha256:03360f9795acb3dfd404adc68bbcd2a7502420099be681b594d2bd50da826d74"],"state_sha256":"766d1d2496abdee2d7b00c40bce757a9b87f118e85183cd909c9eaf42ea55a62"}