{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MX3VK5JGS2BYLHUTY74CHBMJCE","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b979d181362814ee9cd5047f2e19caa1c27fa578343d66e862e02b2c5e19c0ec","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T16:49:19Z","title_canon_sha256":"59bbf75517b9cc3d38f3423e728810c9d3ed4e863975fa3f968e26374e6c8911"},"schema_version":"1.0","source":{"id":"2607.27122","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.27122","created_at":"2026-07-30T01:23:38Z"},{"alias_kind":"arxiv_version","alias_value":"2607.27122v1","created_at":"2026-07-30T01:23:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27122","created_at":"2026-07-30T01:23:38Z"},{"alias_kind":"pith_short_12","alias_value":"MX3VK5JGS2BY","created_at":"2026-07-30T01:23:38Z"},{"alias_kind":"pith_short_16","alias_value":"MX3VK5JGS2BYLHUT","created_at":"2026-07-30T01:23:38Z"},{"alias_kind":"pith_short_8","alias_value":"MX3VK5JG","created_at":"2026-07-30T01:23:38Z"}],"graph_snapshots":[{"event_id":"sha256:18ee6e6d2319d3d3c332c2c1755ea25095098e750b7eadf921e043269d26ff68","target":"graph","created_at":"2026-07-30T01:23:38Z","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/2607.27122/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gastrointestinal (GI) endoscopic image analysis has shifted from single-label classification toward visual question answering (VQA), where a model must answer free-form clinical questions about an image. While recent vision-language models (VLMs) achieve promising answer accuracy on this task, clinical adoption also requires the model's internal representations to reflect the visual evidence behind its answers. We propose a simple multi-task fine-tuning recipe that constructs auxiliary grounding and description tasks from an existing VQA dataset with minimal additional annotation: expert-annot","authors_text":"Itbaan Safwan, Muhammad Annas Shaikh, Muhammad Atif Tahir, Ramail Khan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T16:49:19Z","title":"Towards Grounded GI Endoscopy VQA via Multi-Task Learning on Small VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27122","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:bbbd794678bece779ebbf3e47f5f9d0a03d764c28278553cb1c6cd8039abbbd2","target":"record","created_at":"2026-07-30T01:23:38Z","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":"b979d181362814ee9cd5047f2e19caa1c27fa578343d66e862e02b2c5e19c0ec","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T16:49:19Z","title_canon_sha256":"59bbf75517b9cc3d38f3423e728810c9d3ed4e863975fa3f968e26374e6c8911"},"schema_version":"1.0","source":{"id":"2607.27122","kind":"arxiv","version":1}},"canonical_sha256":"65f75575269683859e93c7f82385891128a5eed95d0048d9dbaf8eb3ed7aa03b","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65f75575269683859e93c7f82385891128a5eed95d0048d9dbaf8eb3ed7aa03b","first_computed_at":"2026-07-30T01:23:38.420323Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:23:38.420323Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.27122","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbbd794678bece779ebbf3e47f5f9d0a03d764c28278553cb1c6cd8039abbbd2","sha256:18ee6e6d2319d3d3c332c2c1755ea25095098e750b7eadf921e043269d26ff68","sha256:663253f313464ad9ba1a84a9a4824571345cd864748e3953430ef0128f6644f0"],"state_sha256":"53c8e2b0b722e840b5cda3f12b3060cceb8bbf61ee939fc3f5ce80ab8fcd8082"}