{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MX3VK5JGS2BYLHUTY74CHBMJCE","short_pith_number":"pith:MX3VK5JG","canonical_record":{"source":{"id":"2607.27122","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T16:49:19Z","cross_cats_sorted":[],"title_canon_sha256":"59bbf75517b9cc3d38f3423e728810c9d3ed4e863975fa3f968e26374e6c8911","abstract_canon_sha256":"b979d181362814ee9cd5047f2e19caa1c27fa578343d66e862e02b2c5e19c0ec"},"schema_version":"1.0"},"canonical_sha256":"65f75575269683859e93c7f82385891128a5eed95d0048d9dbaf8eb3ed7aa03b","source":{"kind":"arxiv","id":"2607.27122","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MX3VK5JGS2BYLHUTY74CHBMJCE","target":"record","payload":{"canonical_record":{"source":{"id":"2607.27122","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T16:49:19Z","cross_cats_sorted":[],"title_canon_sha256":"59bbf75517b9cc3d38f3423e728810c9d3ed4e863975fa3f968e26374e6c8911","abstract_canon_sha256":"b979d181362814ee9cd5047f2e19caa1c27fa578343d66e862e02b2c5e19c0ec"},"schema_version":"1.0"},"canonical_sha256":"65f75575269683859e93c7f82385891128a5eed95d0048d9dbaf8eb3ed7aa03b","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65f75575269683859e93c7f82385891128a5eed95d0048d9dbaf8eb3ed7aa03b","last_reissued_at":"2026-07-30T01:23:38.420323Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:23:38.420323Z"},"source_kind":"arxiv","source_id":"2607.27122","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:23:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CBRNSYRXVAAA0Onf6SBlW40E+0uqr8g/ofrjMeCcYDOrgQKpZsu80L2+e03odz1ARcTL63wEEUJk8pABP1bkDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:09:22.920808Z"},"content_sha256":"bbbd794678bece779ebbf3e47f5f9d0a03d764c28278553cb1c6cd8039abbbd2","schema_version":"1.0","event_id":"sha256:bbbd794678bece779ebbf3e47f5f9d0a03d764c28278553cb1c6cd8039abbbd2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MX3VK5JGS2BYLHUTY74CHBMJCE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Grounded GI Endoscopy VQA via Multi-Task Learning on Small VLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Itbaan Safwan, Muhammad Annas Shaikh, Muhammad Atif Tahir, Ramail Khan","submitted_at":"2026-07-29T16:49:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27122","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/2607.27122/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:23:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9kCu6fpF4PZDDR2HHtLVDM/EF4UImX8HKZN0iFyz+jwfTU234u9Amp2XU8nDxKpVgwSP6uX8i5gGKI5ekCtACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:09:22.921306Z"},"content_sha256":"18ee6e6d2319d3d3c332c2c1755ea25095098e750b7eadf921e043269d26ff68","schema_version":"1.0","event_id":"sha256:18ee6e6d2319d3d3c332c2c1755ea25095098e750b7eadf921e043269d26ff68"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:MX3VK5JGS2BYLHUTY74CHBMJCE","target":"integrity","payload":{"note":"Identifier '10.1053/j.gastro.2025.07' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"Jong, M.R., Boers, T.G.W., Fockens, K.N., et al.: GastroNet-5M: A multicenter dataset for developing foundation models in gastrointestinal endoscopy. Gastroen- terology170(1), 174–187 (2026).https://doi.org/10.1053/j.gastro.2025.07. 030 10 ","arxiv_id":"2607.27122","detector":"doi_compliance","evidence":{"doi":"10.1053/j.gastro.2025.07","arxiv_id":null,"ref_index":10,"raw_excerpt":"Jong, M.R., Boers, T.G.W., Fockens, K.N., et al.: GastroNet-5M: A multicenter dataset for developing foundation models in gastrointestinal endoscopy. Gastroen- terology170(1), 174–187 (2026).https://doi.org/10.1053/j.gastro.2025.07. 030 10 I. Safwan et al","parse_status":"well_formed","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"],"resolution_status":"hard_miss"},"severity":"critical","ref_index":10,"audited_at":"2026-07-30T11:41:38.019940Z","event_type":"pith.integrity.v1","detected_doi":"10.1053/j.gastro.2025.07","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"92bc5ade427e659e96578de09b9af105be26d765a150d07033a3800598b640a3","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":13891,"payload_sha256":"8518f489429f47eac68325e1506637a933dcb3ba7ba5642f8108879c46c41042","signature_b64":null,"signing_key_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T11:46:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VVE87qX9u8z12Z96R8AwPJjWMp6qlSfgwuKl0HVYfkY/1qYk1UYWUQcz09JEQn9AYHEJC1UyTRwl4USxIswBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T04:09:22.926026Z"},"content_sha256":"663253f313464ad9ba1a84a9a4824571345cd864748e3953430ef0128f6644f0","schema_version":"1.0","event_id":"sha256:663253f313464ad9ba1a84a9a4824571345cd864748e3953430ef0128f6644f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MX3VK5JGS2BYLHUTY74CHBMJCE/bundle.json","state_url":"https://pith.science/pith/MX3VK5JGS2BYLHUTY74CHBMJCE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MX3VK5JGS2BYLHUTY74CHBMJCE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T04:09:22Z","links":{"resolver":"https://pith.science/pith/MX3VK5JGS2BYLHUTY74CHBMJCE","bundle":"https://pith.science/pith/MX3VK5JGS2BYLHUTY74CHBMJCE/bundle.json","state":"https://pith.science/pith/MX3VK5JGS2BYLHUTY74CHBMJCE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MX3VK5JGS2BYLHUTY74CHBMJCE/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IKDpJqiecldoTXrptSQrDX0GUC5DQkbC08GDd3qEFOppj7Z9nurPwhUHw0LQR19JaR0GbJQalznUhjCSvLbNDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T04:09:22.928817Z","bundle_sha256":"d9e5bf2cea2273f1dc0b37347c1880b1a6448fab4f75d11a9c73284f5550e1ba"}}