{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TGGUM6YRPECROWGKHUDLSHYJ4P","short_pith_number":"pith:TGGUM6YR","canonical_record":{"source":{"id":"2309.11080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-20T06:06:10Z","cross_cats_sorted":[],"title_canon_sha256":"64a4de3ce20c5609811325479fd4c3df8788022e10c3c025e19d4a5bf057dcf3","abstract_canon_sha256":"038eb79bb567080815a67c5bca00544ad641326b8c76342c628a5a2f88080558"},"schema_version":"1.0"},"canonical_sha256":"998d467b1179051758ca3d06b91f09e3ff20083d930bb2082897a247c5b5261c","source":{"kind":"arxiv","id":"2309.11080","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.11080","created_at":"2026-07-05T06:52:30Z"},{"alias_kind":"arxiv_version","alias_value":"2309.11080v1","created_at":"2026-07-05T06:52:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11080","created_at":"2026-07-05T06:52:30Z"},{"alias_kind":"pith_short_12","alias_value":"TGGUM6YRPECR","created_at":"2026-07-05T06:52:30Z"},{"alias_kind":"pith_short_16","alias_value":"TGGUM6YRPECROWGK","created_at":"2026-07-05T06:52:30Z"},{"alias_kind":"pith_short_8","alias_value":"TGGUM6YR","created_at":"2026-07-05T06:52:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TGGUM6YRPECROWGKHUDLSHYJ4P","target":"record","payload":{"canonical_record":{"source":{"id":"2309.11080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-20T06:06:10Z","cross_cats_sorted":[],"title_canon_sha256":"64a4de3ce20c5609811325479fd4c3df8788022e10c3c025e19d4a5bf057dcf3","abstract_canon_sha256":"038eb79bb567080815a67c5bca00544ad641326b8c76342c628a5a2f88080558"},"schema_version":"1.0"},"canonical_sha256":"998d467b1179051758ca3d06b91f09e3ff20083d930bb2082897a247c5b5261c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:30.898201Z","signature_b64":"giBI94BgybEGyYIFu3zHYwgzq82PeZRCkKaMG6GQEJFRuNI/r2AAooai75QqOOHw6blztOyH8WkLH4GruGDMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"998d467b1179051758ca3d06b91f09e3ff20083d930bb2082897a247c5b5261c","last_reissued_at":"2026-07-05T06:52:30.897805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:30.897805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.11080","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":"2026-07-05T06:52:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"StSRraY6ibYvjo5ui7iXbpcvUxWjn4BvWH4ODs9ro8k5lvDLQalesKmtHKwU/ByzpgmKBlqimIwjKFMajgJ+Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:18:26.042339Z"},"content_sha256":"1b7b0b00247ef85ca66f7495bfb92b380e52e187c2a51e72d47f918681a7ca2e","schema_version":"1.0","event_id":"sha256:1b7b0b00247ef85ca66f7495bfb92b380e52e187c2a51e72d47f918681a7ca2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TGGUM6YRPECROWGKHUDLSHYJ4P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Visual Question Answering in the Medical Domain","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arcot Sowmya, Louisa Canepa, Sonit Singh","submitted_at":"2023-09-20T06:06:10Z","abstract_excerpt":"Medical visual question answering (Med-VQA) is a machine learning task that aims to create a system that can answer natural language questions based on given medical images. Although there has been rapid progress on the general VQA task, less progress has been made on Med-VQA due to the lack of large-scale annotated datasets. In this paper, we present domain-specific pre-training strategies, including a novel contrastive learning pretraining method, to mitigate the problem of small datasets for the Med-VQA task. We find that the model benefits from components that use fewer parameters. We also"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11080","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/2309.11080/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":"2026-07-05T06:52:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iyrRmnelV1CqeBwX5w8N7jLaPZ6KXvCepJDeo5hxS3j6EtuAg8DsFsGdCYnX69RUTr7uFRaQ8acI6LJhOLcqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:18:26.042851Z"},"content_sha256":"412064b298b5be823b283daa7678ec0fb8da4d3e57ad289c086fea11071177fb","schema_version":"1.0","event_id":"sha256:412064b298b5be823b283daa7678ec0fb8da4d3e57ad289c086fea11071177fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TGGUM6YRPECROWGKHUDLSHYJ4P/bundle.json","state_url":"https://pith.science/pith/TGGUM6YRPECROWGKHUDLSHYJ4P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TGGUM6YRPECROWGKHUDLSHYJ4P/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":"2026-08-09T00:18:26Z","links":{"resolver":"https://pith.science/pith/TGGUM6YRPECROWGKHUDLSHYJ4P","bundle":"https://pith.science/pith/TGGUM6YRPECROWGKHUDLSHYJ4P/bundle.json","state":"https://pith.science/pith/TGGUM6YRPECROWGKHUDLSHYJ4P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TGGUM6YRPECROWGKHUDLSHYJ4P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TGGUM6YRPECROWGKHUDLSHYJ4P","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":"038eb79bb567080815a67c5bca00544ad641326b8c76342c628a5a2f88080558","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-20T06:06:10Z","title_canon_sha256":"64a4de3ce20c5609811325479fd4c3df8788022e10c3c025e19d4a5bf057dcf3"},"schema_version":"1.0","source":{"id":"2309.11080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.11080","created_at":"2026-07-05T06:52:30Z"},{"alias_kind":"arxiv_version","alias_value":"2309.11080v1","created_at":"2026-07-05T06:52:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.11080","created_at":"2026-07-05T06:52:30Z"},{"alias_kind":"pith_short_12","alias_value":"TGGUM6YRPECR","created_at":"2026-07-05T06:52:30Z"},{"alias_kind":"pith_short_16","alias_value":"TGGUM6YRPECROWGK","created_at":"2026-07-05T06:52:30Z"},{"alias_kind":"pith_short_8","alias_value":"TGGUM6YR","created_at":"2026-07-05T06:52:30Z"}],"graph_snapshots":[{"event_id":"sha256:412064b298b5be823b283daa7678ec0fb8da4d3e57ad289c086fea11071177fb","target":"graph","created_at":"2026-07-05T06:52:30Z","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/2309.11080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Medical visual question answering (Med-VQA) is a machine learning task that aims to create a system that can answer natural language questions based on given medical images. Although there has been rapid progress on the general VQA task, less progress has been made on Med-VQA due to the lack of large-scale annotated datasets. In this paper, we present domain-specific pre-training strategies, including a novel contrastive learning pretraining method, to mitigate the problem of small datasets for the Med-VQA task. We find that the model benefits from components that use fewer parameters. We also","authors_text":"Arcot Sowmya, Louisa Canepa, Sonit Singh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-20T06:06:10Z","title":"Visual Question Answering in the Medical Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.11080","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":"sha256:1b7b0b00247ef85ca66f7495bfb92b380e52e187c2a51e72d47f918681a7ca2e","target":"record","created_at":"2026-07-05T06:52:30Z","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":"038eb79bb567080815a67c5bca00544ad641326b8c76342c628a5a2f88080558","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-20T06:06:10Z","title_canon_sha256":"64a4de3ce20c5609811325479fd4c3df8788022e10c3c025e19d4a5bf057dcf3"},"schema_version":"1.0","source":{"id":"2309.11080","kind":"arxiv","version":1}},"canonical_sha256":"998d467b1179051758ca3d06b91f09e3ff20083d930bb2082897a247c5b5261c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"998d467b1179051758ca3d06b91f09e3ff20083d930bb2082897a247c5b5261c","first_computed_at":"2026-07-05T06:52:30.897805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:52:30.897805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"giBI94BgybEGyYIFu3zHYwgzq82PeZRCkKaMG6GQEJFRuNI/r2AAooai75QqOOHw6blztOyH8WkLH4GruGDMDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:52:30.898201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.11080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b7b0b00247ef85ca66f7495bfb92b380e52e187c2a51e72d47f918681a7ca2e","sha256:412064b298b5be823b283daa7678ec0fb8da4d3e57ad289c086fea11071177fb"],"state_sha256":"81e0cc4c224b755e044149c0ba1562ac366a7d945ef7703f2eabc3f39c410c6a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KaxwMaUIO2If3pgWbxce85Ezhc1t0KoloqmbsNfwRPz4/OHJ7kaC37qKjnqVsMMGVW1f4m9Tf+l0XJ9ekqPYDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:18:26.046497Z","bundle_sha256":"7b8fa5bf6caf37e0e30e42ab8d47ba77a32d982ebef6e0fcc78962147bd3729f"}}