{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IBWGQXNKT6PMVGWPUI5JRZ5UDZ","short_pith_number":"pith:IBWGQXNK","canonical_record":{"source":{"id":"2607.04694","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-06T05:52:33Z","cross_cats_sorted":[],"title_canon_sha256":"ee173ae8ca41a9d170005723ee86b5d389f6d6cd5922b5322ba09034fa026444","abstract_canon_sha256":"a5463339abdb68d82bdf2553016a9dbd275613753a3b10ad8c1f372792dec0c6"},"schema_version":"1.0"},"canonical_sha256":"406c685daa9f9eca9acfa23a98e7b41e647348d5bed2dd9db17bbb2e065f3b38","source":{"kind":"arxiv","id":"2607.04694","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04694","created_at":"2026-07-07T02:19:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04694v1","created_at":"2026-07-07T02:19:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04694","created_at":"2026-07-07T02:19:58Z"},{"alias_kind":"pith_short_12","alias_value":"IBWGQXNKT6PM","created_at":"2026-07-07T02:19:58Z"},{"alias_kind":"pith_short_16","alias_value":"IBWGQXNKT6PMVGWP","created_at":"2026-07-07T02:19:58Z"},{"alias_kind":"pith_short_8","alias_value":"IBWGQXNK","created_at":"2026-07-07T02:19:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IBWGQXNKT6PMVGWPUI5JRZ5UDZ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.04694","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-06T05:52:33Z","cross_cats_sorted":[],"title_canon_sha256":"ee173ae8ca41a9d170005723ee86b5d389f6d6cd5922b5322ba09034fa026444","abstract_canon_sha256":"a5463339abdb68d82bdf2553016a9dbd275613753a3b10ad8c1f372792dec0c6"},"schema_version":"1.0"},"canonical_sha256":"406c685daa9f9eca9acfa23a98e7b41e647348d5bed2dd9db17bbb2e065f3b38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:58.489578Z","signature_b64":"zMITEMZtg7C1iLrHJ6by/PQkPs17c7A6vLll4abXhfMpEG4vxSGME0K2ap/WFrNNVCCirK26h67ToXOcfWwcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"406c685daa9f9eca9acfa23a98e7b41e647348d5bed2dd9db17bbb2e065f3b38","last_reissued_at":"2026-07-07T02:19:58.488638Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:58.488638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.04694","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":"2026-07-07T02:19:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TNxVATWwk2MMTW4IYPme8yZnOmfa7i8uNVskW0wetdhDZJ0TH39MRKs10xxjIXiYa+ECuq0Bqn6KhTF5g7M4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T08:34:22.078790Z"},"content_sha256":"25a528c1f62dd9495665532cc64360eaa2a149aec7f4680299647de6fb90ee5c","schema_version":"1.0","event_id":"sha256:25a528c1f62dd9495665532cc64360eaa2a149aec7f4680299647de6fb90ee5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IBWGQXNKT6PMVGWPUI5JRZ5UDZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Solve the Missing First Step: Can VLMs Standardize Raw Heterogeneous Medical Data?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cunhao Zhu, Dongliang Xu, Haoyang Lyu, Serena Yeung-Levy, Xiaoxiao Sun, Xin Chen, Xudong Luo, Yue Yao","submitted_at":"2026-07-06T05:52:33Z","abstract_excerpt":"As vision-language models (VLMs) are increasingly applied to medical AI, existing benchmarks mainly focus on evaluating their diagnosis ability over given medical images and texts, implicitly assuming that standardized medical images, texts or question-answer pairs are already prepared. However, this assumption does not hold when we apply VLMs in real clinical practice, where medical data is often raw, heterogeneous, and fragmented across different sources. In this paper, we study this missing step, i.e., raw medical data standardization. Specifically, models are given raw dataset folders and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04694","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/2607.04694/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":"2026-07-07T02:19:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KY3WULcOn5YneCI5J5QHyFFiPigX9E7gfKzy7oxXeD/K+/kkyhddzEBPrhajL+0+SbOT39sk71AVSfZkbj1dCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T08:34:22.079223Z"},"content_sha256":"618e16071877e389fdb7ba11a9e8e016d496d026ef08b80bc0e8e6da9572371f","schema_version":"1.0","event_id":"sha256:618e16071877e389fdb7ba11a9e8e016d496d026ef08b80bc0e8e6da9572371f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IBWGQXNKT6PMVGWPUI5JRZ5UDZ/bundle.json","state_url":"https://pith.science/pith/IBWGQXNKT6PMVGWPUI5JRZ5UDZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IBWGQXNKT6PMVGWPUI5JRZ5UDZ/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":"2026-08-01T08:34:22Z","links":{"resolver":"https://pith.science/pith/IBWGQXNKT6PMVGWPUI5JRZ5UDZ","bundle":"https://pith.science/pith/IBWGQXNKT6PMVGWPUI5JRZ5UDZ/bundle.json","state":"https://pith.science/pith/IBWGQXNKT6PMVGWPUI5JRZ5UDZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IBWGQXNKT6PMVGWPUI5JRZ5UDZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IBWGQXNKT6PMVGWPUI5JRZ5UDZ","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":"a5463339abdb68d82bdf2553016a9dbd275613753a3b10ad8c1f372792dec0c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-06T05:52:33Z","title_canon_sha256":"ee173ae8ca41a9d170005723ee86b5d389f6d6cd5922b5322ba09034fa026444"},"schema_version":"1.0","source":{"id":"2607.04694","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04694","created_at":"2026-07-07T02:19:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04694v1","created_at":"2026-07-07T02:19:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04694","created_at":"2026-07-07T02:19:58Z"},{"alias_kind":"pith_short_12","alias_value":"IBWGQXNKT6PM","created_at":"2026-07-07T02:19:58Z"},{"alias_kind":"pith_short_16","alias_value":"IBWGQXNKT6PMVGWP","created_at":"2026-07-07T02:19:58Z"},{"alias_kind":"pith_short_8","alias_value":"IBWGQXNK","created_at":"2026-07-07T02:19:58Z"}],"graph_snapshots":[{"event_id":"sha256:618e16071877e389fdb7ba11a9e8e016d496d026ef08b80bc0e8e6da9572371f","target":"graph","created_at":"2026-07-07T02:19:58Z","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/2607.04694/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As vision-language models (VLMs) are increasingly applied to medical AI, existing benchmarks mainly focus on evaluating their diagnosis ability over given medical images and texts, implicitly assuming that standardized medical images, texts or question-answer pairs are already prepared. However, this assumption does not hold when we apply VLMs in real clinical practice, where medical data is often raw, heterogeneous, and fragmented across different sources. In this paper, we study this missing step, i.e., raw medical data standardization. Specifically, models are given raw dataset folders and ","authors_text":"Cunhao Zhu, Dongliang Xu, Haoyang Lyu, Serena Yeung-Levy, Xiaoxiao Sun, Xin Chen, Xudong Luo, Yue Yao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-06T05:52:33Z","title":"Solve the Missing First Step: Can VLMs Standardize Raw Heterogeneous Medical Data?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04694","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":"sha256:25a528c1f62dd9495665532cc64360eaa2a149aec7f4680299647de6fb90ee5c","target":"record","created_at":"2026-07-07T02:19:58Z","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":"a5463339abdb68d82bdf2553016a9dbd275613753a3b10ad8c1f372792dec0c6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-06T05:52:33Z","title_canon_sha256":"ee173ae8ca41a9d170005723ee86b5d389f6d6cd5922b5322ba09034fa026444"},"schema_version":"1.0","source":{"id":"2607.04694","kind":"arxiv","version":1}},"canonical_sha256":"406c685daa9f9eca9acfa23a98e7b41e647348d5bed2dd9db17bbb2e065f3b38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"406c685daa9f9eca9acfa23a98e7b41e647348d5bed2dd9db17bbb2e065f3b38","first_computed_at":"2026-07-07T02:19:58.488638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:58.488638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zMITEMZtg7C1iLrHJ6by/PQkPs17c7A6vLll4abXhfMpEG4vxSGME0K2ap/WFrNNVCCirK26h67ToXOcfWwcAw==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:58.489578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04694","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25a528c1f62dd9495665532cc64360eaa2a149aec7f4680299647de6fb90ee5c","sha256:618e16071877e389fdb7ba11a9e8e016d496d026ef08b80bc0e8e6da9572371f"],"state_sha256":"867ae52856e3c47f6c20201c2fa90fdfa73d2815d7ebdb2c506e58355f3ab289"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/o1pQcU+TnTWxQL/gdCih33gxhZigDo6C+hg0FimvQRyGiNGk08Flh4kid150QWh5X2IN/ZnaaQ3cuI2Jtx2AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T08:34:22.081952Z","bundle_sha256":"ae83758a7367d78431ceb5cffd612284f0a59dc57e2fa12a5533c607353668c3"}}