{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZTHIKNIO63JWVKHJB6STLYRIPN","short_pith_number":"pith:ZTHIKNIO","schema_version":"1.0","canonical_sha256":"ccce85350ef6d36aa8e90fa535e2287b6d02721e508e3b331afc0f4c1c0146c2","source":{"kind":"arxiv","id":"2504.15929","version":2},"attestation_state":"computed","paper":{"title":"Meta-Entity Driven Triplet Mining for Aligning Medical Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aykut Ko\\c{c}, Melih B. Yilmaz, M. Talat Yavuz, Muti Kara, Saban Ozturk, Tolga \\c{C}ukur","submitted_at":"2025-04-22T14:17:51Z","abstract_excerpt":"Diagnostic imaging relies on interpreting both images and radiology reports, but the growing data volumes place significant pressure on medical experts, yielding increased errors and workflow backlogs. Medical vision-language models (med-VLMs) have emerged as a powerful framework to efficiently process multimodal imaging data, particularly in chest X-ray (CXR) evaluations, albeit their performance hinges on how well image and text representations are aligned. Existing alignment methods, predominantly based on contrastive learning, prioritize separation between disease classes over segregation "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.15929","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T14:17:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7a4a74a6effb486ddb5822f251a4622a6099f81c2aa869bb87367207a5102811","abstract_canon_sha256":"adfb7adb6d75bfc5709675c404f5b1b652df3e548fc85cc7cc4b4f88883162b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:18.530213Z","signature_b64":"izwQ405lxI8osmfcjp7GzkhNHk/M6nCarHFxf4vtKWj5wOE5qj11g+u8pxAF+vL1dWMxx6MB3sga2oL98xn4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccce85350ef6d36aa8e90fa535e2287b6d02721e508e3b331afc0f4c1c0146c2","last_reissued_at":"2026-07-05T10:53:18.529608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:18.529608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Entity Driven Triplet Mining for Aligning Medical Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aykut Ko\\c{c}, Melih B. Yilmaz, M. Talat Yavuz, Muti Kara, Saban Ozturk, Tolga \\c{C}ukur","submitted_at":"2025-04-22T14:17:51Z","abstract_excerpt":"Diagnostic imaging relies on interpreting both images and radiology reports, but the growing data volumes place significant pressure on medical experts, yielding increased errors and workflow backlogs. Medical vision-language models (med-VLMs) have emerged as a powerful framework to efficiently process multimodal imaging data, particularly in chest X-ray (CXR) evaluations, albeit their performance hinges on how well image and text representations are aligned. Existing alignment methods, predominantly based on contrastive learning, prioritize separation between disease classes over segregation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15929","kind":"arxiv","version":2},"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/2504.15929/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.15929","created_at":"2026-07-05T10:53:18.529681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15929v2","created_at":"2026-07-05T10:53:18.529681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15929","created_at":"2026-07-05T10:53:18.529681+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZTHIKNIO63JW","created_at":"2026-07-05T10:53:18.529681+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZTHIKNIO63JWVKHJ","created_at":"2026-07-05T10:53:18.529681+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZTHIKNIO","created_at":"2026-07-05T10:53:18.529681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZTHIKNIO63JWVKHJB6STLYRIPN","json":"https://pith.science/pith/ZTHIKNIO63JWVKHJB6STLYRIPN.json","graph_json":"https://pith.science/api/pith-number/ZTHIKNIO63JWVKHJB6STLYRIPN/graph.json","events_json":"https://pith.science/api/pith-number/ZTHIKNIO63JWVKHJB6STLYRIPN/events.json","paper":"https://pith.science/paper/ZTHIKNIO"},"agent_actions":{"view_html":"https://pith.science/pith/ZTHIKNIO63JWVKHJB6STLYRIPN","download_json":"https://pith.science/pith/ZTHIKNIO63JWVKHJB6STLYRIPN.json","view_paper":"https://pith.science/paper/ZTHIKNIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15929&json=true","fetch_graph":"https://pith.science/api/pith-number/ZTHIKNIO63JWVKHJB6STLYRIPN/graph.json","fetch_events":"https://pith.science/api/pith-number/ZTHIKNIO63JWVKHJB6STLYRIPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZTHIKNIO63JWVKHJB6STLYRIPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZTHIKNIO63JWVKHJB6STLYRIPN/action/storage_attestation","attest_author":"https://pith.science/pith/ZTHIKNIO63JWVKHJB6STLYRIPN/action/author_attestation","sign_citation":"https://pith.science/pith/ZTHIKNIO63JWVKHJB6STLYRIPN/action/citation_signature","submit_replication":"https://pith.science/pith/ZTHIKNIO63JWVKHJB6STLYRIPN/action/replication_record"}},"created_at":"2026-07-05T10:53:18.529681+00:00","updated_at":"2026-07-05T10:53:18.529681+00:00"}