{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MRRZTGYSM5QDZTNAFPGP57TOLS","short_pith_number":"pith:MRRZTGYS","schema_version":"1.0","canonical_sha256":"6463999b1267603ccda02bccfefe6e5c84b3ff044e9dd8d889a080d750b48876","source":{"kind":"arxiv","id":"2506.01902","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Biomedical Multi-modal Representation Learning with Multi-scale Pre-training and Perturbed Report Discrimination","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Kayhan Batmanghelich, Li Sun, Xinliu Zhong","submitted_at":"2025-06-02T17:23:25Z","abstract_excerpt":"Vision-language models pre-trained on large scale of unlabeled biomedical images and associated reports learn generalizable semantic representations. These multi-modal representations can benefit various downstream tasks in the biomedical domain. Contrastive learning is widely used to pre-train vision-language models for general natural images and associated captions. Despite its popularity, we found biomedical texts have complex and domain-specific semantics that are often neglected by common contrastive methods. To address this issue, we propose a novel method, perturbed report discriminatio"},"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":"2506.01902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T17:23:25Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b199799fc3bf9e7e450a894e005f1031ac63866345f86a2681e406c45bb80cdd","abstract_canon_sha256":"20ec184fc68fc7f7db0dc465ed638d1db79d79451ad2de579885def514f5759e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:21.046159Z","signature_b64":"or4SHglX6av/0yN9m2GO3OQGTi9eIx6NynQxvuaY81s32U3f6xd28JyA2+2ZcIe6G0ROPbd0tKZbm21jeJL0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6463999b1267603ccda02bccfefe6e5c84b3ff044e9dd8d889a080d750b48876","last_reissued_at":"2026-07-05T11:14:21.045690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:21.045690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Biomedical Multi-modal Representation Learning with Multi-scale Pre-training and Perturbed Report Discrimination","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Kayhan Batmanghelich, Li Sun, Xinliu Zhong","submitted_at":"2025-06-02T17:23:25Z","abstract_excerpt":"Vision-language models pre-trained on large scale of unlabeled biomedical images and associated reports learn generalizable semantic representations. These multi-modal representations can benefit various downstream tasks in the biomedical domain. Contrastive learning is widely used to pre-train vision-language models for general natural images and associated captions. Despite its popularity, we found biomedical texts have complex and domain-specific semantics that are often neglected by common contrastive methods. To address this issue, we propose a novel method, perturbed report discriminatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01902","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/2506.01902/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":"2506.01902","created_at":"2026-07-05T11:14:21.045757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01902v1","created_at":"2026-07-05T11:14:21.045757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01902","created_at":"2026-07-05T11:14:21.045757+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRRZTGYSM5QD","created_at":"2026-07-05T11:14:21.045757+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRRZTGYSM5QDZTNA","created_at":"2026-07-05T11:14:21.045757+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRRZTGYS","created_at":"2026-07-05T11:14:21.045757+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/MRRZTGYSM5QDZTNAFPGP57TOLS","json":"https://pith.science/pith/MRRZTGYSM5QDZTNAFPGP57TOLS.json","graph_json":"https://pith.science/api/pith-number/MRRZTGYSM5QDZTNAFPGP57TOLS/graph.json","events_json":"https://pith.science/api/pith-number/MRRZTGYSM5QDZTNAFPGP57TOLS/events.json","paper":"https://pith.science/paper/MRRZTGYS"},"agent_actions":{"view_html":"https://pith.science/pith/MRRZTGYSM5QDZTNAFPGP57TOLS","download_json":"https://pith.science/pith/MRRZTGYSM5QDZTNAFPGP57TOLS.json","view_paper":"https://pith.science/paper/MRRZTGYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01902&json=true","fetch_graph":"https://pith.science/api/pith-number/MRRZTGYSM5QDZTNAFPGP57TOLS/graph.json","fetch_events":"https://pith.science/api/pith-number/MRRZTGYSM5QDZTNAFPGP57TOLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRRZTGYSM5QDZTNAFPGP57TOLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRRZTGYSM5QDZTNAFPGP57TOLS/action/storage_attestation","attest_author":"https://pith.science/pith/MRRZTGYSM5QDZTNAFPGP57TOLS/action/author_attestation","sign_citation":"https://pith.science/pith/MRRZTGYSM5QDZTNAFPGP57TOLS/action/citation_signature","submit_replication":"https://pith.science/pith/MRRZTGYSM5QDZTNAFPGP57TOLS/action/replication_record"}},"created_at":"2026-07-05T11:14:21.045757+00:00","updated_at":"2026-07-05T11:14:21.045757+00:00"}