{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MRRZTGYSM5QDZTNAFPGP57TOLS","short_pith_number":"pith:MRRZTGYS","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"},"canonical_sha256":"6463999b1267603ccda02bccfefe6e5c84b3ff044e9dd8d889a080d750b48876","source":{"kind":"arxiv","id":"2506.01902","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01902","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01902v1","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01902","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"pith_short_12","alias_value":"MRRZTGYSM5QD","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"pith_short_16","alias_value":"MRRZTGYSM5QDZTNA","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"pith_short_8","alias_value":"MRRZTGYS","created_at":"2026-07-05T11:14:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MRRZTGYSM5QDZTNAFPGP57TOLS","target":"record","payload":{"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"},"canonical_sha256":"6463999b1267603ccda02bccfefe6e5c84b3ff044e9dd8d889a080d750b48876","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"},"source_kind":"arxiv","source_id":"2506.01902","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":"2026-07-05T11:14:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RJRcP0VAEEBZ65B+BbOChkSia7V40zGlUvt26kN5h7TJCCNCiSP+iNxgMVrGmzEyThKe3vxoplQAqS2zbMVEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:51:49.103478Z"},"content_sha256":"de2e54d84960c3cf5e172596f0cdfc130e473a39c46c3c63d70771d2760daa5a","schema_version":"1.0","event_id":"sha256:de2e54d84960c3cf5e172596f0cdfc130e473a39c46c3c63d70771d2760daa5a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MRRZTGYSM5QDZTNAFPGP57TOLS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dji5d+fqee0uNNoXpWU+VbalfLsqc9dSq7KXanoXbWdrHhnFlvd/WA0anxfa9b06tsPLVjYofrGYnqFPNsCICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:51:49.104008Z"},"content_sha256":"a006ae5ca33ddba3cc7f71126c454104423ddca396b48f7a4b5c7b7dc6e7f9e2","schema_version":"1.0","event_id":"sha256:a006ae5ca33ddba3cc7f71126c454104423ddca396b48f7a4b5c7b7dc6e7f9e2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MRRZTGYSM5QDZTNAFPGP57TOLS/bundle.json","state_url":"https://pith.science/pith/MRRZTGYSM5QDZTNAFPGP57TOLS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MRRZTGYSM5QDZTNAFPGP57TOLS/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":"2026-08-08T11:51:49Z","links":{"resolver":"https://pith.science/pith/MRRZTGYSM5QDZTNAFPGP57TOLS","bundle":"https://pith.science/pith/MRRZTGYSM5QDZTNAFPGP57TOLS/bundle.json","state":"https://pith.science/pith/MRRZTGYSM5QDZTNAFPGP57TOLS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MRRZTGYSM5QDZTNAFPGP57TOLS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MRRZTGYSM5QDZTNAFPGP57TOLS","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":"20ec184fc68fc7f7db0dc465ed638d1db79d79451ad2de579885def514f5759e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T17:23:25Z","title_canon_sha256":"b199799fc3bf9e7e450a894e005f1031ac63866345f86a2681e406c45bb80cdd"},"schema_version":"1.0","source":{"id":"2506.01902","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01902","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01902v1","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01902","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"pith_short_12","alias_value":"MRRZTGYSM5QD","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"pith_short_16","alias_value":"MRRZTGYSM5QDZTNA","created_at":"2026-07-05T11:14:21Z"},{"alias_kind":"pith_short_8","alias_value":"MRRZTGYS","created_at":"2026-07-05T11:14:21Z"}],"graph_snapshots":[{"event_id":"sha256:a006ae5ca33ddba3cc7f71126c454104423ddca396b48f7a4b5c7b7dc6e7f9e2","target":"graph","created_at":"2026-07-05T11:14:21Z","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/2506.01902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kayhan Batmanghelich, Li Sun, Xinliu Zhong","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T17:23:25Z","title":"Enhancing Biomedical Multi-modal Representation Learning with Multi-scale Pre-training and Perturbed Report Discrimination"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01902","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:de2e54d84960c3cf5e172596f0cdfc130e473a39c46c3c63d70771d2760daa5a","target":"record","created_at":"2026-07-05T11:14:21Z","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":"20ec184fc68fc7f7db0dc465ed638d1db79d79451ad2de579885def514f5759e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-02T17:23:25Z","title_canon_sha256":"b199799fc3bf9e7e450a894e005f1031ac63866345f86a2681e406c45bb80cdd"},"schema_version":"1.0","source":{"id":"2506.01902","kind":"arxiv","version":1}},"canonical_sha256":"6463999b1267603ccda02bccfefe6e5c84b3ff044e9dd8d889a080d750b48876","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6463999b1267603ccda02bccfefe6e5c84b3ff044e9dd8d889a080d750b48876","first_computed_at":"2026-07-05T11:14:21.045690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:21.045690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"or4SHglX6av/0yN9m2GO3OQGTi9eIx6NynQxvuaY81s32U3f6xd28JyA2+2ZcIe6G0ROPbd0tKZbm21jeJL0Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:21.046159Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01902","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de2e54d84960c3cf5e172596f0cdfc130e473a39c46c3c63d70771d2760daa5a","sha256:a006ae5ca33ddba3cc7f71126c454104423ddca396b48f7a4b5c7b7dc6e7f9e2"],"state_sha256":"f88860d0c4ef8e8539e92caf629fb73a99cfbd8fc5b109ad0d0d91c8df357f6d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SVKDzypZLolPXiy8dNs/Jy5bxKdZZdcAsKBYcDkNxuWFNHjSgT1+5a2wPS5fgdjiRKC9R48liA6Le9/iaRBdBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:51:49.108198Z","bundle_sha256":"eec63e6e339f92cf90dc1a7fbf57dde62fde18af15e79b50df8c7631aedfab8c"}}