{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZH5SYXRWLT3F3SD4QVMMS326CM","short_pith_number":"pith:ZH5SYXRW","schema_version":"1.0","canonical_sha256":"c9fb2c5e365cf65dc87c8558c96f5e13284ce0b4ac645c6f164e219f0ebfe7a2","source":{"kind":"arxiv","id":"2607.26885","version":1},"attestation_state":"computed","paper":{"title":"SCALPEL: Semantic Cross-modal Alignment via LLM-Powered Encoder Learning for Medical Vision-Language Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunbo Jiang, Enyu Bao, Fangli Guan, Liqi Yan, Xiangyu Shen, Yihao Wu, Yunzhan Fu","submitted_at":"2026-07-29T13:12:32Z","abstract_excerpt":"Vision-language pre-training (VLP) serves as a cornerstone for medical multimodal representation learning. However, existing medical VLP frameworks are often constrained by the limited context windows and shallow representational capacities of lightweight text encoders when processing lengthy, terminology-dense clinical reports. While integrating medical large language models (LLMs) offers unprecedented clinical reasoning capabilities, it introduces three major bottlenecks: (i) the anisotropic representational collapse of generative LLMs under standard contrastive objectives, (ii) the prohibit"},"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":"2607.26885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T13:12:32Z","cross_cats_sorted":[],"title_canon_sha256":"d064ba15e59872d4593c1243a3cf5259680c7260e39c6cd846767ab425a38b68","abstract_canon_sha256":"c666df60173e09c402105d49afa1b3fcbf29043b7bb6166389db47135a187d07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9fb2c5e365cf65dc87c8558c96f5e13284ce0b4ac645c6f164e219f0ebfe7a2","last_reissued_at":"2026-07-30T01:22:52.237917Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:22:52.237917Z"},"graph_snapshot":{"paper":{"title":"SCALPEL: Semantic Cross-modal Alignment via LLM-Powered Encoder Learning for Medical Vision-Language Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunbo Jiang, Enyu Bao, Fangli Guan, Liqi Yan, Xiangyu Shen, Yihao Wu, Yunzhan Fu","submitted_at":"2026-07-29T13:12:32Z","abstract_excerpt":"Vision-language pre-training (VLP) serves as a cornerstone for medical multimodal representation learning. However, existing medical VLP frameworks are often constrained by the limited context windows and shallow representational capacities of lightweight text encoders when processing lengthy, terminology-dense clinical reports. While integrating medical large language models (LLMs) offers unprecedented clinical reasoning capabilities, it introduces three major bottlenecks: (i) the anisotropic representational collapse of generative LLMs under standard contrastive objectives, (ii) the prohibit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26885","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/2607.26885/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":"2607.26885","created_at":"2026-07-30T01:22:52.243021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.26885v1","created_at":"2026-07-30T01:22:52.243021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26885","created_at":"2026-07-30T01:22:52.243021+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZH5SYXRWLT3F","created_at":"2026-07-30T01:22:52.243021+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZH5SYXRWLT3F3SD4","created_at":"2026-07-30T01:22:52.243021+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZH5SYXRW","created_at":"2026-07-30T01:22:52.243021+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/ZH5SYXRWLT3F3SD4QVMMS326CM","json":"https://pith.science/pith/ZH5SYXRWLT3F3SD4QVMMS326CM.json","graph_json":"https://pith.science/api/pith-number/ZH5SYXRWLT3F3SD4QVMMS326CM/graph.json","events_json":"https://pith.science/api/pith-number/ZH5SYXRWLT3F3SD4QVMMS326CM/events.json","paper":"https://pith.science/paper/ZH5SYXRW"},"agent_actions":{"view_html":"https://pith.science/pith/ZH5SYXRWLT3F3SD4QVMMS326CM","download_json":"https://pith.science/pith/ZH5SYXRWLT3F3SD4QVMMS326CM.json","view_paper":"https://pith.science/paper/ZH5SYXRW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.26885&json=true","fetch_graph":"https://pith.science/api/pith-number/ZH5SYXRWLT3F3SD4QVMMS326CM/graph.json","fetch_events":"https://pith.science/api/pith-number/ZH5SYXRWLT3F3SD4QVMMS326CM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZH5SYXRWLT3F3SD4QVMMS326CM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZH5SYXRWLT3F3SD4QVMMS326CM/action/storage_attestation","attest_author":"https://pith.science/pith/ZH5SYXRWLT3F3SD4QVMMS326CM/action/author_attestation","sign_citation":"https://pith.science/pith/ZH5SYXRWLT3F3SD4QVMMS326CM/action/citation_signature","submit_replication":"https://pith.science/pith/ZH5SYXRWLT3F3SD4QVMMS326CM/action/replication_record"}},"created_at":"2026-07-30T01:22:52.243021+00:00","updated_at":"2026-07-30T01:22:52.243021+00:00"}