{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UWXKTU6FSB4FNISCA33MMY7HM3","short_pith_number":"pith:UWXKTU6F","schema_version":"1.0","canonical_sha256":"a5aea9d3c5907856a24206f6c663e766eccf837d284585b74bcf32b240dd752f","source":{"kind":"arxiv","id":"2607.21970","version":1},"attestation_state":"computed","paper":{"title":"TextSLIP: Text Self-Supervised CLIP for Medical Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoyu Jiang, Ziping Cong","submitted_at":"2026-07-24T04:34:10Z","abstract_excerpt":"Automating radiology report generation is important for improving reporting consistency and clinical workflows . While Contrastive Language--Image Pretraining (CLIP) has advanced medical vision language modeling, existing CLIP-style approaches may still provide insufficient fine-grained semantic supervision for complex report generation. Standard CLIP primarily optimizes cross-modal alignment, without explicitly structuring the textual embedding space that guides visual representation learning. To address this limitation, we propose TextSLIP, a general medical vision-language pretraining frame"},"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":"2607.21970","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-24T04:34:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"185a09376883f344ece060750843fd29638f04d8ef04e07752ef17ed29fcc19d","abstract_canon_sha256":"90309c7f4613c6a19c358e3136e852cdc51982bc3bdb7b69ff21bdfc93bf8199"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T00:20:30.575966Z","signature_b64":"ArR2V1299Rw8GRWM20DH5BJWPz1PkVxk5Lf8eQa3vsBfKJkQP9L/EQKuZgwvlkbv6IRbSNCdnciQPpoL3PZaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5aea9d3c5907856a24206f6c663e766eccf837d284585b74bcf32b240dd752f","last_reissued_at":"2026-07-27T00:20:30.575132Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T00:20:30.575132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextSLIP: Text Self-Supervised CLIP for Medical Report Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoyu Jiang, Ziping Cong","submitted_at":"2026-07-24T04:34:10Z","abstract_excerpt":"Automating radiology report generation is important for improving reporting consistency and clinical workflows . While Contrastive Language--Image Pretraining (CLIP) has advanced medical vision language modeling, existing CLIP-style approaches may still provide insufficient fine-grained semantic supervision for complex report generation. Standard CLIP primarily optimizes cross-modal alignment, without explicitly structuring the textual embedding space that guides visual representation learning. To address this limitation, we propose TextSLIP, a general medical vision-language pretraining frame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21970","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/2607.21970/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":"2607.21970","created_at":"2026-07-27T00:20:30.575566+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21970v1","created_at":"2026-07-27T00:20:30.575566+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21970","created_at":"2026-07-27T00:20:30.575566+00:00"},{"alias_kind":"pith_short_12","alias_value":"UWXKTU6FSB4F","created_at":"2026-07-27T00:20:30.575566+00:00"},{"alias_kind":"pith_short_16","alias_value":"UWXKTU6FSB4FNISC","created_at":"2026-07-27T00:20:30.575566+00:00"},{"alias_kind":"pith_short_8","alias_value":"UWXKTU6F","created_at":"2026-07-27T00:20:30.575566+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/UWXKTU6FSB4FNISCA33MMY7HM3","json":"https://pith.science/pith/UWXKTU6FSB4FNISCA33MMY7HM3.json","graph_json":"https://pith.science/api/pith-number/UWXKTU6FSB4FNISCA33MMY7HM3/graph.json","events_json":"https://pith.science/api/pith-number/UWXKTU6FSB4FNISCA33MMY7HM3/events.json","paper":"https://pith.science/paper/UWXKTU6F"},"agent_actions":{"view_html":"https://pith.science/pith/UWXKTU6FSB4FNISCA33MMY7HM3","download_json":"https://pith.science/pith/UWXKTU6FSB4FNISCA33MMY7HM3.json","view_paper":"https://pith.science/paper/UWXKTU6F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21970&json=true","fetch_graph":"https://pith.science/api/pith-number/UWXKTU6FSB4FNISCA33MMY7HM3/graph.json","fetch_events":"https://pith.science/api/pith-number/UWXKTU6FSB4FNISCA33MMY7HM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UWXKTU6FSB4FNISCA33MMY7HM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UWXKTU6FSB4FNISCA33MMY7HM3/action/storage_attestation","attest_author":"https://pith.science/pith/UWXKTU6FSB4FNISCA33MMY7HM3/action/author_attestation","sign_citation":"https://pith.science/pith/UWXKTU6FSB4FNISCA33MMY7HM3/action/citation_signature","submit_replication":"https://pith.science/pith/UWXKTU6FSB4FNISCA33MMY7HM3/action/replication_record"}},"created_at":"2026-07-27T00:20:30.575566+00:00","updated_at":"2026-07-27T00:20:30.575566+00:00"}