{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZSCIZM34IJWTWSCJJWFHKTECEQ","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":"7f9a5db56b27a66bdccb4fa874fce4d2d28d8eca35a92b5baca199345374ab18","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T05:56:41Z","title_canon_sha256":"36935922f67605ba4372894817784a60a328ee7a789ac1a686ffdae8918087a1"},"schema_version":"1.0","source":{"id":"2608.04472","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04472","created_at":"2026-08-06T01:35:40Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04472v1","created_at":"2026-08-06T01:35:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04472","created_at":"2026-08-06T01:35:40Z"},{"alias_kind":"pith_short_12","alias_value":"ZSCIZM34IJWT","created_at":"2026-08-06T01:35:40Z"},{"alias_kind":"pith_short_16","alias_value":"ZSCIZM34IJWTWSCJ","created_at":"2026-08-06T01:35:40Z"},{"alias_kind":"pith_short_8","alias_value":"ZSCIZM34","created_at":"2026-08-06T01:35:40Z"}],"graph_snapshots":[{"event_id":"sha256:26729d06a0ab798c8c65bc970ed098f5b6b135552e01f3ce7e7bc1515627cee3","target":"graph","created_at":"2026-08-06T01:35:40Z","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/2608.04472/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The development of foundation models (FMs) is crucial for advancing endoscopic image analysis. However, existing endoscopy FMs mainly rely on self-supervised learning from uni-modal images or videos, overlooking the rich semantic knowledge contained in clinical reports. Furthermore, effectively leveraging these records is hindered by a fundamental modality gap: structured anatomical descriptions are not naturally mapped to specific frames within the high-redundancy, uncurated visual streams. In this paper, we present EndoVLM, a novel vision-language FM pre-trained on over 348K endoscopic exami","authors_text":"Bin Lv, Jianwei Xu, Liang Huang, Ling Zhang, Sijing Li, Yingda Xia, Yue Hu, Zhenyu Yi, Zhongwei Qiu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T05:56:41Z","title":"EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04472","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:e49e6174936a3ad01c2ce701c7530aaa7ca6a599400a61b682e8db4d00f82910","target":"record","created_at":"2026-08-06T01:35:40Z","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":"7f9a5db56b27a66bdccb4fa874fce4d2d28d8eca35a92b5baca199345374ab18","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T05:56:41Z","title_canon_sha256":"36935922f67605ba4372894817784a60a328ee7a789ac1a686ffdae8918087a1"},"schema_version":"1.0","source":{"id":"2608.04472","kind":"arxiv","version":1}},"canonical_sha256":"cc848cb37c426d3b48494d8a754c8224317cc855cf11a9e8e3c1f8189fa42a43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc848cb37c426d3b48494d8a754c8224317cc855cf11a9e8e3c1f8189fa42a43","first_computed_at":"2026-08-06T01:35:40.389999Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:35:40.389999Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MGwG1DNHUEWZ6kdvaXvTU5HHmyos+cC61sq6yPS5Psg1Y9qfzy/+qexG1iS77dpRXsxluokyEj1VZFhLVPPXBA==","signature_status":"signed_v1","signed_at":"2026-08-06T01:35:40.391519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.04472","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e49e6174936a3ad01c2ce701c7530aaa7ca6a599400a61b682e8db4d00f82910","sha256:26729d06a0ab798c8c65bc970ed098f5b6b135552e01f3ce7e7bc1515627cee3"],"state_sha256":"317e76041b51e5c80992cda8be0043c6edc8cb673c5fdb8f3ebd933a8f2e4841"}