{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MCECVGM7Z7JFCM6AHTG3PG7V67","short_pith_number":"pith:MCECVGM7","schema_version":"1.0","canonical_sha256":"60882a999fcfd25133c03ccdb79bf5f7e368e485859d0f2516185518221e48c4","source":{"kind":"arxiv","id":"2501.05488","version":1},"attestation_state":"computed","paper":{"title":"EndoDINO: A Foundation Model for GI Endoscopy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Angad Kalra, Matt Schwartz, Patrick Dermyer","submitted_at":"2025-01-08T18:57:05Z","abstract_excerpt":"In this work, we present EndoDINO, a foundation model for GI endoscopy tasks that achieves strong generalizability by pre-training on a well-curated image dataset sampled from the largest known GI endoscopy video dataset in the literature. Specifically, we pre-trained ViT models with 1B, 307M, and 86M parameters using datasets ranging from 100K to 10M curated images. Using EndoDINO as a frozen feature encoder, we achieved state-of-the-art performance in anatomical landmark classification, polyp segmentation, and Mayo endoscopic scoring (MES) for ulcerative colitis with only simple decoder head"},"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":"2501.05488","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-08T18:57:05Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"9c2d6e0aa22e08785a6972d82ce718541b92ccabc1144644e3dc12c0e4602d17","abstract_canon_sha256":"b260e4606e0ebf17ce78ecec607b30b22bc7b3e08d469e161010044f52296211"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:15.410483Z","signature_b64":"on+67bYIf+JiW0snqMRb77EamIP8MXk5/GpvcRZ0S6tZtLtaRNoxqc3zwYQ0drpFbOC5iekPhKVs5GZn9JSfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60882a999fcfd25133c03ccdb79bf5f7e368e485859d0f2516185518221e48c4","last_reissued_at":"2026-07-05T10:36:15.409925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:15.409925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EndoDINO: A Foundation Model for GI Endoscopy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Angad Kalra, Matt Schwartz, Patrick Dermyer","submitted_at":"2025-01-08T18:57:05Z","abstract_excerpt":"In this work, we present EndoDINO, a foundation model for GI endoscopy tasks that achieves strong generalizability by pre-training on a well-curated image dataset sampled from the largest known GI endoscopy video dataset in the literature. Specifically, we pre-trained ViT models with 1B, 307M, and 86M parameters using datasets ranging from 100K to 10M curated images. Using EndoDINO as a frozen feature encoder, we achieved state-of-the-art performance in anatomical landmark classification, polyp segmentation, and Mayo endoscopic scoring (MES) for ulcerative colitis with only simple decoder head"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05488","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/2501.05488/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":"2501.05488","created_at":"2026-07-05T10:36:15.409989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05488v1","created_at":"2026-07-05T10:36:15.409989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05488","created_at":"2026-07-05T10:36:15.409989+00:00"},{"alias_kind":"pith_short_12","alias_value":"MCECVGM7Z7JF","created_at":"2026-07-05T10:36:15.409989+00:00"},{"alias_kind":"pith_short_16","alias_value":"MCECVGM7Z7JFCM6A","created_at":"2026-07-05T10:36:15.409989+00:00"},{"alias_kind":"pith_short_8","alias_value":"MCECVGM7","created_at":"2026-07-05T10:36:15.409989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17340","citing_title":"Geometry-Consistent Endoscopic Representations for Image-Guided Navigation via Structured Foundation Model Adaptation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05649","citing_title":"Analogical Reasoning as a Doctor: A Foundation Model for Gastrointestinal Endoscopy Diagnosis","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MCECVGM7Z7JFCM6AHTG3PG7V67","json":"https://pith.science/pith/MCECVGM7Z7JFCM6AHTG3PG7V67.json","graph_json":"https://pith.science/api/pith-number/MCECVGM7Z7JFCM6AHTG3PG7V67/graph.json","events_json":"https://pith.science/api/pith-number/MCECVGM7Z7JFCM6AHTG3PG7V67/events.json","paper":"https://pith.science/paper/MCECVGM7"},"agent_actions":{"view_html":"https://pith.science/pith/MCECVGM7Z7JFCM6AHTG3PG7V67","download_json":"https://pith.science/pith/MCECVGM7Z7JFCM6AHTG3PG7V67.json","view_paper":"https://pith.science/paper/MCECVGM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05488&json=true","fetch_graph":"https://pith.science/api/pith-number/MCECVGM7Z7JFCM6AHTG3PG7V67/graph.json","fetch_events":"https://pith.science/api/pith-number/MCECVGM7Z7JFCM6AHTG3PG7V67/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MCECVGM7Z7JFCM6AHTG3PG7V67/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MCECVGM7Z7JFCM6AHTG3PG7V67/action/storage_attestation","attest_author":"https://pith.science/pith/MCECVGM7Z7JFCM6AHTG3PG7V67/action/author_attestation","sign_citation":"https://pith.science/pith/MCECVGM7Z7JFCM6AHTG3PG7V67/action/citation_signature","submit_replication":"https://pith.science/pith/MCECVGM7Z7JFCM6AHTG3PG7V67/action/replication_record"}},"created_at":"2026-07-05T10:36:15.409989+00:00","updated_at":"2026-07-05T10:36:15.409989+00:00"}