{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OUS2MOD46D7RZXWO3EMISLVQTM","short_pith_number":"pith:OUS2MOD4","schema_version":"1.0","canonical_sha256":"7525a6387cf0ff1cdeced918892eb09b02939ac84a21f652a6b827dbb2137a00","source":{"kind":"arxiv","id":"2310.11173","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Extraction and Distillation from Large-Scale Image-Text Colonoscopy Records Leveraging Large Language and Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Manning Wang, Peiyao Fu, Pinghong Zhou, Quanlin Li, Shuo Wang, Xiaoyuan Luo, Yan Zhu, Yike Guo, Yizhe Zhang, Zhijian Song, Zhiwei Yang","submitted_at":"2023-10-17T11:41:38Z","abstract_excerpt":"The development of artificial intelligence systems for colonoscopy analysis often necessitates expert-annotated image datasets. However, limitations in dataset size and diversity impede model performance and generalisation. Image-text colonoscopy records from routine clinical practice, comprising millions of images and text reports, serve as a valuable data source, though annotating them is labour-intensive. Here we leverage recent advancements in large language and vision models and propose EndoKED, a data mining paradigm for deep knowledge extraction and distillation. EndoKED automates the t"},"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":"2310.11173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-17T11:41:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2cae69ad07d4d5a77365d9e4cd019d241cd92496624c2e56c2543eaec52831c2","abstract_canon_sha256":"6132ab6a815278af105f00a0ed8c936940e7c94cb78134e91d57ba1d2e933b04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:51.632343Z","signature_b64":"G0d8mRycDct7NtXwyvp1uVQMljLZxIhzjIbL0nRDflAqVNf+6sG6NmeC0UnYo15bLZ25l+QozzOUFjJ+HAHIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7525a6387cf0ff1cdeced918892eb09b02939ac84a21f652a6b827dbb2137a00","last_reissued_at":"2026-07-05T07:01:51.631683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:51.631683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Extraction and Distillation from Large-Scale Image-Text Colonoscopy Records Leveraging Large Language and Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Manning Wang, Peiyao Fu, Pinghong Zhou, Quanlin Li, Shuo Wang, Xiaoyuan Luo, Yan Zhu, Yike Guo, Yizhe Zhang, Zhijian Song, Zhiwei Yang","submitted_at":"2023-10-17T11:41:38Z","abstract_excerpt":"The development of artificial intelligence systems for colonoscopy analysis often necessitates expert-annotated image datasets. However, limitations in dataset size and diversity impede model performance and generalisation. Image-text colonoscopy records from routine clinical practice, comprising millions of images and text reports, serve as a valuable data source, though annotating them is labour-intensive. Here we leverage recent advancements in large language and vision models and propose EndoKED, a data mining paradigm for deep knowledge extraction and distillation. EndoKED automates the t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11173","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/2310.11173/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":"2310.11173","created_at":"2026-07-05T07:01:51.631776+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.11173v1","created_at":"2026-07-05T07:01:51.631776+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11173","created_at":"2026-07-05T07:01:51.631776+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUS2MOD46D7R","created_at":"2026-07-05T07:01:51.631776+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUS2MOD46D7RZXWO","created_at":"2026-07-05T07:01:51.631776+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUS2MOD4","created_at":"2026-07-05T07:01:51.631776+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.04381","citing_title":"Enabling Real-Time Colonoscopic Polyp Segmentation on Commodity CPUs via Ultra-Lightweight Architecture","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OUS2MOD46D7RZXWO3EMISLVQTM","json":"https://pith.science/pith/OUS2MOD46D7RZXWO3EMISLVQTM.json","graph_json":"https://pith.science/api/pith-number/OUS2MOD46D7RZXWO3EMISLVQTM/graph.json","events_json":"https://pith.science/api/pith-number/OUS2MOD46D7RZXWO3EMISLVQTM/events.json","paper":"https://pith.science/paper/OUS2MOD4"},"agent_actions":{"view_html":"https://pith.science/pith/OUS2MOD46D7RZXWO3EMISLVQTM","download_json":"https://pith.science/pith/OUS2MOD46D7RZXWO3EMISLVQTM.json","view_paper":"https://pith.science/paper/OUS2MOD4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.11173&json=true","fetch_graph":"https://pith.science/api/pith-number/OUS2MOD46D7RZXWO3EMISLVQTM/graph.json","fetch_events":"https://pith.science/api/pith-number/OUS2MOD46D7RZXWO3EMISLVQTM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUS2MOD46D7RZXWO3EMISLVQTM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUS2MOD46D7RZXWO3EMISLVQTM/action/storage_attestation","attest_author":"https://pith.science/pith/OUS2MOD46D7RZXWO3EMISLVQTM/action/author_attestation","sign_citation":"https://pith.science/pith/OUS2MOD46D7RZXWO3EMISLVQTM/action/citation_signature","submit_replication":"https://pith.science/pith/OUS2MOD46D7RZXWO3EMISLVQTM/action/replication_record"}},"created_at":"2026-07-05T07:01:51.631776+00:00","updated_at":"2026-07-05T07:01:51.631776+00:00"}