{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XPIIMNMIVTFJ3ZE75HC5SVHBZV","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":"6973e137599d4de3dc1471521cf1e0736af2c38f99725efdc7e59f576918d8bc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T09:03:39Z","title_canon_sha256":"5f7f20f7af2d9dd5c29b79ee3e365e61d788d1c0d182e3e6cdf0624927eb88c6"},"schema_version":"1.0","source":{"id":"2509.00752","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00752","created_at":"2026-07-05T12:02:22Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00752v1","created_at":"2026-07-05T12:02:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00752","created_at":"2026-07-05T12:02:22Z"},{"alias_kind":"pith_short_12","alias_value":"XPIIMNMIVTFJ","created_at":"2026-07-05T12:02:22Z"},{"alias_kind":"pith_short_16","alias_value":"XPIIMNMIVTFJ3ZE7","created_at":"2026-07-05T12:02:22Z"},{"alias_kind":"pith_short_8","alias_value":"XPIIMNMI","created_at":"2026-07-05T12:02:22Z"}],"graph_snapshots":[{"event_id":"sha256:03126bcd124368b488776cfdcf722c1c0a653898e741177f40e23e64f46b4784","target":"graph","created_at":"2026-07-05T12:02:22Z","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/2509.00752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a unified vision-language framework tailored for ENT endoscopy image analysis that simultaneously tackles three clinically-relevant tasks: image classification, image-to-image retrieval, and text-to-image retrieval. Unlike conventional CNN-based pipelines that struggle to capture cross-modal semantics, our approach leverages the CLIP ViT-B/16 backbone and enhances it through Low-Rank Adaptation, multi-level CLS token aggregation, and spherical feature interpolation. These components collectively enable efficient fine-tuning on limited medical data while improving representation dive","authors_text":"Doan Anh Phan Huu, Nhat Nam Mai, Thao Thi Phuong Dao, Trung-Nghia Le, Trung Thai Tran, Van Toi Giap, Y Hop Nguyen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T09:03:39Z","title":"Multi-Level CLS Token Fusion for Contrastive Learning in Endoscopy Image Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00752","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:f89aa52f6ff9df258a08956e840d6b3fef5bda6d80aa675167b1823a8a5be286","target":"record","created_at":"2026-07-05T12:02:22Z","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":"6973e137599d4de3dc1471521cf1e0736af2c38f99725efdc7e59f576918d8bc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-31T09:03:39Z","title_canon_sha256":"5f7f20f7af2d9dd5c29b79ee3e365e61d788d1c0d182e3e6cdf0624927eb88c6"},"schema_version":"1.0","source":{"id":"2509.00752","kind":"arxiv","version":1}},"canonical_sha256":"bbd0863588acca9de49fe9c5d954e1cd7f93f7cb56846b95aba65931f61fe89e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbd0863588acca9de49fe9c5d954e1cd7f93f7cb56846b95aba65931f61fe89e","first_computed_at":"2026-07-05T12:02:22.300356Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:22.300356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+hr5Hjp+abWJtKq0zo3qp7VhB2csx0RhK3oAs9wpmW1TK3sXVt74iEbhxESickLSRoLaL8RXsNC7aaabyZtBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:22.300917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00752","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f89aa52f6ff9df258a08956e840d6b3fef5bda6d80aa675167b1823a8a5be286","sha256:03126bcd124368b488776cfdcf722c1c0a653898e741177f40e23e64f46b4784"],"state_sha256":"0c6f89bd71bde3399da6cae016402762b785c86c4a8ecfe8453f699bfee6a47c"}