{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YEJ7RVX3ZUSJ62KY2EMPWXT33N","short_pith_number":"pith:YEJ7RVX3","canonical_record":{"source":{"id":"2410.17827","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-23T12:40:33Z","cross_cats_sorted":[],"title_canon_sha256":"dd24668804713e0bf1b1f779d336dd4f0af724c1194a4af7e51485158aefa071","abstract_canon_sha256":"844c192184b7841d2fe653e75c0a6838d5a97f614c034d321131203274cfb680"},"schema_version":"1.0"},"canonical_sha256":"c113f8d6fbcd249f6958d118fb5e7bdb74946b0afaeedc2e6eaa31479e2e5533","source":{"kind":"arxiv","id":"2410.17827","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17827","created_at":"2026-07-05T09:24:45Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17827v1","created_at":"2026-07-05T09:24:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17827","created_at":"2026-07-05T09:24:45Z"},{"alias_kind":"pith_short_12","alias_value":"YEJ7RVX3ZUSJ","created_at":"2026-07-05T09:24:45Z"},{"alias_kind":"pith_short_16","alias_value":"YEJ7RVX3ZUSJ62KY","created_at":"2026-07-05T09:24:45Z"},{"alias_kind":"pith_short_8","alias_value":"YEJ7RVX3","created_at":"2026-07-05T09:24:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YEJ7RVX3ZUSJ62KY2EMPWXT33N","target":"record","payload":{"canonical_record":{"source":{"id":"2410.17827","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-23T12:40:33Z","cross_cats_sorted":[],"title_canon_sha256":"dd24668804713e0bf1b1f779d336dd4f0af724c1194a4af7e51485158aefa071","abstract_canon_sha256":"844c192184b7841d2fe653e75c0a6838d5a97f614c034d321131203274cfb680"},"schema_version":"1.0"},"canonical_sha256":"c113f8d6fbcd249f6958d118fb5e7bdb74946b0afaeedc2e6eaa31479e2e5533","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:45.533851Z","signature_b64":"tyBV21ckNrLmztU17Q+a2PbW5jqmfcp9jx41Gog9dM9ISrVqV/qRwebWR+igw/pEJPNDnhCYQ6pxRp0UPoCOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c113f8d6fbcd249f6958d118fb5e7bdb74946b0afaeedc2e6eaa31479e2e5533","last_reissued_at":"2026-07-05T09:24:45.533351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:45.533351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.17827","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:24:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1v2CDGowWw9L0Nl7nD8Ft09lZmNQpSlMdWymee6WbpX9ywNKEtCVDbA8C/KVFgVlPt/8mhLPjc3c9umWHSCxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:22:21.099028Z"},"content_sha256":"a1f203eae2c650c671148465a8613ae38666c0e1636b60ebfc915cc3afb0dffc","schema_version":"1.0","event_id":"sha256:a1f203eae2c650c671148465a8613ae38666c0e1636b60ebfc915cc3afb0dffc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YEJ7RVX3ZUSJ62KY2EMPWXT33N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RE-tune: Incremental Fine Tuning of Biomedical Vision-Language Models for Multi-label Chest X-ray Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Andrew D. Bagdanov, Marco Mistretta","submitted_at":"2024-10-23T12:40:33Z","abstract_excerpt":"In this paper we introduce RE-tune, a novel approach for fine-tuning pre-trained Multimodal Biomedical Vision-Language models (VLMs) in Incremental Learning scenarios for multi-label chest disease diagnosis. RE-tune freezes the backbones and only trains simple adaptors on top of the Image and Text encoders of the VLM. By engineering positive and negative text prompts for diseases, we leverage the ability of Large Language Models to steer the training trajectory. We evaluate RE-tune in three realistic incremental learning scenarios: class-incremental, label-incremental, and data-incremental. Ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17827","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/2410.17827/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:24:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H3CNZ22HF0WkuSYLEFSYjgxk/DGu2qOOz2ZTntgk5UyX1L4UBALCWFaKO9ZchP1m/Qv9OyaHx52VGSulOG2lBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:22:21.100301Z"},"content_sha256":"8ed57a314c7d395fd0f5ca5c447d0a9d4461530486656cb4e3f99bca591861f8","schema_version":"1.0","event_id":"sha256:8ed57a314c7d395fd0f5ca5c447d0a9d4461530486656cb4e3f99bca591861f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YEJ7RVX3ZUSJ62KY2EMPWXT33N/bundle.json","state_url":"https://pith.science/pith/YEJ7RVX3ZUSJ62KY2EMPWXT33N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YEJ7RVX3ZUSJ62KY2EMPWXT33N/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T20:22:21Z","links":{"resolver":"https://pith.science/pith/YEJ7RVX3ZUSJ62KY2EMPWXT33N","bundle":"https://pith.science/pith/YEJ7RVX3ZUSJ62KY2EMPWXT33N/bundle.json","state":"https://pith.science/pith/YEJ7RVX3ZUSJ62KY2EMPWXT33N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YEJ7RVX3ZUSJ62KY2EMPWXT33N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YEJ7RVX3ZUSJ62KY2EMPWXT33N","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":"844c192184b7841d2fe653e75c0a6838d5a97f614c034d321131203274cfb680","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-23T12:40:33Z","title_canon_sha256":"dd24668804713e0bf1b1f779d336dd4f0af724c1194a4af7e51485158aefa071"},"schema_version":"1.0","source":{"id":"2410.17827","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17827","created_at":"2026-07-05T09:24:45Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17827v1","created_at":"2026-07-05T09:24:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17827","created_at":"2026-07-05T09:24:45Z"},{"alias_kind":"pith_short_12","alias_value":"YEJ7RVX3ZUSJ","created_at":"2026-07-05T09:24:45Z"},{"alias_kind":"pith_short_16","alias_value":"YEJ7RVX3ZUSJ62KY","created_at":"2026-07-05T09:24:45Z"},{"alias_kind":"pith_short_8","alias_value":"YEJ7RVX3","created_at":"2026-07-05T09:24:45Z"}],"graph_snapshots":[{"event_id":"sha256:8ed57a314c7d395fd0f5ca5c447d0a9d4461530486656cb4e3f99bca591861f8","target":"graph","created_at":"2026-07-05T09:24:45Z","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/2410.17827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper we introduce RE-tune, a novel approach for fine-tuning pre-trained Multimodal Biomedical Vision-Language models (VLMs) in Incremental Learning scenarios for multi-label chest disease diagnosis. RE-tune freezes the backbones and only trains simple adaptors on top of the Image and Text encoders of the VLM. By engineering positive and negative text prompts for diseases, we leverage the ability of Large Language Models to steer the training trajectory. We evaluate RE-tune in three realistic incremental learning scenarios: class-incremental, label-incremental, and data-incremental. Ou","authors_text":"Andrew D. Bagdanov, Marco Mistretta","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-23T12:40:33Z","title":"RE-tune: Incremental Fine Tuning of Biomedical Vision-Language Models for Multi-label Chest X-ray Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17827","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:a1f203eae2c650c671148465a8613ae38666c0e1636b60ebfc915cc3afb0dffc","target":"record","created_at":"2026-07-05T09:24:45Z","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":"844c192184b7841d2fe653e75c0a6838d5a97f614c034d321131203274cfb680","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-23T12:40:33Z","title_canon_sha256":"dd24668804713e0bf1b1f779d336dd4f0af724c1194a4af7e51485158aefa071"},"schema_version":"1.0","source":{"id":"2410.17827","kind":"arxiv","version":1}},"canonical_sha256":"c113f8d6fbcd249f6958d118fb5e7bdb74946b0afaeedc2e6eaa31479e2e5533","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c113f8d6fbcd249f6958d118fb5e7bdb74946b0afaeedc2e6eaa31479e2e5533","first_computed_at":"2026-07-05T09:24:45.533351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:24:45.533351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tyBV21ckNrLmztU17Q+a2PbW5jqmfcp9jx41Gog9dM9ISrVqV/qRwebWR+igw/pEJPNDnhCYQ6pxRp0UPoCOAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:24:45.533851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.17827","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1f203eae2c650c671148465a8613ae38666c0e1636b60ebfc915cc3afb0dffc","sha256:8ed57a314c7d395fd0f5ca5c447d0a9d4461530486656cb4e3f99bca591861f8"],"state_sha256":"7988b69831ea4f98690c4bea60373db2e4dcae74aa5acd35b8ff9cecd3b49bf5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gj8VxZNyF/2n+nWJHfAum/GYnmZFlGKjAKT4T6fJvGtL5XUpGR3E/h9kj3cfhpeg4+2Tm2jWOG0A1V/QbCKnBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:22:21.106988Z","bundle_sha256":"354c39b3ccd8c8c8a81364cb750011dd09dfcb7b1fe0912232dd037ef41bcba5"}}