{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BYU7DYZOMKL754CXFI64U6LWB5","short_pith_number":"pith:BYU7DYZO","schema_version":"1.0","canonical_sha256":"0e29f1e32e6297fef0572a3dca79760f601ad2d84ac99fb17bf8c32028e2e271","source":{"kind":"arxiv","id":"2508.11673","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Regularization over LoRA for Multimodal Biomedical Image Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.MM"],"primary_cat":"cs.LG","authors_text":"Haojie Zhang, Hulin Kuang, Lihui Cen, Min Zeng, Shichao Kan, Yigang Cen, Yixiong Liang, Zhe Qu","submitted_at":"2025-08-08T01:10:06Z","abstract_excerpt":"Multimodal Biomedical Image Incremental Learning (MBIIL) is essential for handling diverse tasks and modalities in the biomedical domain, as training separate models for each modality or task significantly increases inference costs. Existing incremental learning methods focus on task expansion within a single modality, whereas MBIIL seeks to train a unified model incrementally across modalities. The MBIIL faces two challenges: I) How to preserve previously learned knowledge during incremental updates? II) How to effectively leverage knowledge acquired from existing modalities to support new mo"},"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":"2508.11673","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-08T01:10:06Z","cross_cats_sorted":["cs.AI","cs.CV","cs.MM"],"title_canon_sha256":"6201783c27b60afb9cd1569b8e13e3aa3e69386675e63fea73f496d366255ff0","abstract_canon_sha256":"142c49904cf7bb5fbfc70d183b0f2ae6afd2492f3755cad83e66f9da0fb80f28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:52.160982Z","signature_b64":"ZF+E6iQRGRXrtWFUrfsf58EvIBeP8662Qom+y5LdZzOj/ChlBVHv+SkAiLaRKs3i0C5ogY6e62OAWRs/xO8GAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e29f1e32e6297fef0572a3dca79760f601ad2d84ac99fb17bf8c32028e2e271","last_reissued_at":"2026-07-05T11:54:52.160593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:52.160593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Regularization over LoRA for Multimodal Biomedical Image Incremental Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.MM"],"primary_cat":"cs.LG","authors_text":"Haojie Zhang, Hulin Kuang, Lihui Cen, Min Zeng, Shichao Kan, Yigang Cen, Yixiong Liang, Zhe Qu","submitted_at":"2025-08-08T01:10:06Z","abstract_excerpt":"Multimodal Biomedical Image Incremental Learning (MBIIL) is essential for handling diverse tasks and modalities in the biomedical domain, as training separate models for each modality or task significantly increases inference costs. Existing incremental learning methods focus on task expansion within a single modality, whereas MBIIL seeks to train a unified model incrementally across modalities. The MBIIL faces two challenges: I) How to preserve previously learned knowledge during incremental updates? II) How to effectively leverage knowledge acquired from existing modalities to support new mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11673","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/2508.11673/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":"2508.11673","created_at":"2026-07-05T11:54:52.160649+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11673v1","created_at":"2026-07-05T11:54:52.160649+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11673","created_at":"2026-07-05T11:54:52.160649+00:00"},{"alias_kind":"pith_short_12","alias_value":"BYU7DYZOMKL7","created_at":"2026-07-05T11:54:52.160649+00:00"},{"alias_kind":"pith_short_16","alias_value":"BYU7DYZOMKL754CX","created_at":"2026-07-05T11:54:52.160649+00:00"},{"alias_kind":"pith_short_8","alias_value":"BYU7DYZO","created_at":"2026-07-05T11:54:52.160649+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BYU7DYZOMKL754CXFI64U6LWB5","json":"https://pith.science/pith/BYU7DYZOMKL754CXFI64U6LWB5.json","graph_json":"https://pith.science/api/pith-number/BYU7DYZOMKL754CXFI64U6LWB5/graph.json","events_json":"https://pith.science/api/pith-number/BYU7DYZOMKL754CXFI64U6LWB5/events.json","paper":"https://pith.science/paper/BYU7DYZO"},"agent_actions":{"view_html":"https://pith.science/pith/BYU7DYZOMKL754CXFI64U6LWB5","download_json":"https://pith.science/pith/BYU7DYZOMKL754CXFI64U6LWB5.json","view_paper":"https://pith.science/paper/BYU7DYZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11673&json=true","fetch_graph":"https://pith.science/api/pith-number/BYU7DYZOMKL754CXFI64U6LWB5/graph.json","fetch_events":"https://pith.science/api/pith-number/BYU7DYZOMKL754CXFI64U6LWB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BYU7DYZOMKL754CXFI64U6LWB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BYU7DYZOMKL754CXFI64U6LWB5/action/storage_attestation","attest_author":"https://pith.science/pith/BYU7DYZOMKL754CXFI64U6LWB5/action/author_attestation","sign_citation":"https://pith.science/pith/BYU7DYZOMKL754CXFI64U6LWB5/action/citation_signature","submit_replication":"https://pith.science/pith/BYU7DYZOMKL754CXFI64U6LWB5/action/replication_record"}},"created_at":"2026-07-05T11:54:52.160649+00:00","updated_at":"2026-07-05T11:54:52.160649+00:00"}