{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M6AVXTTV5VBAZ7TBRQ2WHS5A35","short_pith_number":"pith:M6AVXTTV","schema_version":"1.0","canonical_sha256":"67815bce75ed420cfe618c3563cba0df7386b6df030df45485ce75f44554814e","source":{"kind":"arxiv","id":"2502.00832","version":1},"attestation_state":"computed","paper":{"title":"Generalization of Medical Large Language Models through Cross-Domain Weak Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eric Gonzalez, Harrison Fuller, Robert Long","submitted_at":"2025-02-02T16:05:23Z","abstract_excerpt":"The advancement of large language models (LLMs) has opened new frontiers in natural language processing, particularly in specialized domains like healthcare. In this paper, we propose the Incremental Curriculum-Based Fine-Tuning (ICFT) framework to enhance the generative capabilities of medical large language models (MLLMs). ICFT combines curriculum-based learning, dual-stage memory coordination, and parameter-efficient fine-tuning to enable a progressive transition from general linguistic knowledge to strong domain-specific expertise. Experimental results across diverse medical NLP tasks, inc"},"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":"2502.00832","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-02T16:05:23Z","cross_cats_sorted":[],"title_canon_sha256":"8ce7cc967da51a70c13a7e5b186bd0d2d217c6f756945fb83d134b1fecab1190","abstract_canon_sha256":"e03dbb26fe2c679b31ff94337907dd17028cc723d63c400649dd56e0e6b674b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:39.039499Z","signature_b64":"6KAOjbzYQHbOtd2SdArSnems8SvwP0GLoBQXfIYieyu3QayjVzLSV+n2PatQqKDVsrSchbKEZszGu7KKOuH2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67815bce75ed420cfe618c3563cba0df7386b6df030df45485ce75f44554814e","last_reissued_at":"2026-07-05T10:08:39.039066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:39.039066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalization of Medical Large Language Models through Cross-Domain Weak Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eric Gonzalez, Harrison Fuller, Robert Long","submitted_at":"2025-02-02T16:05:23Z","abstract_excerpt":"The advancement of large language models (LLMs) has opened new frontiers in natural language processing, particularly in specialized domains like healthcare. In this paper, we propose the Incremental Curriculum-Based Fine-Tuning (ICFT) framework to enhance the generative capabilities of medical large language models (MLLMs). ICFT combines curriculum-based learning, dual-stage memory coordination, and parameter-efficient fine-tuning to enable a progressive transition from general linguistic knowledge to strong domain-specific expertise. Experimental results across diverse medical NLP tasks, inc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00832","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/2502.00832/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":"2502.00832","created_at":"2026-07-05T10:08:39.039133+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00832v1","created_at":"2026-07-05T10:08:39.039133+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00832","created_at":"2026-07-05T10:08:39.039133+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6AVXTTV5VBA","created_at":"2026-07-05T10:08:39.039133+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6AVXTTV5VBAZ7TB","created_at":"2026-07-05T10:08:39.039133+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6AVXTTV","created_at":"2026-07-05T10:08:39.039133+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00014","citing_title":"SWE-Bench-CL: Continual Learning for Coding Agents","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6AVXTTV5VBAZ7TBRQ2WHS5A35","json":"https://pith.science/pith/M6AVXTTV5VBAZ7TBRQ2WHS5A35.json","graph_json":"https://pith.science/api/pith-number/M6AVXTTV5VBAZ7TBRQ2WHS5A35/graph.json","events_json":"https://pith.science/api/pith-number/M6AVXTTV5VBAZ7TBRQ2WHS5A35/events.json","paper":"https://pith.science/paper/M6AVXTTV"},"agent_actions":{"view_html":"https://pith.science/pith/M6AVXTTV5VBAZ7TBRQ2WHS5A35","download_json":"https://pith.science/pith/M6AVXTTV5VBAZ7TBRQ2WHS5A35.json","view_paper":"https://pith.science/paper/M6AVXTTV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00832&json=true","fetch_graph":"https://pith.science/api/pith-number/M6AVXTTV5VBAZ7TBRQ2WHS5A35/graph.json","fetch_events":"https://pith.science/api/pith-number/M6AVXTTV5VBAZ7TBRQ2WHS5A35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6AVXTTV5VBAZ7TBRQ2WHS5A35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6AVXTTV5VBAZ7TBRQ2WHS5A35/action/storage_attestation","attest_author":"https://pith.science/pith/M6AVXTTV5VBAZ7TBRQ2WHS5A35/action/author_attestation","sign_citation":"https://pith.science/pith/M6AVXTTV5VBAZ7TBRQ2WHS5A35/action/citation_signature","submit_replication":"https://pith.science/pith/M6AVXTTV5VBAZ7TBRQ2WHS5A35/action/replication_record"}},"created_at":"2026-07-05T10:08:39.039133+00:00","updated_at":"2026-07-05T10:08:39.039133+00:00"}