{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:J67KGPM3BJSJ7VGHFAHNPSIEXZ","short_pith_number":"pith:J67KGPM3","schema_version":"1.0","canonical_sha256":"4fbea33d9b0a649fd4c7280ed7c904be5dde79d82c2af6611136368962524c0c","source":{"kind":"arxiv","id":"2607.27490","version":1},"attestation_state":"computed","paper":{"title":"MedLLM: An Open Medical Language Model at the Sub-Billion Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Asim Ahmed, Maxx Richard Rahman, Mihan Mohagheghzadeh, Wolfgang Maass","submitted_at":"2026-07-29T22:10:40Z","abstract_excerpt":"Open medical language models have converged on a single scale: every widely used system runs at 7B parameters or more, leaving the sub-billion regime uncharacterized. We present MedLLM, an open 0.1B-parameter medical language model trained through a fully open three-phase pipeline: general pretraining with curriculum sequence-length scheduling, domain fine-tuning on MedFineWeb, a reference-guided medical corpus we release that is selected from general web data by embedding similarity to medical question-answering (QA) data, and preference-aligned fine-tuning combining SFT with direct preferenc"},"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":"2607.27490","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-29T22:10:40Z","cross_cats_sorted":[],"title_canon_sha256":"87da4edfec1788dad56f7f9950229ca9153bc98d7f360af5506ee02182c35729","abstract_canon_sha256":"e748327fd260823c85c2b7dbc65fc4aaca63149ad1542ad9c58302681841c94d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fbea33d9b0a649fd4c7280ed7c904be5dde79d82c2af6611136368962524c0c","last_reissued_at":"2026-07-31T01:24:14.808147Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:24:14.808147Z"},"graph_snapshot":{"paper":{"title":"MedLLM: An Open Medical Language Model at the Sub-Billion Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Asim Ahmed, Maxx Richard Rahman, Mihan Mohagheghzadeh, Wolfgang Maass","submitted_at":"2026-07-29T22:10:40Z","abstract_excerpt":"Open medical language models have converged on a single scale: every widely used system runs at 7B parameters or more, leaving the sub-billion regime uncharacterized. We present MedLLM, an open 0.1B-parameter medical language model trained through a fully open three-phase pipeline: general pretraining with curriculum sequence-length scheduling, domain fine-tuning on MedFineWeb, a reference-guided medical corpus we release that is selected from general web data by embedding similarity to medical question-answering (QA) data, and preference-aligned fine-tuning combining SFT with direct preferenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27490","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/2607.27490/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":"2607.27490","created_at":"2026-07-31T01:24:14.811221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27490v1","created_at":"2026-07-31T01:24:14.811221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27490","created_at":"2026-07-31T01:24:14.811221+00:00"},{"alias_kind":"pith_short_12","alias_value":"J67KGPM3BJSJ","created_at":"2026-07-31T01:24:14.811221+00:00"},{"alias_kind":"pith_short_16","alias_value":"J67KGPM3BJSJ7VGH","created_at":"2026-07-31T01:24:14.811221+00:00"},{"alias_kind":"pith_short_8","alias_value":"J67KGPM3","created_at":"2026-07-31T01:24:14.811221+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/J67KGPM3BJSJ7VGHFAHNPSIEXZ","json":"https://pith.science/pith/J67KGPM3BJSJ7VGHFAHNPSIEXZ.json","graph_json":"https://pith.science/api/pith-number/J67KGPM3BJSJ7VGHFAHNPSIEXZ/graph.json","events_json":"https://pith.science/api/pith-number/J67KGPM3BJSJ7VGHFAHNPSIEXZ/events.json","paper":"https://pith.science/paper/J67KGPM3"},"agent_actions":{"view_html":"https://pith.science/pith/J67KGPM3BJSJ7VGHFAHNPSIEXZ","download_json":"https://pith.science/pith/J67KGPM3BJSJ7VGHFAHNPSIEXZ.json","view_paper":"https://pith.science/paper/J67KGPM3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27490&json=true","fetch_graph":"https://pith.science/api/pith-number/J67KGPM3BJSJ7VGHFAHNPSIEXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/J67KGPM3BJSJ7VGHFAHNPSIEXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J67KGPM3BJSJ7VGHFAHNPSIEXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J67KGPM3BJSJ7VGHFAHNPSIEXZ/action/storage_attestation","attest_author":"https://pith.science/pith/J67KGPM3BJSJ7VGHFAHNPSIEXZ/action/author_attestation","sign_citation":"https://pith.science/pith/J67KGPM3BJSJ7VGHFAHNPSIEXZ/action/citation_signature","submit_replication":"https://pith.science/pith/J67KGPM3BJSJ7VGHFAHNPSIEXZ/action/replication_record"}},"created_at":"2026-07-31T01:24:14.811221+00:00","updated_at":"2026-07-31T01:24:14.811221+00:00"}