{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GJ6GABHNFHVC2U3PQU242OXUTY","short_pith_number":"pith:GJ6GABHN","schema_version":"1.0","canonical_sha256":"327c6004ed29ea2d536f8535cd3af49e365eaa5c035b1f9f887e6d16d8c22c97","source":{"kind":"arxiv","id":"2606.22079","version":1},"attestation_state":"computed","paper":{"title":"Where Does the Signal Live? A Web Data Recipe for Medical Encoder Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bofeng Huang, Diane Bouchacourt, Fajwel Fogel, Jacques Sun, Nicolas Barascud","submitted_at":"2026-06-20T14:54:27Z","abstract_excerpt":"Web data curation has been widely studied for decoder Large Language Model (LLM) pretraining. Encoders for dense-terminology domains such as medicine, by contrast, are pretrained on small, manually-curated corpora that limit scalability and writing style diversity, a bottleneck even more severe in non-English clinical settings. Whether web-scale data curation also benefits encoder Masked Language Modeling (MLM) in a dense-terminology domain remains an open question. To address this, we introduce two complementary levers. Medical-term density filtering selects documents rich in medical terms. S"},"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":"2606.22079","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-20T14:54:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"895c8845fcef97fbbb74a784a5dd85249d2ef1c30cd136e1e0aec878dcfab82a","abstract_canon_sha256":"9ba402a0d47121af607d89358e1b5d6af3b7774e17f45c988e170b4e067dc6f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:27.639868Z","signature_b64":"iIL4biptOouvbEWZft9kGFK7UA4+wsrVcqOLTqpkfTUSCwd8tylf0739Yx3+wAfCDBecT44xYgv2iqbS559ACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"327c6004ed29ea2d536f8535cd3af49e365eaa5c035b1f9f887e6d16d8c22c97","last_reissued_at":"2026-06-23T02:13:27.639466Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:27.639466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Where Does the Signal Live? A Web Data Recipe for Medical Encoder Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bofeng Huang, Diane Bouchacourt, Fajwel Fogel, Jacques Sun, Nicolas Barascud","submitted_at":"2026-06-20T14:54:27Z","abstract_excerpt":"Web data curation has been widely studied for decoder Large Language Model (LLM) pretraining. Encoders for dense-terminology domains such as medicine, by contrast, are pretrained on small, manually-curated corpora that limit scalability and writing style diversity, a bottleneck even more severe in non-English clinical settings. Whether web-scale data curation also benefits encoder Masked Language Modeling (MLM) in a dense-terminology domain remains an open question. To address this, we introduce two complementary levers. Medical-term density filtering selects documents rich in medical terms. S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22079","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/2606.22079/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":"2606.22079","created_at":"2026-06-23T02:13:27.639521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22079v1","created_at":"2026-06-23T02:13:27.639521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22079","created_at":"2026-06-23T02:13:27.639521+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJ6GABHNFHVC","created_at":"2026-06-23T02:13:27.639521+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJ6GABHNFHVC2U3P","created_at":"2026-06-23T02:13:27.639521+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJ6GABHN","created_at":"2026-06-23T02:13:27.639521+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/GJ6GABHNFHVC2U3PQU242OXUTY","json":"https://pith.science/pith/GJ6GABHNFHVC2U3PQU242OXUTY.json","graph_json":"https://pith.science/api/pith-number/GJ6GABHNFHVC2U3PQU242OXUTY/graph.json","events_json":"https://pith.science/api/pith-number/GJ6GABHNFHVC2U3PQU242OXUTY/events.json","paper":"https://pith.science/paper/GJ6GABHN"},"agent_actions":{"view_html":"https://pith.science/pith/GJ6GABHNFHVC2U3PQU242OXUTY","download_json":"https://pith.science/pith/GJ6GABHNFHVC2U3PQU242OXUTY.json","view_paper":"https://pith.science/paper/GJ6GABHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22079&json=true","fetch_graph":"https://pith.science/api/pith-number/GJ6GABHNFHVC2U3PQU242OXUTY/graph.json","fetch_events":"https://pith.science/api/pith-number/GJ6GABHNFHVC2U3PQU242OXUTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJ6GABHNFHVC2U3PQU242OXUTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJ6GABHNFHVC2U3PQU242OXUTY/action/storage_attestation","attest_author":"https://pith.science/pith/GJ6GABHNFHVC2U3PQU242OXUTY/action/author_attestation","sign_citation":"https://pith.science/pith/GJ6GABHNFHVC2U3PQU242OXUTY/action/citation_signature","submit_replication":"https://pith.science/pith/GJ6GABHNFHVC2U3PQU242OXUTY/action/replication_record"}},"created_at":"2026-06-23T02:13:27.639521+00:00","updated_at":"2026-06-23T02:13:27.639521+00:00"}