{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4KGRP4UOUIG4ZQKPLHYNGLF4U2","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":"63b41d5f554017276c9c2135dca7528563ae01e8315ec24562ed070a7eb9fddb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T13:59:48Z","title_canon_sha256":"78040856d04769eefc3a09d848bd18a9172b68035d68947914543d2c317daa67"},"schema_version":"1.0","source":{"id":"2409.02725","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02725","created_at":"2026-07-05T09:03:09Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02725v1","created_at":"2026-07-05T09:03:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02725","created_at":"2026-07-05T09:03:09Z"},{"alias_kind":"pith_short_12","alias_value":"4KGRP4UOUIG4","created_at":"2026-07-05T09:03:09Z"},{"alias_kind":"pith_short_16","alias_value":"4KGRP4UOUIG4ZQKP","created_at":"2026-07-05T09:03:09Z"},{"alias_kind":"pith_short_8","alias_value":"4KGRP4UO","created_at":"2026-07-05T09:03:09Z"}],"graph_snapshots":[{"event_id":"sha256:9b23e7edc70c1780be6a731092ddbcd20bd12b26306a9ce0299ae231330b4f42","target":"graph","created_at":"2026-07-05T09:03:09Z","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/2409.02725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Domain adaptation is a widely used method in natural language processing (NLP) to improve the performance of a language model within a specific domain. This method is particularly common in the biomedical domain, which sees regular publication of numerous scientific articles. PubMed, a significant corpus of text, is frequently used in the biomedical domain. The primary objective of this study is to explore whether refining a pre-training dataset using specific quality metrics for scientific papers can enhance the performance of the resulting model. To accomplish this, we employ two straightfor","authors_text":"Mathieu La\\\"i-king, Patrick Paroubek","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T13:59:48Z","title":"Pre-training data selection for biomedical domain adaptation using journal impact metrics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02725","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":"sha256:0bc45ecc356a69213be8844d4e70d508d95b86505e02eeadb36f3132faed0753","target":"record","created_at":"2026-07-05T09:03:09Z","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":"63b41d5f554017276c9c2135dca7528563ae01e8315ec24562ed070a7eb9fddb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T13:59:48Z","title_canon_sha256":"78040856d04769eefc3a09d848bd18a9172b68035d68947914543d2c317daa67"},"schema_version":"1.0","source":{"id":"2409.02725","kind":"arxiv","version":1}},"canonical_sha256":"e28d17f28ea20dccc14f59f0d32cbca68c843d678439fc9e6967f11d45c6932d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e28d17f28ea20dccc14f59f0d32cbca68c843d678439fc9e6967f11d45c6932d","first_computed_at":"2026-07-05T09:03:09.274146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:09.274146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uijxt9Mc6pxhPGEOG3svmu3ImGD8AjHFx57UldevtuxKiQZLCv7G+ALHwxbiHxdR7XNJPbxH41eThzfDvmz4CA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:09.274678Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.02725","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bc45ecc356a69213be8844d4e70d508d95b86505e02eeadb36f3132faed0753","sha256:9b23e7edc70c1780be6a731092ddbcd20bd12b26306a9ce0299ae231330b4f42"],"state_sha256":"2295683bd1d5ab81911bbc9f46bc89f8b202f5e3ad6bc008761e541293daa994"}