{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LPOQOCQMB6JSU6IXXVF2PZY6JA","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":"6049d9e02cb496dc993f023a1b8cc17f8c97bc0e1cb94118b483bda71db509ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-29T15:48:58Z","title_canon_sha256":"31db49cf7fd91f134aae5a5b4ea67dd19ce97a1b75a7fc227957bee8abb4898a"},"schema_version":"1.0","source":{"id":"2009.14109","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.14109","created_at":"2026-07-05T01:39:17Z"},{"alias_kind":"arxiv_version","alias_value":"2009.14109v2","created_at":"2026-07-05T01:39:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.14109","created_at":"2026-07-05T01:39:17Z"},{"alias_kind":"pith_short_12","alias_value":"LPOQOCQMB6JS","created_at":"2026-07-05T01:39:17Z"},{"alias_kind":"pith_short_16","alias_value":"LPOQOCQMB6JSU6IX","created_at":"2026-07-05T01:39:17Z"},{"alias_kind":"pith_short_8","alias_value":"LPOQOCQM","created_at":"2026-07-05T01:39:17Z"}],"graph_snapshots":[{"event_id":"sha256:f345ca946e1e2867e28eee8d8f020085b8f875ad8859a42807226bc8e61f73e8","target":"graph","created_at":"2026-07-05T01:39:17Z","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/2009.14109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many NLP applications, such as biomedical data and technical support, have 10-100 million tokens of in-domain data and limited computational resources for learning from it. How should we train a language model in this scenario? Most language modeling research considers either a small dataset with a closed vocabulary (like the standard 1 million token Penn Treebank), or the whole web with byte-pair encoding. We show that for our target setting in English, initialising and freezing input embeddings using in-domain data can improve language model performance by providing a useful representation o","authors_text":"Charles Welch, Jonathan K. Kummerfeld, Rada Mihalcea","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-29T15:48:58Z","title":"Improving Low Compute Language Modeling with In-Domain Embedding Initialisation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.14109","kind":"arxiv","version":2},"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":"sha256:71c13e3957ccbdc3d87294806e4e56f37d6e85508c6852506688a3aebea578a5","target":"record","created_at":"2026-07-05T01:39:17Z","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":"6049d9e02cb496dc993f023a1b8cc17f8c97bc0e1cb94118b483bda71db509ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-29T15:48:58Z","title_canon_sha256":"31db49cf7fd91f134aae5a5b4ea67dd19ce97a1b75a7fc227957bee8abb4898a"},"schema_version":"1.0","source":{"id":"2009.14109","kind":"arxiv","version":2}},"canonical_sha256":"5bdd070a0c0f932a7917bd4ba7e71e480fc08e1258189fd3dc6ec86715fa0380","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bdd070a0c0f932a7917bd4ba7e71e480fc08e1258189fd3dc6ec86715fa0380","first_computed_at":"2026-07-05T01:39:17.246754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:39:17.246754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jf5Y415E4jwASh0HIdyUavjGzL9vYOWM7frfMUYEzNypTqEaOUnPxNq1IIpzkBEmXbAZaSPDhLBFy5ZeBhnwCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:39:17.247144Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.14109","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71c13e3957ccbdc3d87294806e4e56f37d6e85508c6852506688a3aebea578a5","sha256:f345ca946e1e2867e28eee8d8f020085b8f875ad8859a42807226bc8e61f73e8"],"state_sha256":"3c8e008870ca57aee8d3ae11332a49283989e3882bd94c19ebc0694f36b6ca68"}