{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CJHMKOQL36GHGOWFRF75VMIAUJ","short_pith_number":"pith:CJHMKOQL","schema_version":"1.0","canonical_sha256":"124ec53a0bdf8c733ac5897fdab100a246b3d3e7081c30cf897c6121d1091411","source":{"kind":"arxiv","id":"2010.12532","version":1},"attestation_state":"computed","paper":{"title":"GiBERT: Introducing Linguistic Knowledge into BERT through a Lightweight Gated Injection Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marek Rei, Maria Liakata, Nicole Peinelt","submitted_at":"2020-10-23T17:00:26Z","abstract_excerpt":"Large pre-trained language models such as BERT have been the driving force behind recent improvements across many NLP tasks. However, BERT is only trained to predict missing words - either behind masks or in the next sentence - and has no knowledge of lexical, syntactic or semantic information beyond what it picks up through unsupervised pre-training. We propose a novel method to explicitly inject linguistic knowledge in the form of word embeddings into any layer of a pre-trained BERT. Our performance improvements on multiple semantic similarity datasets when injecting dependency-based and cou"},"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":"2010.12532","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T17:00:26Z","cross_cats_sorted":[],"title_canon_sha256":"83cf42d5b36df7cc5fd08d29224a8fd85c09810bc2030e7cfd2e37f5aed8e2a2","abstract_canon_sha256":"91d1fac9f4d5b1373fb14ef58c55fd6fceb0dccdb1af94e4af1302d908e26319"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:38.362088Z","signature_b64":"yuELNVzew+D98f4H6yHqPTMCpI6EtZ+rFGExId6wsul1Drci/ul3aAffwe41n/nD/A9fByLoJd+zv8uz/csqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"124ec53a0bdf8c733ac5897fdab100a246b3d3e7081c30cf897c6121d1091411","last_reissued_at":"2026-07-05T01:45:38.361637Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:38.361637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GiBERT: Introducing Linguistic Knowledge into BERT through a Lightweight Gated Injection Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marek Rei, Maria Liakata, Nicole Peinelt","submitted_at":"2020-10-23T17:00:26Z","abstract_excerpt":"Large pre-trained language models such as BERT have been the driving force behind recent improvements across many NLP tasks. However, BERT is only trained to predict missing words - either behind masks or in the next sentence - and has no knowledge of lexical, syntactic or semantic information beyond what it picks up through unsupervised pre-training. We propose a novel method to explicitly inject linguistic knowledge in the form of word embeddings into any layer of a pre-trained BERT. Our performance improvements on multiple semantic similarity datasets when injecting dependency-based and cou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12532","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/2010.12532/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":"2010.12532","created_at":"2026-07-05T01:45:38.361695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.12532v1","created_at":"2026-07-05T01:45:38.361695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12532","created_at":"2026-07-05T01:45:38.361695+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJHMKOQL36GH","created_at":"2026-07-05T01:45:38.361695+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJHMKOQL36GHGOWF","created_at":"2026-07-05T01:45:38.361695+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJHMKOQL","created_at":"2026-07-05T01:45:38.361695+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/CJHMKOQL36GHGOWFRF75VMIAUJ","json":"https://pith.science/pith/CJHMKOQL36GHGOWFRF75VMIAUJ.json","graph_json":"https://pith.science/api/pith-number/CJHMKOQL36GHGOWFRF75VMIAUJ/graph.json","events_json":"https://pith.science/api/pith-number/CJHMKOQL36GHGOWFRF75VMIAUJ/events.json","paper":"https://pith.science/paper/CJHMKOQL"},"agent_actions":{"view_html":"https://pith.science/pith/CJHMKOQL36GHGOWFRF75VMIAUJ","download_json":"https://pith.science/pith/CJHMKOQL36GHGOWFRF75VMIAUJ.json","view_paper":"https://pith.science/paper/CJHMKOQL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.12532&json=true","fetch_graph":"https://pith.science/api/pith-number/CJHMKOQL36GHGOWFRF75VMIAUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/CJHMKOQL36GHGOWFRF75VMIAUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJHMKOQL36GHGOWFRF75VMIAUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJHMKOQL36GHGOWFRF75VMIAUJ/action/storage_attestation","attest_author":"https://pith.science/pith/CJHMKOQL36GHGOWFRF75VMIAUJ/action/author_attestation","sign_citation":"https://pith.science/pith/CJHMKOQL36GHGOWFRF75VMIAUJ/action/citation_signature","submit_replication":"https://pith.science/pith/CJHMKOQL36GHGOWFRF75VMIAUJ/action/replication_record"}},"created_at":"2026-07-05T01:45:38.361695+00:00","updated_at":"2026-07-05T01:45:38.361695+00:00"}