{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:R6WL3HEGF7EDI72ZHOSRSJ6SH7","short_pith_number":"pith:R6WL3HEG","schema_version":"1.0","canonical_sha256":"8facbd9c862fc8347f593ba51927d23ff83478ab7a9dc304cf884bd57cf6cdfe","source":{"kind":"arxiv","id":"1906.06438","version":1},"attestation_state":"computed","paper":{"title":"Scalable Syntax-Aware Language Models Using Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adhiguna Kuncoro, Chris Dyer, Laura Rimell, Phil Blunsom, Stephen Clark","submitted_at":"2019-06-14T23:42:08Z","abstract_excerpt":"Prior work has shown that, on small amounts of training data, syntactic neural language models learn structurally sensitive generalisations more successfully than sequential language models. However, their computational complexity renders scaling difficult, and it remains an open question whether structural biases are still necessary when sequential models have access to ever larger amounts of training data. To answer this question, we introduce an efficient knowledge distillation (KD) technique that transfers knowledge from a syntactic language model trained on a small corpus to an LSTM langu"},"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":"1906.06438","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-14T23:42:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f355292b923fd07dd3208cccfef1b21ca73abbd1d87fdb9f473549a56405f22e","abstract_canon_sha256":"22d325b828e9d212ebe1243fa28609a773e0d82f219f957d7989c5c2ff174130"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:13.675358Z","signature_b64":"ro96jfyz3j2dPNU7JBT/c0YlkS6b+GhcvszEiKMhrLzLTNxktyjDuuqYfO2xJicZ9vr3PmuQkpZCi2jOtBpsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8facbd9c862fc8347f593ba51927d23ff83478ab7a9dc304cf884bd57cf6cdfe","last_reissued_at":"2026-05-17T23:43:13.674911Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:13.674911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Syntax-Aware Language Models Using Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Adhiguna Kuncoro, Chris Dyer, Laura Rimell, Phil Blunsom, Stephen Clark","submitted_at":"2019-06-14T23:42:08Z","abstract_excerpt":"Prior work has shown that, on small amounts of training data, syntactic neural language models learn structurally sensitive generalisations more successfully than sequential language models. However, their computational complexity renders scaling difficult, and it remains an open question whether structural biases are still necessary when sequential models have access to ever larger amounts of training data. To answer this question, we introduce an efficient knowledge distillation (KD) technique that transfers knowledge from a syntactic language model trained on a small corpus to an LSTM langu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06438","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":""},"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":"1906.06438","created_at":"2026-05-17T23:43:13.674979+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.06438v1","created_at":"2026-05-17T23:43:13.674979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06438","created_at":"2026-05-17T23:43:13.674979+00:00"},{"alias_kind":"pith_short_12","alias_value":"R6WL3HEGF7ED","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"R6WL3HEGF7EDI72Z","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"R6WL3HEG","created_at":"2026-05-18T12:33:27.125529+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/R6WL3HEGF7EDI72ZHOSRSJ6SH7","json":"https://pith.science/pith/R6WL3HEGF7EDI72ZHOSRSJ6SH7.json","graph_json":"https://pith.science/api/pith-number/R6WL3HEGF7EDI72ZHOSRSJ6SH7/graph.json","events_json":"https://pith.science/api/pith-number/R6WL3HEGF7EDI72ZHOSRSJ6SH7/events.json","paper":"https://pith.science/paper/R6WL3HEG"},"agent_actions":{"view_html":"https://pith.science/pith/R6WL3HEGF7EDI72ZHOSRSJ6SH7","download_json":"https://pith.science/pith/R6WL3HEGF7EDI72ZHOSRSJ6SH7.json","view_paper":"https://pith.science/paper/R6WL3HEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.06438&json=true","fetch_graph":"https://pith.science/api/pith-number/R6WL3HEGF7EDI72ZHOSRSJ6SH7/graph.json","fetch_events":"https://pith.science/api/pith-number/R6WL3HEGF7EDI72ZHOSRSJ6SH7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R6WL3HEGF7EDI72ZHOSRSJ6SH7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R6WL3HEGF7EDI72ZHOSRSJ6SH7/action/storage_attestation","attest_author":"https://pith.science/pith/R6WL3HEGF7EDI72ZHOSRSJ6SH7/action/author_attestation","sign_citation":"https://pith.science/pith/R6WL3HEGF7EDI72ZHOSRSJ6SH7/action/citation_signature","submit_replication":"https://pith.science/pith/R6WL3HEGF7EDI72ZHOSRSJ6SH7/action/replication_record"}},"created_at":"2026-05-17T23:43:13.674979+00:00","updated_at":"2026-05-17T23:43:13.674979+00:00"}