{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5D2EMYHB4JAEDJRQVMSW6IXVSS","short_pith_number":"pith:5D2EMYHB","schema_version":"1.0","canonical_sha256":"e8f44660e1e24041a630ab256f22f5949a14fc35611a96d5ce09d188ab52b602","source":{"kind":"arxiv","id":"1809.09605","version":1},"attestation_state":"computed","paper":{"title":"A Re-ranker Scheme for Integrating Large Scale NLU models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengwei Su, Rahul Gupta, Shankar Ananthakrishnan, Spyros Matsoukas","submitted_at":"2018-09-25T17:35:57Z","abstract_excerpt":"Large scale Natural Language Understanding (NLU) systems are typically trained on large quantities of data, requiring a fast and scalable training strategy. A typical design for NLU systems consists of domain-level NLU modules (domain classifier, intent classifier and named entity recognizer). Hypotheses (NLU interpretations consisting of various intent+slot combinations) from these domain specific modules are typically aggregated with another downstream component. The re-ranker integrates outputs from domain-level recognizers, returning a scored list of cross domain hypotheses. An ideal re-ra"},"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":"1809.09605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-25T17:35:57Z","cross_cats_sorted":[],"title_canon_sha256":"d5c89c9db3de6c2c7c525c12b45001357a7296b0f0dc924aa3287795791a50e2","abstract_canon_sha256":"8d5cf47a32dc755884156f2cfea82d36cdca36bb4e281f8963e2c2f30c00ed73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:50.628227Z","signature_b64":"SiLvX/0UYzKZ9eJcHvIaOv5q54PTvNewEYAOXgTB1Vgiouh7+N3/M3RQumpwRyez5L2sh/tSFywa9HKToDP3BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8f44660e1e24041a630ab256f22f5949a14fc35611a96d5ce09d188ab52b602","last_reissued_at":"2026-05-18T00:04:50.627562Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:50.627562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Re-ranker Scheme for Integrating Large Scale NLU models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengwei Su, Rahul Gupta, Shankar Ananthakrishnan, Spyros Matsoukas","submitted_at":"2018-09-25T17:35:57Z","abstract_excerpt":"Large scale Natural Language Understanding (NLU) systems are typically trained on large quantities of data, requiring a fast and scalable training strategy. A typical design for NLU systems consists of domain-level NLU modules (domain classifier, intent classifier and named entity recognizer). Hypotheses (NLU interpretations consisting of various intent+slot combinations) from these domain specific modules are typically aggregated with another downstream component. The re-ranker integrates outputs from domain-level recognizers, returning a scored list of cross domain hypotheses. An ideal re-ra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09605","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":"1809.09605","created_at":"2026-05-18T00:04:50.627655+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.09605v1","created_at":"2026-05-18T00:04:50.627655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09605","created_at":"2026-05-18T00:04:50.627655+00:00"},{"alias_kind":"pith_short_12","alias_value":"5D2EMYHB4JAE","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5D2EMYHB4JAEDJRQ","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5D2EMYHB","created_at":"2026-05-18T12:32:08.215937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.08858","citing_title":"One-vs-All Models for Asynchronous Training: An Empirical Analysis","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5D2EMYHB4JAEDJRQVMSW6IXVSS","json":"https://pith.science/pith/5D2EMYHB4JAEDJRQVMSW6IXVSS.json","graph_json":"https://pith.science/api/pith-number/5D2EMYHB4JAEDJRQVMSW6IXVSS/graph.json","events_json":"https://pith.science/api/pith-number/5D2EMYHB4JAEDJRQVMSW6IXVSS/events.json","paper":"https://pith.science/paper/5D2EMYHB"},"agent_actions":{"view_html":"https://pith.science/pith/5D2EMYHB4JAEDJRQVMSW6IXVSS","download_json":"https://pith.science/pith/5D2EMYHB4JAEDJRQVMSW6IXVSS.json","view_paper":"https://pith.science/paper/5D2EMYHB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.09605&json=true","fetch_graph":"https://pith.science/api/pith-number/5D2EMYHB4JAEDJRQVMSW6IXVSS/graph.json","fetch_events":"https://pith.science/api/pith-number/5D2EMYHB4JAEDJRQVMSW6IXVSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5D2EMYHB4JAEDJRQVMSW6IXVSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5D2EMYHB4JAEDJRQVMSW6IXVSS/action/storage_attestation","attest_author":"https://pith.science/pith/5D2EMYHB4JAEDJRQVMSW6IXVSS/action/author_attestation","sign_citation":"https://pith.science/pith/5D2EMYHB4JAEDJRQVMSW6IXVSS/action/citation_signature","submit_replication":"https://pith.science/pith/5D2EMYHB4JAEDJRQVMSW6IXVSS/action/replication_record"}},"created_at":"2026-05-18T00:04:50.627655+00:00","updated_at":"2026-05-18T00:04:50.627655+00:00"}