{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QRWLIMAEEZSMEE53TYUBYKOTHN","short_pith_number":"pith:QRWLIMAE","schema_version":"1.0","canonical_sha256":"846cb430042664c213bb9e281c29d33b52f4a3119b28804976b90462f8e8fb8e","source":{"kind":"arxiv","id":"2202.10137","version":1},"attestation_state":"computed","paper":{"title":"A new data augmentation method for intent classification enhancement and its application on spoken conversation datasets","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Aharon Satt, Boaz Carmeli, Brian Kingsbury, Hong-Kwang Kuo, Ron Hoory, Samuel Thomas, Zvi Kons","submitted_at":"2022-02-21T11:36:19Z","abstract_excerpt":"Intent classifiers are vital to the successful operation of virtual agent systems. This is especially so in voice activated systems where the data can be noisy with many ambiguous directions for user intents. Before operation begins, these classifiers are generally lacking in real-world training data. Active learning is a common approach used to help label large amounts of collected user input. However, this approach requires many hours of manual labeling work. We present the Nearest Neighbors Scores Improvement (NNSI) algorithm for automatic data selection and labeling. The NNSI reduces the n"},"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":"2202.10137","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-21T11:36:19Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"c4b97202bc9a644371d43b32cd895a559506d7c968b1d21a73ff2756d34d1938","abstract_canon_sha256":"4e4d2b01801864a805bf370040cf2e3ff019b773553d35bd3c9d5eac6d6ef3a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:39.272941Z","signature_b64":"ccPQBry5vZK/JjZhV2YxayAp0YIyh3LKFwrgVhEq41RRnsJxHbFOl6K/6zZgsAk5s5RHAtfev9nF1bNO88kqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"846cb430042664c213bb9e281c29d33b52f4a3119b28804976b90462f8e8fb8e","last_reissued_at":"2026-07-05T03:58:39.272508Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:39.272508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A new data augmentation method for intent classification enhancement and its application on spoken conversation datasets","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Aharon Satt, Boaz Carmeli, Brian Kingsbury, Hong-Kwang Kuo, Ron Hoory, Samuel Thomas, Zvi Kons","submitted_at":"2022-02-21T11:36:19Z","abstract_excerpt":"Intent classifiers are vital to the successful operation of virtual agent systems. This is especially so in voice activated systems where the data can be noisy with many ambiguous directions for user intents. Before operation begins, these classifiers are generally lacking in real-world training data. Active learning is a common approach used to help label large amounts of collected user input. However, this approach requires many hours of manual labeling work. We present the Nearest Neighbors Scores Improvement (NNSI) algorithm for automatic data selection and labeling. The NNSI reduces the n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.10137","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/2202.10137/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":"2202.10137","created_at":"2026-07-05T03:58:39.272579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.10137v1","created_at":"2026-07-05T03:58:39.272579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.10137","created_at":"2026-07-05T03:58:39.272579+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRWLIMAEEZSM","created_at":"2026-07-05T03:58:39.272579+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRWLIMAEEZSMEE53","created_at":"2026-07-05T03:58:39.272579+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRWLIMAE","created_at":"2026-07-05T03:58:39.272579+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/QRWLIMAEEZSMEE53TYUBYKOTHN","json":"https://pith.science/pith/QRWLIMAEEZSMEE53TYUBYKOTHN.json","graph_json":"https://pith.science/api/pith-number/QRWLIMAEEZSMEE53TYUBYKOTHN/graph.json","events_json":"https://pith.science/api/pith-number/QRWLIMAEEZSMEE53TYUBYKOTHN/events.json","paper":"https://pith.science/paper/QRWLIMAE"},"agent_actions":{"view_html":"https://pith.science/pith/QRWLIMAEEZSMEE53TYUBYKOTHN","download_json":"https://pith.science/pith/QRWLIMAEEZSMEE53TYUBYKOTHN.json","view_paper":"https://pith.science/paper/QRWLIMAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.10137&json=true","fetch_graph":"https://pith.science/api/pith-number/QRWLIMAEEZSMEE53TYUBYKOTHN/graph.json","fetch_events":"https://pith.science/api/pith-number/QRWLIMAEEZSMEE53TYUBYKOTHN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRWLIMAEEZSMEE53TYUBYKOTHN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRWLIMAEEZSMEE53TYUBYKOTHN/action/storage_attestation","attest_author":"https://pith.science/pith/QRWLIMAEEZSMEE53TYUBYKOTHN/action/author_attestation","sign_citation":"https://pith.science/pith/QRWLIMAEEZSMEE53TYUBYKOTHN/action/citation_signature","submit_replication":"https://pith.science/pith/QRWLIMAEEZSMEE53TYUBYKOTHN/action/replication_record"}},"created_at":"2026-07-05T03:58:39.272579+00:00","updated_at":"2026-07-05T03:58:39.272579+00:00"}