{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3BIIFVLSF4WLIP6RFLSPNG2MMS","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":"75126ac4b2db6de8eac586fb4c29034a03eb5efb884bd03b3a04eb8151742a17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-05T15:31:28Z","title_canon_sha256":"d08bb16d6ea4564fd5d9b2e5232d015ebfff7c3acc696582ae712b2816060cae"},"schema_version":"1.0","source":{"id":"1904.03122","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03122","created_at":"2026-05-17T23:49:18Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03122v1","created_at":"2026-05-17T23:49:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03122","created_at":"2026-05-17T23:49:18Z"},{"alias_kind":"pith_short_12","alias_value":"3BIIFVLSF4WL","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"3BIIFVLSF4WLIP6R","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"3BIIFVLS","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:2c7ebf0e83d7ae56899593fc019fb876f828f8745df3413b1520bfb2cb9464e7","target":"graph","created_at":"2026-05-17T23:49:18Z","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"},"paper":{"abstract_excerpt":"In a corpus of data, outliers are either errors: mistakes in the data that are counterproductive, or are unique: informative samples that improve model robustness. Identifying outliers can lead to better datasets by (1) removing noise in datasets and (2) guiding collection of additional data to fill gaps. However, the problem of detecting both outlier types has received relatively little attention in NLP, particularly for dialog systems. We introduce a simple and effective technique for detecting both erroneous and unique samples in a corpus of short texts using neural sentence embeddings comb","authors_text":"Andrew Lee, Anish Mahendran, Jason Mars, Johann Hauswald, Jonathan K. Kummerfeld, Lingjia Tang, Michael A. Laurenzano, Parker Hill, Stefan Larson","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-05T15:31:28Z","title":"Outlier Detection for Improved Data Quality and Diversity in Dialog Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03122","kind":"arxiv","version":1},"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:d5180279f6281a9bb1ab2035a880f7e4268b64486f0c1da1a903a879d435a0cf","target":"record","created_at":"2026-05-17T23:49:18Z","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":"75126ac4b2db6de8eac586fb4c29034a03eb5efb884bd03b3a04eb8151742a17","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-05T15:31:28Z","title_canon_sha256":"d08bb16d6ea4564fd5d9b2e5232d015ebfff7c3acc696582ae712b2816060cae"},"schema_version":"1.0","source":{"id":"1904.03122","kind":"arxiv","version":1}},"canonical_sha256":"d85082d5722f2cb43fd12ae4f69b4c64b0e782c9be1d54f7ce05cfdd0cfc4ef6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d85082d5722f2cb43fd12ae4f69b4c64b0e782c9be1d54f7ce05cfdd0cfc4ef6","first_computed_at":"2026-05-17T23:49:18.506205Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:18.506205Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"utpB6c8bCh4aOuL8i5Z36LCrRFZ1ULwrSPZtIl5Kl0JRr/6K9LQ5z04v5vA4EtcrDhNYYC6lxc733s25S/itCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:18.507034Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.03122","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5180279f6281a9bb1ab2035a880f7e4268b64486f0c1da1a903a879d435a0cf","sha256:2c7ebf0e83d7ae56899593fc019fb876f828f8745df3413b1520bfb2cb9464e7"],"state_sha256":"ae7bc1c84283348112130925d90a309978c3dd29801fa877eefd0e7b1ab1a3f2"}