{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XVLL374QQ64OWB5OCVOIDGZ7JT","short_pith_number":"pith:XVLL374Q","schema_version":"1.0","canonical_sha256":"bd56bdff9087b8eb07ae155c819b3f4cc6f5f65b3249862de6cb1d4c7f1afd20","source":{"kind":"arxiv","id":"2105.14313","version":1},"attestation_state":"computed","paper":{"title":"Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hong Xu, Huixing Jiang, Keqing He, Weiran Xu, Yanan Wu, Yuanmeng Yan, Zhiyuan Zeng","submitted_at":"2021-05-29T14:46:38Z","abstract_excerpt":"Existing slot filling models can only recognize pre-defined in-domain slot types from a limited slot set. In the practical application, a reliable dialogue system should know what it does not know. In this paper, we introduce a new task, Novel Slot Detection (NSD), in the task-oriented dialogue system. NSD aims to discover unknown or out-of-domain slot types to strengthen the capability of a dialogue system based on in-domain training data. Besides, we construct two public NSD datasets, propose several strong NSD baselines, and establish a benchmark for future work. Finally, we conduct exhaust"},"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":"2105.14313","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-29T14:46:38Z","cross_cats_sorted":[],"title_canon_sha256":"41852f8530828cd37aed16dac78395b8fd331c66a56908f7be8de7939984f204","abstract_canon_sha256":"ce18b8bef3729065f6bd78b18af89bdb7b795af58ee0159a3fd5c3f86572a48f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:22.506327Z","signature_b64":"TfBUOZr8lSzuqXLy/nyyqhlNkaXp/qINKxHbR05cackg8PUcDmRaoIierRyI8OKrmuTmyeBbK4wmckXXJOwICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd56bdff9087b8eb07ae155c819b3f4cc6f5f65b3249862de6cb1d4c7f1afd20","last_reissued_at":"2026-07-05T02:44:22.505852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:22.505852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hong Xu, Huixing Jiang, Keqing He, Weiran Xu, Yanan Wu, Yuanmeng Yan, Zhiyuan Zeng","submitted_at":"2021-05-29T14:46:38Z","abstract_excerpt":"Existing slot filling models can only recognize pre-defined in-domain slot types from a limited slot set. In the practical application, a reliable dialogue system should know what it does not know. In this paper, we introduce a new task, Novel Slot Detection (NSD), in the task-oriented dialogue system. NSD aims to discover unknown or out-of-domain slot types to strengthen the capability of a dialogue system based on in-domain training data. Besides, we construct two public NSD datasets, propose several strong NSD baselines, and establish a benchmark for future work. Finally, we conduct exhaust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14313","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/2105.14313/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":"2105.14313","created_at":"2026-07-05T02:44:22.505904+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.14313v1","created_at":"2026-07-05T02:44:22.505904+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14313","created_at":"2026-07-05T02:44:22.505904+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVLL374QQ64O","created_at":"2026-07-05T02:44:22.505904+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVLL374QQ64OWB5O","created_at":"2026-07-05T02:44:22.505904+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVLL374Q","created_at":"2026-07-05T02:44:22.505904+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09440","citing_title":"Key Coverage Matters: Semi-Structured Extraction of OCR Clinical Reports","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVLL374QQ64OWB5OCVOIDGZ7JT","json":"https://pith.science/pith/XVLL374QQ64OWB5OCVOIDGZ7JT.json","graph_json":"https://pith.science/api/pith-number/XVLL374QQ64OWB5OCVOIDGZ7JT/graph.json","events_json":"https://pith.science/api/pith-number/XVLL374QQ64OWB5OCVOIDGZ7JT/events.json","paper":"https://pith.science/paper/XVLL374Q"},"agent_actions":{"view_html":"https://pith.science/pith/XVLL374QQ64OWB5OCVOIDGZ7JT","download_json":"https://pith.science/pith/XVLL374QQ64OWB5OCVOIDGZ7JT.json","view_paper":"https://pith.science/paper/XVLL374Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.14313&json=true","fetch_graph":"https://pith.science/api/pith-number/XVLL374QQ64OWB5OCVOIDGZ7JT/graph.json","fetch_events":"https://pith.science/api/pith-number/XVLL374QQ64OWB5OCVOIDGZ7JT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVLL374QQ64OWB5OCVOIDGZ7JT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVLL374QQ64OWB5OCVOIDGZ7JT/action/storage_attestation","attest_author":"https://pith.science/pith/XVLL374QQ64OWB5OCVOIDGZ7JT/action/author_attestation","sign_citation":"https://pith.science/pith/XVLL374QQ64OWB5OCVOIDGZ7JT/action/citation_signature","submit_replication":"https://pith.science/pith/XVLL374QQ64OWB5OCVOIDGZ7JT/action/replication_record"}},"created_at":"2026-07-05T02:44:22.505904+00:00","updated_at":"2026-07-05T02:44:22.505904+00:00"}