{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:B74WZ3CJF5TKWJ5XUE4BLRJEX6","short_pith_number":"pith:B74WZ3CJ","schema_version":"1.0","canonical_sha256":"0ff96cec492f66ab27b7a13815c524bfad32dc58874b0b11698ec0766d5a64d0","source":{"kind":"arxiv","id":"2103.03373","version":1},"attestation_state":"computed","paper":{"title":"Neural model robustness for skill routing in large-scale conversational AI systems: A design choice exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aswarth Dara, Han Li, Jinseok Nam, Ruhi Sarikaya, Spyros Matsoukas, Sunghyun Park, Sungjin Lee, Young-Bum Kim","submitted_at":"2021-03-04T22:54:33Z","abstract_excerpt":"Current state-of-the-art large-scale conversational AI or intelligent digital assistant systems in industry comprises a set of components such as Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU). For some of these systems that leverage a shared NLU ontology (e.g., a centralized intent/slot schema), there exists a separate skill routing component to correctly route a request to an appropriate skill, which is either a first-party or third-party application that actually executes on a user request. The skill routing component is needed as there are thousands of skills t"},"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":"2103.03373","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-04T22:54:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"8c531d19276e7b0041b79be8d62b4d319571fbf3168d5d5254d4e779ccdbbf4e","abstract_canon_sha256":"d2e43d6cd660e5cdad70849ede2dc994000027e96f75257db3a7333c56e2b4b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:34.446548Z","signature_b64":"tGfjmc2HEl4oquLtLDOHH4R9SrirIwmP99TyGCD+vTzP9OhCQxO5pAamEvgzVF8u56o2hFrJ7Id/XwrGCEAYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ff96cec492f66ab27b7a13815c524bfad32dc58874b0b11698ec0766d5a64d0","last_reissued_at":"2026-07-05T02:20:34.445946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:34.445946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural model robustness for skill routing in large-scale conversational AI systems: A design choice exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aswarth Dara, Han Li, Jinseok Nam, Ruhi Sarikaya, Spyros Matsoukas, Sunghyun Park, Sungjin Lee, Young-Bum Kim","submitted_at":"2021-03-04T22:54:33Z","abstract_excerpt":"Current state-of-the-art large-scale conversational AI or intelligent digital assistant systems in industry comprises a set of components such as Automatic Speech Recognition (ASR) and Natural Language Understanding (NLU). For some of these systems that leverage a shared NLU ontology (e.g., a centralized intent/slot schema), there exists a separate skill routing component to correctly route a request to an appropriate skill, which is either a first-party or third-party application that actually executes on a user request. The skill routing component is needed as there are thousands of skills t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03373","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/2103.03373/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":"2103.03373","created_at":"2026-07-05T02:20:34.446012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.03373v1","created_at":"2026-07-05T02:20:34.446012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03373","created_at":"2026-07-05T02:20:34.446012+00:00"},{"alias_kind":"pith_short_12","alias_value":"B74WZ3CJF5TK","created_at":"2026-07-05T02:20:34.446012+00:00"},{"alias_kind":"pith_short_16","alias_value":"B74WZ3CJF5TKWJ5X","created_at":"2026-07-05T02:20:34.446012+00:00"},{"alias_kind":"pith_short_8","alias_value":"B74WZ3CJ","created_at":"2026-07-05T02:20:34.446012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.14299","citing_title":"Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B74WZ3CJF5TKWJ5XUE4BLRJEX6","json":"https://pith.science/pith/B74WZ3CJF5TKWJ5XUE4BLRJEX6.json","graph_json":"https://pith.science/api/pith-number/B74WZ3CJF5TKWJ5XUE4BLRJEX6/graph.json","events_json":"https://pith.science/api/pith-number/B74WZ3CJF5TKWJ5XUE4BLRJEX6/events.json","paper":"https://pith.science/paper/B74WZ3CJ"},"agent_actions":{"view_html":"https://pith.science/pith/B74WZ3CJF5TKWJ5XUE4BLRJEX6","download_json":"https://pith.science/pith/B74WZ3CJF5TKWJ5XUE4BLRJEX6.json","view_paper":"https://pith.science/paper/B74WZ3CJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.03373&json=true","fetch_graph":"https://pith.science/api/pith-number/B74WZ3CJF5TKWJ5XUE4BLRJEX6/graph.json","fetch_events":"https://pith.science/api/pith-number/B74WZ3CJF5TKWJ5XUE4BLRJEX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B74WZ3CJF5TKWJ5XUE4BLRJEX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B74WZ3CJF5TKWJ5XUE4BLRJEX6/action/storage_attestation","attest_author":"https://pith.science/pith/B74WZ3CJF5TKWJ5XUE4BLRJEX6/action/author_attestation","sign_citation":"https://pith.science/pith/B74WZ3CJF5TKWJ5XUE4BLRJEX6/action/citation_signature","submit_replication":"https://pith.science/pith/B74WZ3CJF5TKWJ5XUE4BLRJEX6/action/replication_record"}},"created_at":"2026-07-05T02:20:34.446012+00:00","updated_at":"2026-07-05T02:20:34.446012+00:00"}