{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DJCLNAC2APDC5F4TGF3DLBLDLD","short_pith_number":"pith:DJCLNAC2","schema_version":"1.0","canonical_sha256":"1a44b6805a03c62e9793317635856358d61ec930fcd35f28bf760d59708fa0cb","source":{"kind":"arxiv","id":"2306.03984","version":2},"attestation_state":"computed","paper":{"title":"Toward More Accurate and Generalizable Evaluation Metrics for Task-Oriented Dialogs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abishek Komma, Angeliki Metallinou, Anuj Goyal, Aram Galstyan, Nagesh Panyam Chandrasekarasastry, Spyros Matsoukas, Timothy Leffel","submitted_at":"2023-06-06T19:43:29Z","abstract_excerpt":"Measurement of interaction quality is a critical task for the improvement of spoken dialog systems. Existing approaches to dialog quality estimation either focus on evaluating the quality of individual turns, or collect dialog-level quality measurements from end users immediately following an interaction. In contrast to these approaches, we introduce a new dialog-level annotation workflow called Dialog Quality Annotation (DQA). DQA expert annotators evaluate the quality of dialogs as a whole, and also label dialogs for attributes such as goal completion and user sentiment. In this contribution"},"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":"2306.03984","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-06T19:43:29Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b139ee95bb9a91b832effbb3946d22cc38a05c069d1503fecaafcca7c0396c0f","abstract_canon_sha256":"a3e62946775efa73dcb99446ac8ef61a87ea9a53e1e7a8e3f6bff500d88d08b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:18.086778Z","signature_b64":"mf4O+WSshjOvmYXap/TmYQZYQxXa3wgiWWWN5OoMSvWmwwhnckAFtcapq/2gKk/LJBqMe/V+b98Ooh90r2g8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a44b6805a03c62e9793317635856358d61ec930fcd35f28bf760d59708fa0cb","last_reissued_at":"2026-07-05T08:36:18.086263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:18.086263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward More Accurate and Generalizable Evaluation Metrics for Task-Oriented Dialogs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abishek Komma, Angeliki Metallinou, Anuj Goyal, Aram Galstyan, Nagesh Panyam Chandrasekarasastry, Spyros Matsoukas, Timothy Leffel","submitted_at":"2023-06-06T19:43:29Z","abstract_excerpt":"Measurement of interaction quality is a critical task for the improvement of spoken dialog systems. Existing approaches to dialog quality estimation either focus on evaluating the quality of individual turns, or collect dialog-level quality measurements from end users immediately following an interaction. In contrast to these approaches, we introduce a new dialog-level annotation workflow called Dialog Quality Annotation (DQA). DQA expert annotators evaluate the quality of dialogs as a whole, and also label dialogs for attributes such as goal completion and user sentiment. In this contribution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03984","kind":"arxiv","version":2},"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/2306.03984/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":"2306.03984","created_at":"2026-07-05T08:36:18.086326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.03984v2","created_at":"2026-07-05T08:36:18.086326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03984","created_at":"2026-07-05T08:36:18.086326+00:00"},{"alias_kind":"pith_short_12","alias_value":"DJCLNAC2APDC","created_at":"2026-07-05T08:36:18.086326+00:00"},{"alias_kind":"pith_short_16","alias_value":"DJCLNAC2APDC5F4T","created_at":"2026-07-05T08:36:18.086326+00:00"},{"alias_kind":"pith_short_8","alias_value":"DJCLNAC2","created_at":"2026-07-05T08:36:18.086326+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/DJCLNAC2APDC5F4TGF3DLBLDLD","json":"https://pith.science/pith/DJCLNAC2APDC5F4TGF3DLBLDLD.json","graph_json":"https://pith.science/api/pith-number/DJCLNAC2APDC5F4TGF3DLBLDLD/graph.json","events_json":"https://pith.science/api/pith-number/DJCLNAC2APDC5F4TGF3DLBLDLD/events.json","paper":"https://pith.science/paper/DJCLNAC2"},"agent_actions":{"view_html":"https://pith.science/pith/DJCLNAC2APDC5F4TGF3DLBLDLD","download_json":"https://pith.science/pith/DJCLNAC2APDC5F4TGF3DLBLDLD.json","view_paper":"https://pith.science/paper/DJCLNAC2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.03984&json=true","fetch_graph":"https://pith.science/api/pith-number/DJCLNAC2APDC5F4TGF3DLBLDLD/graph.json","fetch_events":"https://pith.science/api/pith-number/DJCLNAC2APDC5F4TGF3DLBLDLD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DJCLNAC2APDC5F4TGF3DLBLDLD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DJCLNAC2APDC5F4TGF3DLBLDLD/action/storage_attestation","attest_author":"https://pith.science/pith/DJCLNAC2APDC5F4TGF3DLBLDLD/action/author_attestation","sign_citation":"https://pith.science/pith/DJCLNAC2APDC5F4TGF3DLBLDLD/action/citation_signature","submit_replication":"https://pith.science/pith/DJCLNAC2APDC5F4TGF3DLBLDLD/action/replication_record"}},"created_at":"2026-07-05T08:36:18.086326+00:00","updated_at":"2026-07-05T08:36:18.086326+00:00"}