{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:FZLWJLEP5HVPZ2MGI6GWYE6NBT","short_pith_number":"pith:FZLWJLEP","schema_version":"1.0","canonical_sha256":"2e5764ac8fe9eafce986478d6c13cd0cf2e81c07c666a6a03b65e4dad0d5e006","source":{"kind":"arxiv","id":"2005.10716","version":2},"attestation_state":"computed","paper":{"title":"Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"James Zou, Weixin Liang, Zhou Yu","submitted_at":"2020-05-21T15:14:49Z","abstract_excerpt":"Open Domain dialog system evaluation is one of the most important challenges in dialog research. Existing automatic evaluation metrics, such as BLEU are mostly reference-based. They calculate the difference between the generated response and a limited number of available references. Likert-score based self-reported user rating is widely adopted by social conversational systems, such as Amazon Alexa Prize chatbots. However, self-reported user rating suffers from bias and variance among different users. To alleviate this problem, we formulate dialog evaluation as a comparison task. We also propo"},"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":"2005.10716","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-21T15:14:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f515cba5167ee4a73f35fe1540107aef6c0c83866ac9f2115c745dc34f29c2a3","abstract_canon_sha256":"8c5b7a1a669472a276f61d6503051f740947e5d19e3beea92b52df5823136d5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:37:10.528796Z","signature_b64":"XawNbrOCkKJm4XyFuyGzt67Dn8dXbCfYsd4UopGtqBXRYzK5EbTmpIHPOKWgwwzlxl9NXZD7nBTgvSxkHwKNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e5764ac8fe9eafce986478d6c13cd0cf2e81c07c666a6a03b65e4dad0d5e006","last_reissued_at":"2026-07-05T01:37:10.528352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:37:10.528352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"James Zou, Weixin Liang, Zhou Yu","submitted_at":"2020-05-21T15:14:49Z","abstract_excerpt":"Open Domain dialog system evaluation is one of the most important challenges in dialog research. Existing automatic evaluation metrics, such as BLEU are mostly reference-based. They calculate the difference between the generated response and a limited number of available references. Likert-score based self-reported user rating is widely adopted by social conversational systems, such as Amazon Alexa Prize chatbots. However, self-reported user rating suffers from bias and variance among different users. To alleviate this problem, we formulate dialog evaluation as a comparison task. We also propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.10716","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/2005.10716/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":"2005.10716","created_at":"2026-07-05T01:37:10.528411+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.10716v2","created_at":"2026-07-05T01:37:10.528411+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.10716","created_at":"2026-07-05T01:37:10.528411+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZLWJLEP5HVP","created_at":"2026-07-05T01:37:10.528411+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZLWJLEP5HVPZ2MG","created_at":"2026-07-05T01:37:10.528411+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZLWJLEP","created_at":"2026-07-05T01:37:10.528411+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/FZLWJLEP5HVPZ2MGI6GWYE6NBT","json":"https://pith.science/pith/FZLWJLEP5HVPZ2MGI6GWYE6NBT.json","graph_json":"https://pith.science/api/pith-number/FZLWJLEP5HVPZ2MGI6GWYE6NBT/graph.json","events_json":"https://pith.science/api/pith-number/FZLWJLEP5HVPZ2MGI6GWYE6NBT/events.json","paper":"https://pith.science/paper/FZLWJLEP"},"agent_actions":{"view_html":"https://pith.science/pith/FZLWJLEP5HVPZ2MGI6GWYE6NBT","download_json":"https://pith.science/pith/FZLWJLEP5HVPZ2MGI6GWYE6NBT.json","view_paper":"https://pith.science/paper/FZLWJLEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.10716&json=true","fetch_graph":"https://pith.science/api/pith-number/FZLWJLEP5HVPZ2MGI6GWYE6NBT/graph.json","fetch_events":"https://pith.science/api/pith-number/FZLWJLEP5HVPZ2MGI6GWYE6NBT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZLWJLEP5HVPZ2MGI6GWYE6NBT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZLWJLEP5HVPZ2MGI6GWYE6NBT/action/storage_attestation","attest_author":"https://pith.science/pith/FZLWJLEP5HVPZ2MGI6GWYE6NBT/action/author_attestation","sign_citation":"https://pith.science/pith/FZLWJLEP5HVPZ2MGI6GWYE6NBT/action/citation_signature","submit_replication":"https://pith.science/pith/FZLWJLEP5HVPZ2MGI6GWYE6NBT/action/replication_record"}},"created_at":"2026-07-05T01:37:10.528411+00:00","updated_at":"2026-07-05T01:37:10.528411+00:00"}