{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:L7G5SKOZL47BY2TMTXTRUZOWAW","short_pith_number":"pith:L7G5SKOZ","schema_version":"1.0","canonical_sha256":"5fcdd929d95f3e1c6a6c9de71a65d60581793dfb6721981de9e80ebce04399d5","source":{"kind":"arxiv","id":"1701.03079","version":2},"attestation_state":"computed","paper":{"title":"RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chongyang Tao, Dongyan Zhao, Lili Mou, Rui Yan","submitted_at":"2017-01-11T17:43:57Z","abstract_excerpt":"Open-domain human-computer conversation has been attracting increasing attention over the past few years. However, there does not exist a standard automatic evaluation metric for open-domain dialog systems; researchers usually resort to human annotation for model evaluation, which is time- and labor-intensive. In this paper, we propose RUBER, a Referenced metric and Unreferenced metric Blended Evaluation Routine, which evaluates a reply by taking into consideration both a groundtruth reply and a query (previous user-issued utterance). Our metric is learnable, but its training does not require "},"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":"1701.03079","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-01-11T17:43:57Z","cross_cats_sorted":["cs.HC","cs.IR"],"title_canon_sha256":"841fe5fb74e2c7648d407204ab6da8c495dbc287476d0f8f23efaad9afa04e49","abstract_canon_sha256":"ad318f591d5730302301d79fb8c6b99d80c41a2dd6ebf17ddd3b0372612864a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:13.431579Z","signature_b64":"lefj8mG5a8E7ocw/mdcxot3szjGfE/OxMGzjRq4rm53HYYy+F4DI02UZmaPWNdIiZmyI0+gz3mMjEd+p0+KeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fcdd929d95f3e1c6a6c9de71a65d60581793dfb6721981de9e80ebce04399d5","last_reissued_at":"2026-05-18T00:40:13.430926Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:13.430926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RUBER: An Unsupervised Method for Automatic Evaluation of Open-Domain Dialog Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chongyang Tao, Dongyan Zhao, Lili Mou, Rui Yan","submitted_at":"2017-01-11T17:43:57Z","abstract_excerpt":"Open-domain human-computer conversation has been attracting increasing attention over the past few years. However, there does not exist a standard automatic evaluation metric for open-domain dialog systems; researchers usually resort to human annotation for model evaluation, which is time- and labor-intensive. In this paper, we propose RUBER, a Referenced metric and Unreferenced metric Blended Evaluation Routine, which evaluates a reply by taking into consideration both a groundtruth reply and a query (previous user-issued utterance). Our metric is learnable, but its training does not require "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.03079","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":""},"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":"1701.03079","created_at":"2026-05-18T00:40:13.431012+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.03079v2","created_at":"2026-05-18T00:40:13.431012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.03079","created_at":"2026-05-18T00:40:13.431012+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7G5SKOZL47B","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7G5SKOZL47BY2TM","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7G5SKOZ","created_at":"2026-05-18T12:31:28.150371+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/L7G5SKOZL47BY2TMTXTRUZOWAW","json":"https://pith.science/pith/L7G5SKOZL47BY2TMTXTRUZOWAW.json","graph_json":"https://pith.science/api/pith-number/L7G5SKOZL47BY2TMTXTRUZOWAW/graph.json","events_json":"https://pith.science/api/pith-number/L7G5SKOZL47BY2TMTXTRUZOWAW/events.json","paper":"https://pith.science/paper/L7G5SKOZ"},"agent_actions":{"view_html":"https://pith.science/pith/L7G5SKOZL47BY2TMTXTRUZOWAW","download_json":"https://pith.science/pith/L7G5SKOZL47BY2TMTXTRUZOWAW.json","view_paper":"https://pith.science/paper/L7G5SKOZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.03079&json=true","fetch_graph":"https://pith.science/api/pith-number/L7G5SKOZL47BY2TMTXTRUZOWAW/graph.json","fetch_events":"https://pith.science/api/pith-number/L7G5SKOZL47BY2TMTXTRUZOWAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7G5SKOZL47BY2TMTXTRUZOWAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7G5SKOZL47BY2TMTXTRUZOWAW/action/storage_attestation","attest_author":"https://pith.science/pith/L7G5SKOZL47BY2TMTXTRUZOWAW/action/author_attestation","sign_citation":"https://pith.science/pith/L7G5SKOZL47BY2TMTXTRUZOWAW/action/citation_signature","submit_replication":"https://pith.science/pith/L7G5SKOZL47BY2TMTXTRUZOWAW/action/replication_record"}},"created_at":"2026-05-18T00:40:13.431012+00:00","updated_at":"2026-05-18T00:40:13.431012+00:00"}