{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5HQAJLEMLFI5XVY5D3Z6JAJMDN","short_pith_number":"pith:5HQAJLEM","schema_version":"1.0","canonical_sha256":"e9e004ac8c5951dbd71d1ef3e4812c1b5d187e1d615bd4bceaebf8cd4a6dfbb7","source":{"kind":"arxiv","id":"2006.12719","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Evaluation of Interactive Dialog with DialoGPT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Maxine Eskenazi, Shikib Mehri","submitted_at":"2020-06-23T03:36:09Z","abstract_excerpt":"It is important to define meaningful and interpretable automatic evaluation metrics for open-domain dialog research. Standard language generation metrics have been shown to be ineffective for dialog. This paper introduces the FED metric (fine-grained evaluation of dialog), an automatic evaluation metric which uses DialoGPT, without any fine-tuning or supervision. It also introduces the FED dataset which is constructed by annotating a set of human-system and human-human conversations with eighteen fine-grained dialog qualities. The FED metric (1) does not rely on a ground-truth response, (2) do"},"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":"2006.12719","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-23T03:36:09Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"812501b6daf3a27f42a99f4cd43b378dd1835fc09dbfc7ce367e5e322425335e","abstract_canon_sha256":"95443f72e2c611555c09ec745f242f525f8f53b004e99081bcc14a491972e4bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:13:12.579441Z","signature_b64":"iD4OMRkDuWm7lbxhpBmNFIr6vHalHLDgE6AS9cGrWBQ1oSGKQF6Oh7bTDloRNeMicKWmnGrIRnYO0mTHIWZTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9e004ac8c5951dbd71d1ef3e4812c1b5d187e1d615bd4bceaebf8cd4a6dfbb7","last_reissued_at":"2026-07-05T01:13:12.578936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:13:12.578936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Evaluation of Interactive Dialog with DialoGPT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Maxine Eskenazi, Shikib Mehri","submitted_at":"2020-06-23T03:36:09Z","abstract_excerpt":"It is important to define meaningful and interpretable automatic evaluation metrics for open-domain dialog research. Standard language generation metrics have been shown to be ineffective for dialog. This paper introduces the FED metric (fine-grained evaluation of dialog), an automatic evaluation metric which uses DialoGPT, without any fine-tuning or supervision. It also introduces the FED dataset which is constructed by annotating a set of human-system and human-human conversations with eighteen fine-grained dialog qualities. The FED metric (1) does not rely on a ground-truth response, (2) do"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.12719","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/2006.12719/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":"2006.12719","created_at":"2026-07-05T01:13:12.578993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.12719v1","created_at":"2026-07-05T01:13:12.578993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.12719","created_at":"2026-07-05T01:13:12.578993+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HQAJLEMLFI5","created_at":"2026-07-05T01:13:12.578993+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HQAJLEMLFI5XVY5","created_at":"2026-07-05T01:13:12.578993+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HQAJLEM","created_at":"2026-07-05T01:13:12.578993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16310","citing_title":"RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5HQAJLEMLFI5XVY5D3Z6JAJMDN","json":"https://pith.science/pith/5HQAJLEMLFI5XVY5D3Z6JAJMDN.json","graph_json":"https://pith.science/api/pith-number/5HQAJLEMLFI5XVY5D3Z6JAJMDN/graph.json","events_json":"https://pith.science/api/pith-number/5HQAJLEMLFI5XVY5D3Z6JAJMDN/events.json","paper":"https://pith.science/paper/5HQAJLEM"},"agent_actions":{"view_html":"https://pith.science/pith/5HQAJLEMLFI5XVY5D3Z6JAJMDN","download_json":"https://pith.science/pith/5HQAJLEMLFI5XVY5D3Z6JAJMDN.json","view_paper":"https://pith.science/paper/5HQAJLEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.12719&json=true","fetch_graph":"https://pith.science/api/pith-number/5HQAJLEMLFI5XVY5D3Z6JAJMDN/graph.json","fetch_events":"https://pith.science/api/pith-number/5HQAJLEMLFI5XVY5D3Z6JAJMDN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HQAJLEMLFI5XVY5D3Z6JAJMDN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HQAJLEMLFI5XVY5D3Z6JAJMDN/action/storage_attestation","attest_author":"https://pith.science/pith/5HQAJLEMLFI5XVY5D3Z6JAJMDN/action/author_attestation","sign_citation":"https://pith.science/pith/5HQAJLEMLFI5XVY5D3Z6JAJMDN/action/citation_signature","submit_replication":"https://pith.science/pith/5HQAJLEMLFI5XVY5D3Z6JAJMDN/action/replication_record"}},"created_at":"2026-07-05T01:13:12.578993+00:00","updated_at":"2026-07-05T01:13:12.578993+00:00"}