{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZODXM66DIU7FBQ5DC5VOZ3LUEA","short_pith_number":"pith:ZODXM66D","schema_version":"1.0","canonical_sha256":"cb87767bc3453e50c3a3176aeced74203a689052717c0fea8c00e8353ed7c0de","source":{"kind":"arxiv","id":"2010.02140","version":1},"attestation_state":"computed","paper":{"title":"Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Aitor Soroa, Alvaro Rodrigo, Don Tuggener, Eneko Agirre, Jan Deriu, Jon Ander Campos, Mark Cieliebak, Pius von D\\\"aniken, Thiziri Belkacem","submitted_at":"2020-10-05T16:37:52Z","abstract_excerpt":"The lack of time-efficient and reliable evaluation methods hamper the development of conversational dialogue systems (chatbots). Evaluations requiring humans to converse with chatbots are time and cost-intensive, put high cognitive demands on the human judges, and yield low-quality results. In this work, we introduce \\emph{Spot The Bot}, a cost-efficient and robust evaluation framework that replaces human-bot conversations with conversations between bots. Human judges then only annotate for each entity in a conversation whether they think it is human or not (assuming there are humans participa"},"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":"2010.02140","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-10-05T16:37:52Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0c1f4496f79b2bb17eaafac7e62dee7b97a22d340471a6fb1dc08c979554f80d","abstract_canon_sha256":"2980f5f167d6bd6f17bb181a3e0ac3c68cdaed9c63463a0bc13d8e75bab75e94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:17.777132Z","signature_b64":"itV9fNIqhKDz0GNk5Vf9aIQaoPl3eB0jttrNBPrP7B3QW4pXzm92fEbs/SFfUEergiFXF+pESiLs+0ai6MYTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb87767bc3453e50c3a3176aeced74203a689052717c0fea8c00e8353ed7c0de","last_reissued_at":"2026-07-05T01:40:17.776736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:17.776736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Aitor Soroa, Alvaro Rodrigo, Don Tuggener, Eneko Agirre, Jan Deriu, Jon Ander Campos, Mark Cieliebak, Pius von D\\\"aniken, Thiziri Belkacem","submitted_at":"2020-10-05T16:37:52Z","abstract_excerpt":"The lack of time-efficient and reliable evaluation methods hamper the development of conversational dialogue systems (chatbots). Evaluations requiring humans to converse with chatbots are time and cost-intensive, put high cognitive demands on the human judges, and yield low-quality results. In this work, we introduce \\emph{Spot The Bot}, a cost-efficient and robust evaluation framework that replaces human-bot conversations with conversations between bots. Human judges then only annotate for each entity in a conversation whether they think it is human or not (assuming there are humans participa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.02140","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/2010.02140/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":"2010.02140","created_at":"2026-07-05T01:40:17.776791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.02140v1","created_at":"2026-07-05T01:40:17.776791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.02140","created_at":"2026-07-05T01:40:17.776791+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZODXM66DIU7F","created_at":"2026-07-05T01:40:17.776791+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZODXM66DIU7FBQ5D","created_at":"2026-07-05T01:40:17.776791+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZODXM66D","created_at":"2026-07-05T01:40:17.776791+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/ZODXM66DIU7FBQ5DC5VOZ3LUEA","json":"https://pith.science/pith/ZODXM66DIU7FBQ5DC5VOZ3LUEA.json","graph_json":"https://pith.science/api/pith-number/ZODXM66DIU7FBQ5DC5VOZ3LUEA/graph.json","events_json":"https://pith.science/api/pith-number/ZODXM66DIU7FBQ5DC5VOZ3LUEA/events.json","paper":"https://pith.science/paper/ZODXM66D"},"agent_actions":{"view_html":"https://pith.science/pith/ZODXM66DIU7FBQ5DC5VOZ3LUEA","download_json":"https://pith.science/pith/ZODXM66DIU7FBQ5DC5VOZ3LUEA.json","view_paper":"https://pith.science/paper/ZODXM66D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.02140&json=true","fetch_graph":"https://pith.science/api/pith-number/ZODXM66DIU7FBQ5DC5VOZ3LUEA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZODXM66DIU7FBQ5DC5VOZ3LUEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZODXM66DIU7FBQ5DC5VOZ3LUEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZODXM66DIU7FBQ5DC5VOZ3LUEA/action/storage_attestation","attest_author":"https://pith.science/pith/ZODXM66DIU7FBQ5DC5VOZ3LUEA/action/author_attestation","sign_citation":"https://pith.science/pith/ZODXM66DIU7FBQ5DC5VOZ3LUEA/action/citation_signature","submit_replication":"https://pith.science/pith/ZODXM66DIU7FBQ5DC5VOZ3LUEA/action/replication_record"}},"created_at":"2026-07-05T01:40:17.776791+00:00","updated_at":"2026-07-05T01:40:17.776791+00:00"}