{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:DEBQYOKTICR6Y23SISOL2UYCIB","short_pith_number":"pith:DEBQYOKT","schema_version":"1.0","canonical_sha256":"19030c395340a3ec6b72449cbd530240626aa163db646680a579f9b4615bbed9","source":{"kind":"arxiv","id":"1904.06472","version":2},"attestation_state":"computed","paper":{"title":"A Repository of Conversational Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniela Gerz, Georgios Spithourakis, Girish Kumar, I\\~nigo Casanueva, Ivan Vuli\\'c, Matthew Henderson, Nikola Mrk\\v{s}i\\'c, Pawe{\\l} Budzianowski, Pei-Hao Su, Sam Coope, Tsung-Hsien Wen","submitted_at":"2019-04-13T02:59:48Z","abstract_excerpt":"Progress in Machine Learning is often driven by the availability of large datasets, and consistent evaluation metrics for comparing modeling approaches. To this end, we present a repository of conversational datasets consisting of hundreds of millions of examples, and a standardised evaluation procedure for conversational response selection models using '1-of-100 accuracy'. The repository contains scripts that allow researchers to reproduce the standard datasets, or to adapt the pre-processing and data filtering steps to their needs. We introduce and evaluate several competitive baselines for "},"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":"1904.06472","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-13T02:59:48Z","cross_cats_sorted":[],"title_canon_sha256":"8fb89387d5f5b74731b19c913651c29ebc1fafc8f2f39c1f9b7eead92202fed6","abstract_canon_sha256":"9d8879a044909d854cc7b26c586629cdee05d557eee742d3aabc29e49431bd20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:47.282284Z","signature_b64":"mln0V/DSOEFNaTJ/gWng7Vs4HoG/LzkUEKQIi64DBp7WjQ6CyezY4aDwmdqf+HplzWyWTTejmeQAT7UBqOipDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19030c395340a3ec6b72449cbd530240626aa163db646680a579f9b4615bbed9","last_reissued_at":"2026-05-17T23:44:47.281669Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:47.281669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Repository of Conversational Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniela Gerz, Georgios Spithourakis, Girish Kumar, I\\~nigo Casanueva, Ivan Vuli\\'c, Matthew Henderson, Nikola Mrk\\v{s}i\\'c, Pawe{\\l} Budzianowski, Pei-Hao Su, Sam Coope, Tsung-Hsien Wen","submitted_at":"2019-04-13T02:59:48Z","abstract_excerpt":"Progress in Machine Learning is often driven by the availability of large datasets, and consistent evaluation metrics for comparing modeling approaches. To this end, we present a repository of conversational datasets consisting of hundreds of millions of examples, and a standardised evaluation procedure for conversational response selection models using '1-of-100 accuracy'. The repository contains scripts that allow researchers to reproduce the standard datasets, or to adapt the pre-processing and data filtering steps to their needs. We introduce and evaluate several competitive baselines for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06472","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":"1904.06472","created_at":"2026-05-17T23:44:47.281768+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.06472v2","created_at":"2026-05-17T23:44:47.281768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06472","created_at":"2026-05-17T23:44:47.281768+00:00"},{"alias_kind":"pith_short_12","alias_value":"DEBQYOKTICR6","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"DEBQYOKTICR6Y23S","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"DEBQYOKT","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01687","citing_title":"MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DEBQYOKTICR6Y23SISOL2UYCIB","json":"https://pith.science/pith/DEBQYOKTICR6Y23SISOL2UYCIB.json","graph_json":"https://pith.science/api/pith-number/DEBQYOKTICR6Y23SISOL2UYCIB/graph.json","events_json":"https://pith.science/api/pith-number/DEBQYOKTICR6Y23SISOL2UYCIB/events.json","paper":"https://pith.science/paper/DEBQYOKT"},"agent_actions":{"view_html":"https://pith.science/pith/DEBQYOKTICR6Y23SISOL2UYCIB","download_json":"https://pith.science/pith/DEBQYOKTICR6Y23SISOL2UYCIB.json","view_paper":"https://pith.science/paper/DEBQYOKT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.06472&json=true","fetch_graph":"https://pith.science/api/pith-number/DEBQYOKTICR6Y23SISOL2UYCIB/graph.json","fetch_events":"https://pith.science/api/pith-number/DEBQYOKTICR6Y23SISOL2UYCIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DEBQYOKTICR6Y23SISOL2UYCIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DEBQYOKTICR6Y23SISOL2UYCIB/action/storage_attestation","attest_author":"https://pith.science/pith/DEBQYOKTICR6Y23SISOL2UYCIB/action/author_attestation","sign_citation":"https://pith.science/pith/DEBQYOKTICR6Y23SISOL2UYCIB/action/citation_signature","submit_replication":"https://pith.science/pith/DEBQYOKTICR6Y23SISOL2UYCIB/action/replication_record"}},"created_at":"2026-05-17T23:44:47.281768+00:00","updated_at":"2026-05-17T23:44:47.281768+00:00"}