{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DEBQYOKTICR6Y23SISOL2UYCIB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9d8879a044909d854cc7b26c586629cdee05d557eee742d3aabc29e49431bd20","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-13T02:59:48Z","title_canon_sha256":"8fb89387d5f5b74731b19c913651c29ebc1fafc8f2f39c1f9b7eead92202fed6"},"schema_version":"1.0","source":{"id":"1904.06472","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06472","created_at":"2026-05-17T23:44:47Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06472v2","created_at":"2026-05-17T23:44:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06472","created_at":"2026-05-17T23:44:47Z"},{"alias_kind":"pith_short_12","alias_value":"DEBQYOKTICR6","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DEBQYOKTICR6Y23S","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DEBQYOKT","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:db83c43fc715fbd6658f7c5778845ae85ccf4d650e719633788fd5dd5986294e","target":"graph","created_at":"2026-05-17T23:44:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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 ","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-13T02:59:48Z","title":"A Repository of Conversational Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06472","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ac129d5fb7150bbcbb5ba1d2f8ae12d4ce64dc8b89c40cab14bf753d5bfaa4b5","target":"record","created_at":"2026-05-17T23:44:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9d8879a044909d854cc7b26c586629cdee05d557eee742d3aabc29e49431bd20","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-13T02:59:48Z","title_canon_sha256":"8fb89387d5f5b74731b19c913651c29ebc1fafc8f2f39c1f9b7eead92202fed6"},"schema_version":"1.0","source":{"id":"1904.06472","kind":"arxiv","version":2}},"canonical_sha256":"19030c395340a3ec6b72449cbd530240626aa163db646680a579f9b4615bbed9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19030c395340a3ec6b72449cbd530240626aa163db646680a579f9b4615bbed9","first_computed_at":"2026-05-17T23:44:47.281669Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:47.281669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mln0V/DSOEFNaTJ/gWng7Vs4HoG/LzkUEKQIi64DBp7WjQ6CyezY4aDwmdqf+HplzWyWTTejmeQAT7UBqOipDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:47.282284Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.06472","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac129d5fb7150bbcbb5ba1d2f8ae12d4ce64dc8b89c40cab14bf753d5bfaa4b5","sha256:db83c43fc715fbd6658f7c5778845ae85ccf4d650e719633788fd5dd5986294e"],"state_sha256":"7c8c5bfeb267874c8bbf11a663da86801e6b7d3819b2773f20e85d8f96958dce"}