{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Y45BZ6GYUX47YE4ICLRX72LSHI","short_pith_number":"pith:Y45BZ6GY","schema_version":"1.0","canonical_sha256":"c73a1cf8d8a5f9fc138812e37fe9723a2915921eccd01c9e90a00c5266eed4a1","source":{"kind":"arxiv","id":"1809.06641","version":2},"attestation_state":"computed","paper":{"title":"Talking to myself: self-dialogues as data for conversational agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ben Krause, Bonnie Webber, Daniel Duma, Emmanuel Kahembwe, Federico Fancellu, Joachim Fainberg, Marco Damonte, Mihai Dobre","submitted_at":"2018-09-18T11:09:49Z","abstract_excerpt":"Conversational agents are gaining popularity with the increasing ubiquity of smart devices. However, training agents in a data driven manner is challenging due to a lack of suitable corpora. This paper presents a novel method for gathering topical, unstructured conversational data in an efficient way: self-dialogues through crowd-sourcing. Alongside this paper, we include a corpus of 3.6 million words across 23 topics. We argue the utility of the corpus by comparing self-dialogues with standard two-party conversations as well as data from other corpora."},"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":"1809.06641","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-18T11:09:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"076879257674e048c866444bd0d5d8892613e48ea5b038cec11384f1e2edd983","abstract_canon_sha256":"e8982c64772e9f8fcf5984052555865eb69c1ef8d02103c5fd38e66618a5bdf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:21.265352Z","signature_b64":"28uCLhee9NhB5l1OOvWik1IsXsJqb+FFt4x1ptDvz24j/UV/eBeCSHVTK3Up0H4IXI6PQ8Pw8h4EdDgcSToKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c73a1cf8d8a5f9fc138812e37fe9723a2915921eccd01c9e90a00c5266eed4a1","last_reissued_at":"2026-05-18T00:05:21.264864Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:21.264864Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Talking to myself: self-dialogues as data for conversational agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ben Krause, Bonnie Webber, Daniel Duma, Emmanuel Kahembwe, Federico Fancellu, Joachim Fainberg, Marco Damonte, Mihai Dobre","submitted_at":"2018-09-18T11:09:49Z","abstract_excerpt":"Conversational agents are gaining popularity with the increasing ubiquity of smart devices. However, training agents in a data driven manner is challenging due to a lack of suitable corpora. This paper presents a novel method for gathering topical, unstructured conversational data in an efficient way: self-dialogues through crowd-sourcing. Alongside this paper, we include a corpus of 3.6 million words across 23 topics. We argue the utility of the corpus by comparing self-dialogues with standard two-party conversations as well as data from other corpora."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06641","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":"1809.06641","created_at":"2026-05-18T00:05:21.264940+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.06641v2","created_at":"2026-05-18T00:05:21.264940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06641","created_at":"2026-05-18T00:05:21.264940+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y45BZ6GYUX47","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y45BZ6GYUX47YE4I","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y45BZ6GY","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.03975","citing_title":"Implicit Discourse Relation Identification for Open-domain Dialogues","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y45BZ6GYUX47YE4ICLRX72LSHI","json":"https://pith.science/pith/Y45BZ6GYUX47YE4ICLRX72LSHI.json","graph_json":"https://pith.science/api/pith-number/Y45BZ6GYUX47YE4ICLRX72LSHI/graph.json","events_json":"https://pith.science/api/pith-number/Y45BZ6GYUX47YE4ICLRX72LSHI/events.json","paper":"https://pith.science/paper/Y45BZ6GY"},"agent_actions":{"view_html":"https://pith.science/pith/Y45BZ6GYUX47YE4ICLRX72LSHI","download_json":"https://pith.science/pith/Y45BZ6GYUX47YE4ICLRX72LSHI.json","view_paper":"https://pith.science/paper/Y45BZ6GY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.06641&json=true","fetch_graph":"https://pith.science/api/pith-number/Y45BZ6GYUX47YE4ICLRX72LSHI/graph.json","fetch_events":"https://pith.science/api/pith-number/Y45BZ6GYUX47YE4ICLRX72LSHI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y45BZ6GYUX47YE4ICLRX72LSHI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y45BZ6GYUX47YE4ICLRX72LSHI/action/storage_attestation","attest_author":"https://pith.science/pith/Y45BZ6GYUX47YE4ICLRX72LSHI/action/author_attestation","sign_citation":"https://pith.science/pith/Y45BZ6GYUX47YE4ICLRX72LSHI/action/citation_signature","submit_replication":"https://pith.science/pith/Y45BZ6GYUX47YE4ICLRX72LSHI/action/replication_record"}},"created_at":"2026-05-18T00:05:21.264940+00:00","updated_at":"2026-05-18T00:05:21.264940+00:00"}