{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:44WMOGLIT54TEBIYPTP7EKZCTX","short_pith_number":"pith:44WMOGLI","schema_version":"1.0","canonical_sha256":"e72cc719689f793205187cdff22b229de3e7a0146920cf7668edba5e13feb1e8","source":{"kind":"arxiv","id":"1810.11118","version":2},"attestation_state":"computed","paper":{"title":"A Large-Scale Corpus for Conversation Disentanglement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chulaka Gunasekara, Jatin Ganhotra, Jonathan K. Kummerfeld, Joseph Peper, Lazaros Polymenakos, Sai R. Gouravajhala, Siva Sankalp Patel, Vignesh Athreya, Walter S. Lasecki","submitted_at":"2018-10-25T21:44:14Z","abstract_excerpt":"Disentangling conversations mixed together in a single stream of messages is a difficult task, made harder by the lack of large manually annotated datasets. We created a new dataset of 77,563 messages manually annotated with reply-structure graphs that both disentangle conversations and define internal conversation structure. Our dataset is 16 times larger than all previously released datasets combined, the first to include adjudication of annotation disagreements, and the first to include context. We use our data to re-examine prior work, in particular, finding that 80% of conversations in a "},"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":"1810.11118","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-25T21:44:14Z","cross_cats_sorted":[],"title_canon_sha256":"91d2d05be039e459b9036145abfa121b3b5a0798a4a3065d4647f57a24f4cfd1","abstract_canon_sha256":"8c81093b7d44820d058538f70482118ad233a2acb45303c6b02f43a38456b9f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:07:48.364270Z","signature_b64":"UT/EWJYufpO9aNv6ETknPx6MixtV0Z5dJxK7QAg9Nc7/wjCz9ocJzNKzknMJMkfmkbpz6lIfsnBm1BilFlAaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e72cc719689f793205187cdff22b229de3e7a0146920cf7668edba5e13feb1e8","last_reissued_at":"2026-07-05T01:07:48.363807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:07:48.363807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Large-Scale Corpus for Conversation Disentanglement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chulaka Gunasekara, Jatin Ganhotra, Jonathan K. Kummerfeld, Joseph Peper, Lazaros Polymenakos, Sai R. Gouravajhala, Siva Sankalp Patel, Vignesh Athreya, Walter S. Lasecki","submitted_at":"2018-10-25T21:44:14Z","abstract_excerpt":"Disentangling conversations mixed together in a single stream of messages is a difficult task, made harder by the lack of large manually annotated datasets. We created a new dataset of 77,563 messages manually annotated with reply-structure graphs that both disentangle conversations and define internal conversation structure. Our dataset is 16 times larger than all previously released datasets combined, the first to include adjudication of annotation disagreements, and the first to include context. We use our data to re-examine prior work, in particular, finding that 80% of conversations in a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11118","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1810.11118/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":"1810.11118","created_at":"2026-07-05T01:07:48.363864+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.11118v2","created_at":"2026-07-05T01:07:48.363864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11118","created_at":"2026-07-05T01:07:48.363864+00:00"},{"alias_kind":"pith_short_12","alias_value":"44WMOGLIT54T","created_at":"2026-07-05T01:07:48.363864+00:00"},{"alias_kind":"pith_short_16","alias_value":"44WMOGLIT54TEBIY","created_at":"2026-07-05T01:07:48.363864+00:00"},{"alias_kind":"pith_short_8","alias_value":"44WMOGLI","created_at":"2026-07-05T01:07:48.363864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1907.05792","citing_title":"Knowledge-incorporating ESIM models for Response Selection in Retrieval-based Dialog Systems","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/44WMOGLIT54TEBIYPTP7EKZCTX","json":"https://pith.science/pith/44WMOGLIT54TEBIYPTP7EKZCTX.json","graph_json":"https://pith.science/api/pith-number/44WMOGLIT54TEBIYPTP7EKZCTX/graph.json","events_json":"https://pith.science/api/pith-number/44WMOGLIT54TEBIYPTP7EKZCTX/events.json","paper":"https://pith.science/paper/44WMOGLI"},"agent_actions":{"view_html":"https://pith.science/pith/44WMOGLIT54TEBIYPTP7EKZCTX","download_json":"https://pith.science/pith/44WMOGLIT54TEBIYPTP7EKZCTX.json","view_paper":"https://pith.science/paper/44WMOGLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.11118&json=true","fetch_graph":"https://pith.science/api/pith-number/44WMOGLIT54TEBIYPTP7EKZCTX/graph.json","fetch_events":"https://pith.science/api/pith-number/44WMOGLIT54TEBIYPTP7EKZCTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/44WMOGLIT54TEBIYPTP7EKZCTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/44WMOGLIT54TEBIYPTP7EKZCTX/action/storage_attestation","attest_author":"https://pith.science/pith/44WMOGLIT54TEBIYPTP7EKZCTX/action/author_attestation","sign_citation":"https://pith.science/pith/44WMOGLIT54TEBIYPTP7EKZCTX/action/citation_signature","submit_replication":"https://pith.science/pith/44WMOGLIT54TEBIYPTP7EKZCTX/action/replication_record"}},"created_at":"2026-07-05T01:07:48.363864+00:00","updated_at":"2026-07-05T01:07:48.363864+00:00"}