{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KIS6Q6D5EIHD22C4BOBE6TH7QD","short_pith_number":"pith:KIS6Q6D5","schema_version":"1.0","canonical_sha256":"5225e8787d220e3d685c0b824f4cff80f68d5382a7dee190ef70cd43852c8bec","source":{"kind":"arxiv","id":"2109.02492","version":2},"attestation_state":"computed","paper":{"title":"DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenguang Zhu, Michael Zeng, Ming Zhong, Yang Liu, Yichong Xu","submitted_at":"2021-09-06T13:55:03Z","abstract_excerpt":"Dialogue is an essential part of human communication and cooperation. Existing research mainly focuses on short dialogue scenarios in a one-on-one fashion. However, multi-person interactions in the real world, such as meetings or interviews, are frequently over a few thousand words. There is still a lack of corresponding research and powerful tools to understand and process such long dialogues. Therefore, in this work, we present a pre-training framework for long dialogue understanding and summarization. Considering the nature of long conversations, we propose a window-based denoising approach"},"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":"2109.02492","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-06T13:55:03Z","cross_cats_sorted":[],"title_canon_sha256":"d6e6f3ff302d78c29b629221c06738baa0221498b6a96965e90fe5ff9a4b0a08","abstract_canon_sha256":"c040ba5927ab830e1918346027ba9859989841b36a445de4d6a84859d1138d64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:21.840796Z","signature_b64":"V7z/BbnCbIeh5Yu98K5k5QVD23WlLNW/0XWV6Ffh9V02wSKSQgk7Qb5cttROP460lu1h7c0Dsm6l3MuQ2NUeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5225e8787d220e3d685c0b824f4cff80f68d5382a7dee190ef70cd43852c8bec","last_reissued_at":"2026-07-05T03:46:21.839769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:21.839769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DialogLM: Pre-trained Model for Long Dialogue Understanding and Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenguang Zhu, Michael Zeng, Ming Zhong, Yang Liu, Yichong Xu","submitted_at":"2021-09-06T13:55:03Z","abstract_excerpt":"Dialogue is an essential part of human communication and cooperation. Existing research mainly focuses on short dialogue scenarios in a one-on-one fashion. However, multi-person interactions in the real world, such as meetings or interviews, are frequently over a few thousand words. There is still a lack of corresponding research and powerful tools to understand and process such long dialogues. Therefore, in this work, we present a pre-training framework for long dialogue understanding and summarization. Considering the nature of long conversations, we propose a window-based denoising approach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.02492","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/2109.02492/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":"2109.02492","created_at":"2026-07-05T03:46:21.839840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.02492v2","created_at":"2026-07-05T03:46:21.839840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.02492","created_at":"2026-07-05T03:46:21.839840+00:00"},{"alias_kind":"pith_short_12","alias_value":"KIS6Q6D5EIHD","created_at":"2026-07-05T03:46:21.839840+00:00"},{"alias_kind":"pith_short_16","alias_value":"KIS6Q6D5EIHD22C4","created_at":"2026-07-05T03:46:21.839840+00:00"},{"alias_kind":"pith_short_8","alias_value":"KIS6Q6D5","created_at":"2026-07-05T03:46:21.839840+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06276","citing_title":"Linear Semantic Segmentation for Low-Resource Spoken Dialects","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KIS6Q6D5EIHD22C4BOBE6TH7QD","json":"https://pith.science/pith/KIS6Q6D5EIHD22C4BOBE6TH7QD.json","graph_json":"https://pith.science/api/pith-number/KIS6Q6D5EIHD22C4BOBE6TH7QD/graph.json","events_json":"https://pith.science/api/pith-number/KIS6Q6D5EIHD22C4BOBE6TH7QD/events.json","paper":"https://pith.science/paper/KIS6Q6D5"},"agent_actions":{"view_html":"https://pith.science/pith/KIS6Q6D5EIHD22C4BOBE6TH7QD","download_json":"https://pith.science/pith/KIS6Q6D5EIHD22C4BOBE6TH7QD.json","view_paper":"https://pith.science/paper/KIS6Q6D5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.02492&json=true","fetch_graph":"https://pith.science/api/pith-number/KIS6Q6D5EIHD22C4BOBE6TH7QD/graph.json","fetch_events":"https://pith.science/api/pith-number/KIS6Q6D5EIHD22C4BOBE6TH7QD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KIS6Q6D5EIHD22C4BOBE6TH7QD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KIS6Q6D5EIHD22C4BOBE6TH7QD/action/storage_attestation","attest_author":"https://pith.science/pith/KIS6Q6D5EIHD22C4BOBE6TH7QD/action/author_attestation","sign_citation":"https://pith.science/pith/KIS6Q6D5EIHD22C4BOBE6TH7QD/action/citation_signature","submit_replication":"https://pith.science/pith/KIS6Q6D5EIHD22C4BOBE6TH7QD/action/replication_record"}},"created_at":"2026-07-05T03:46:21.839840+00:00","updated_at":"2026-07-05T03:46:21.839840+00:00"}