{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WDJK5H5VD72J5W2OIRSLM66GI4","short_pith_number":"pith:WDJK5H5V","schema_version":"1.0","canonical_sha256":"b0d2ae9fb51ff49edb4e4464b67bc6470decf12272fd45fea518c4e42511d52d","source":{"kind":"arxiv","id":"2203.05797","version":2},"attestation_state":"computed","paper":{"title":"Long Time No See! Open-Domain Conversation with Long-Term Persona Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"HaiFeng Wang, Hua Wu, Shihang Wang, Wenquan Wu, Xinchao Xu, Zheng-Yu Niu, Zhibin Gou","submitted_at":"2022-03-11T08:41:14Z","abstract_excerpt":"Most of the open-domain dialogue models tend to perform poorly in the setting of long-term human-bot conversations. The possible reason is that they lack the capability of understanding and memorizing long-term dialogue history information. To address this issue, we present a novel task of Long-term Memory Conversation (LeMon) and then build a new dialogue dataset DuLeMon and a dialogue generation framework with Long-Term Memory (LTM) mechanism (called PLATO-LTM). This LTM mechanism enables our system to accurately extract and continuously update long-term persona memory without requiring mult"},"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":"2203.05797","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-11T08:41:14Z","cross_cats_sorted":[],"title_canon_sha256":"ca66dda5890bd8257950a84d6eb2208f1cf0d3db546a6ca82bcb3af854f0b3d0","abstract_canon_sha256":"71b39adbc6e0da058d115a5d9e941425d44ccd785326d85031925e6376320b40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:47.779362Z","signature_b64":"D1y04n+3oUwEqiqafhOU4A62hUQvpRMrj+B8w8JJhqP/3r4RDmIVzHatrN7yT/5X1CjEhnNHbrDCr0ZO+I+8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0d2ae9fb51ff49edb4e4464b67bc6470decf12272fd45fea518c4e42511d52d","last_reissued_at":"2026-07-05T04:04:47.778962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:47.778962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Long Time No See! Open-Domain Conversation with Long-Term Persona Memory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"HaiFeng Wang, Hua Wu, Shihang Wang, Wenquan Wu, Xinchao Xu, Zheng-Yu Niu, Zhibin Gou","submitted_at":"2022-03-11T08:41:14Z","abstract_excerpt":"Most of the open-domain dialogue models tend to perform poorly in the setting of long-term human-bot conversations. The possible reason is that they lack the capability of understanding and memorizing long-term dialogue history information. To address this issue, we present a novel task of Long-term Memory Conversation (LeMon) and then build a new dialogue dataset DuLeMon and a dialogue generation framework with Long-Term Memory (LTM) mechanism (called PLATO-LTM). This LTM mechanism enables our system to accurately extract and continuously update long-term persona memory without requiring mult"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.05797","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/2203.05797/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":"2203.05797","created_at":"2026-07-05T04:04:47.779016+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.05797v2","created_at":"2026-07-05T04:04:47.779016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.05797","created_at":"2026-07-05T04:04:47.779016+00:00"},{"alias_kind":"pith_short_12","alias_value":"WDJK5H5VD72J","created_at":"2026-07-05T04:04:47.779016+00:00"},{"alias_kind":"pith_short_16","alias_value":"WDJK5H5VD72J5W2O","created_at":"2026-07-05T04:04:47.779016+00:00"},{"alias_kind":"pith_short_8","alias_value":"WDJK5H5V","created_at":"2026-07-05T04:04:47.779016+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":136,"is_internal_anchor":false},{"citing_arxiv_id":"2410.17448","citing_title":"In Context Learning and Reasoning for Symbolic Regression with Large Language Models","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":192,"is_internal_anchor":false},{"citing_arxiv_id":"2305.10250","citing_title":"MemoryBank: Enhancing Large Language Models with Long-Term Memory","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WDJK5H5VD72J5W2OIRSLM66GI4","json":"https://pith.science/pith/WDJK5H5VD72J5W2OIRSLM66GI4.json","graph_json":"https://pith.science/api/pith-number/WDJK5H5VD72J5W2OIRSLM66GI4/graph.json","events_json":"https://pith.science/api/pith-number/WDJK5H5VD72J5W2OIRSLM66GI4/events.json","paper":"https://pith.science/paper/WDJK5H5V"},"agent_actions":{"view_html":"https://pith.science/pith/WDJK5H5VD72J5W2OIRSLM66GI4","download_json":"https://pith.science/pith/WDJK5H5VD72J5W2OIRSLM66GI4.json","view_paper":"https://pith.science/paper/WDJK5H5V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.05797&json=true","fetch_graph":"https://pith.science/api/pith-number/WDJK5H5VD72J5W2OIRSLM66GI4/graph.json","fetch_events":"https://pith.science/api/pith-number/WDJK5H5VD72J5W2OIRSLM66GI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WDJK5H5VD72J5W2OIRSLM66GI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WDJK5H5VD72J5W2OIRSLM66GI4/action/storage_attestation","attest_author":"https://pith.science/pith/WDJK5H5VD72J5W2OIRSLM66GI4/action/author_attestation","sign_citation":"https://pith.science/pith/WDJK5H5VD72J5W2OIRSLM66GI4/action/citation_signature","submit_replication":"https://pith.science/pith/WDJK5H5VD72J5W2OIRSLM66GI4/action/replication_record"}},"created_at":"2026-07-05T04:04:47.779016+00:00","updated_at":"2026-07-05T04:04:47.779016+00:00"}