{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LULEAPHJ6SNRSL6J4AS6A74EJU","short_pith_number":"pith:LULEAPHJ","canonical_record":{"source":{"id":"2009.12735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-27T03:33:22Z","cross_cats_sorted":["cs.HC","cs.LG"],"title_canon_sha256":"a9719f66a328e62881d4f85b94ee11680ad0bd958bb0a6abc01794f834dbc741","abstract_canon_sha256":"1be05ab6e54bd8ecaacbcd9445f88c9f09bbecf8737d73bd1fc20573bec0efe1"},"schema_version":"1.0"},"canonical_sha256":"5d16403ce9f49b192fc9e025e07f844d36c263d00ef5a45a8d8dff82722a05d4","source":{"kind":"arxiv","id":"2009.12735","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.12735","created_at":"2026-07-05T01:38:22Z"},{"alias_kind":"arxiv_version","alias_value":"2009.12735v1","created_at":"2026-07-05T01:38:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12735","created_at":"2026-07-05T01:38:22Z"},{"alias_kind":"pith_short_12","alias_value":"LULEAPHJ6SNR","created_at":"2026-07-05T01:38:22Z"},{"alias_kind":"pith_short_16","alias_value":"LULEAPHJ6SNRSL6J","created_at":"2026-07-05T01:38:22Z"},{"alias_kind":"pith_short_8","alias_value":"LULEAPHJ","created_at":"2026-07-05T01:38:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LULEAPHJ6SNRSL6J4AS6A74EJU","target":"record","payload":{"canonical_record":{"source":{"id":"2009.12735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-27T03:33:22Z","cross_cats_sorted":["cs.HC","cs.LG"],"title_canon_sha256":"a9719f66a328e62881d4f85b94ee11680ad0bd958bb0a6abc01794f834dbc741","abstract_canon_sha256":"1be05ab6e54bd8ecaacbcd9445f88c9f09bbecf8737d73bd1fc20573bec0efe1"},"schema_version":"1.0"},"canonical_sha256":"5d16403ce9f49b192fc9e025e07f844d36c263d00ef5a45a8d8dff82722a05d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:22.804460Z","signature_b64":"Le1v1w81BrK4mgTh2LaMIvx7LQixiTwulfqurju9grIbFqwVTZjrcINA4VFSQHlyuwj0HjfMooOBCrFCAMLfCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d16403ce9f49b192fc9e025e07f844d36c263d00ef5a45a8d8dff82722a05d4","last_reissued_at":"2026-07-05T01:38:22.803830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:22.803830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.12735","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:38:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bCpVn+1Dhsxf6zHf0tja1IUhf3OLPZk0HF1yag6yAHoJ9kSt4pOIfY6kue1kVZJr5ye/8NKo1/3S5otcBI6dCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:35:58.367255Z"},"content_sha256":"66333c6bc01df57f8ed7e375b897dfd684419890d6ff30a3964c3ef388a7f198","schema_version":"1.0","event_id":"sha256:66333c6bc01df57f8ed7e375b897dfd684419890d6ff30a3964c3ef388a7f198"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LULEAPHJ6SNRSL6J4AS6A74EJU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modeling Topical Relevance for Multi-Turn Dialogue Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dawei Yin, Hainan Zhang, Hongshen Chen, Liang Pang, Yanyan Lan, Zhuoye Ding","submitted_at":"2020-09-27T03:33:22Z","abstract_excerpt":"Topic drift is a common phenomenon in multi-turn dialogue. Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropriate responses accordingly. However, existing models usually use word or sentence level similarities to detect the relevant contexts, which fail to well capture the topical level relevance. In this paper, we propose a new model, named STAR-BTM, to tackle this problem. Firstly, the Biterm Topic Model is pre-trained on the whole training dataset. Then, the topic level attention we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12735","kind":"arxiv","version":1},"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/2009.12735/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:38:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KxtSkSPlUp8d+/igR1LIHHH3E9KR+9jy4S7J3HSIPycj7WQ8SMxRxSB2aOC9ekM1heaBZb+eIUtrLghIHV7gBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T13:35:58.367898Z"},"content_sha256":"ffe74412733eef461b5465155244130abb472280efb748c54ac74440958020c2","schema_version":"1.0","event_id":"sha256:ffe74412733eef461b5465155244130abb472280efb748c54ac74440958020c2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LULEAPHJ6SNRSL6J4AS6A74EJU/bundle.json","state_url":"https://pith.science/pith/LULEAPHJ6SNRSL6J4AS6A74EJU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LULEAPHJ6SNRSL6J4AS6A74EJU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-31T13:35:58Z","links":{"resolver":"https://pith.science/pith/LULEAPHJ6SNRSL6J4AS6A74EJU","bundle":"https://pith.science/pith/LULEAPHJ6SNRSL6J4AS6A74EJU/bundle.json","state":"https://pith.science/pith/LULEAPHJ6SNRSL6J4AS6A74EJU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LULEAPHJ6SNRSL6J4AS6A74EJU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LULEAPHJ6SNRSL6J4AS6A74EJU","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":"1be05ab6e54bd8ecaacbcd9445f88c9f09bbecf8737d73bd1fc20573bec0efe1","cross_cats_sorted":["cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-27T03:33:22Z","title_canon_sha256":"a9719f66a328e62881d4f85b94ee11680ad0bd958bb0a6abc01794f834dbc741"},"schema_version":"1.0","source":{"id":"2009.12735","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.12735","created_at":"2026-07-05T01:38:22Z"},{"alias_kind":"arxiv_version","alias_value":"2009.12735v1","created_at":"2026-07-05T01:38:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12735","created_at":"2026-07-05T01:38:22Z"},{"alias_kind":"pith_short_12","alias_value":"LULEAPHJ6SNR","created_at":"2026-07-05T01:38:22Z"},{"alias_kind":"pith_short_16","alias_value":"LULEAPHJ6SNRSL6J","created_at":"2026-07-05T01:38:22Z"},{"alias_kind":"pith_short_8","alias_value":"LULEAPHJ","created_at":"2026-07-05T01:38:22Z"}],"graph_snapshots":[{"event_id":"sha256:ffe74412733eef461b5465155244130abb472280efb748c54ac74440958020c2","target":"graph","created_at":"2026-07-05T01:38:22Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2009.12735/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Topic drift is a common phenomenon in multi-turn dialogue. Therefore, an ideal dialogue generation models should be able to capture the topic information of each context, detect the relevant context, and produce appropriate responses accordingly. However, existing models usually use word or sentence level similarities to detect the relevant contexts, which fail to well capture the topical level relevance. In this paper, we propose a new model, named STAR-BTM, to tackle this problem. Firstly, the Biterm Topic Model is pre-trained on the whole training dataset. Then, the topic level attention we","authors_text":"Dawei Yin, Hainan Zhang, Hongshen Chen, Liang Pang, Yanyan Lan, Zhuoye Ding","cross_cats":["cs.HC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-27T03:33:22Z","title":"Modeling Topical Relevance for Multi-Turn Dialogue Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12735","kind":"arxiv","version":1},"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":"sha256:66333c6bc01df57f8ed7e375b897dfd684419890d6ff30a3964c3ef388a7f198","target":"record","created_at":"2026-07-05T01:38:22Z","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":"1be05ab6e54bd8ecaacbcd9445f88c9f09bbecf8737d73bd1fc20573bec0efe1","cross_cats_sorted":["cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-27T03:33:22Z","title_canon_sha256":"a9719f66a328e62881d4f85b94ee11680ad0bd958bb0a6abc01794f834dbc741"},"schema_version":"1.0","source":{"id":"2009.12735","kind":"arxiv","version":1}},"canonical_sha256":"5d16403ce9f49b192fc9e025e07f844d36c263d00ef5a45a8d8dff82722a05d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d16403ce9f49b192fc9e025e07f844d36c263d00ef5a45a8d8dff82722a05d4","first_computed_at":"2026-07-05T01:38:22.803830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:38:22.803830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Le1v1w81BrK4mgTh2LaMIvx7LQixiTwulfqurju9grIbFqwVTZjrcINA4VFSQHlyuwj0HjfMooOBCrFCAMLfCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:38:22.804460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.12735","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66333c6bc01df57f8ed7e375b897dfd684419890d6ff30a3964c3ef388a7f198","sha256:ffe74412733eef461b5465155244130abb472280efb748c54ac74440958020c2"],"state_sha256":"d7c4da4ae9e45d067e3e6028c2c7837d076fe6025bcf12ff7ef47534fa25a638"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y5Y6D7mR/4xEimvMU35lgCLksX8vTziPFvm/pGTjN04b4RjkiktsHFfiMjVW87HO3qOKwinhiDfxDqUlfR4gAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T13:35:58.376656Z","bundle_sha256":"af3007eeb7a9eb6f1f2ba7ba2295be26d79c3cc8f10c2087ec41e2cd8ddaf06e"}}