{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4QGXVIZ2ST5UYNOKS2FXHEZQUB","short_pith_number":"pith:4QGXVIZ2","schema_version":"1.0","canonical_sha256":"e40d7aa33a94fb4c35ca968b739330a05a4de5f4d241f7b0ee08f9fa7b90de36","source":{"kind":"arxiv","id":"2607.29196","version":1},"attestation_state":"computed","paper":{"title":"Hy-MultiTurn: A Six-Dimensional Benchmark for Deep Multi-Turn Dialogue Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenxu Liu, Eileen Ye, Jiawen Tao, Maxm Pan, Mengzhou Wu, Wenhan Yu, Xiaokun Yuan, Yanbing Jiang, Yaoming Li, Yaxin Fan","submitted_at":"2026-07-31T09:15:56Z","abstract_excerpt":"Long-running multi-turn interactions with chatbots and agents are now common, and a correct response often depends on remembering earlier details, tracking later revisions, identifying intended objects or referents, and withholding action when required conditions are unmet. Existing multi-turn benchmarks typically cover short exchanges and do not fully evaluate these capabilities in long multi-turn interactions, particularly in Chinese, while offering limited insight into how and why models fail. To address these limitations, we analyze real chatbot failures to identify six recurring mechanism"},"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":"2607.29196","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-31T09:15:56Z","cross_cats_sorted":[],"title_canon_sha256":"fc0553043a7aa38c8041c0a8ab4e18ee0132d97c110491b69456a579991eab15","abstract_canon_sha256":"f460e43e1ab1ba492600c18da24a624ada4b3628eb2019f8e55f8f35457c82bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:20:57.531539Z","signature_b64":"r2vyXZDS08plVkH6upyQCDVVb84iPD8F31cqFZC+MsVTwAPFaDwCEqshD+s+uHKtGQAJTx2pribz871U+/26Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e40d7aa33a94fb4c35ca968b739330a05a4de5f4d241f7b0ee08f9fa7b90de36","last_reissued_at":"2026-08-03T01:20:57.530007Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:20:57.530007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hy-MultiTurn: A Six-Dimensional Benchmark for Deep Multi-Turn Dialogue Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenxu Liu, Eileen Ye, Jiawen Tao, Maxm Pan, Mengzhou Wu, Wenhan Yu, Xiaokun Yuan, Yanbing Jiang, Yaoming Li, Yaxin Fan","submitted_at":"2026-07-31T09:15:56Z","abstract_excerpt":"Long-running multi-turn interactions with chatbots and agents are now common, and a correct response often depends on remembering earlier details, tracking later revisions, identifying intended objects or referents, and withholding action when required conditions are unmet. Existing multi-turn benchmarks typically cover short exchanges and do not fully evaluate these capabilities in long multi-turn interactions, particularly in Chinese, while offering limited insight into how and why models fail. To address these limitations, we analyze real chatbot failures to identify six recurring mechanism"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29196","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/2607.29196/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":"2607.29196","created_at":"2026-08-03T01:20:57.530935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.29196v1","created_at":"2026-08-03T01:20:57.530935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29196","created_at":"2026-08-03T01:20:57.530935+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QGXVIZ2ST5U","created_at":"2026-08-03T01:20:57.530935+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QGXVIZ2ST5UYNOK","created_at":"2026-08-03T01:20:57.530935+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QGXVIZ2","created_at":"2026-08-03T01:20:57.530935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4QGXVIZ2ST5UYNOKS2FXHEZQUB","json":"https://pith.science/pith/4QGXVIZ2ST5UYNOKS2FXHEZQUB.json","graph_json":"https://pith.science/api/pith-number/4QGXVIZ2ST5UYNOKS2FXHEZQUB/graph.json","events_json":"https://pith.science/api/pith-number/4QGXVIZ2ST5UYNOKS2FXHEZQUB/events.json","paper":"https://pith.science/paper/4QGXVIZ2"},"agent_actions":{"view_html":"https://pith.science/pith/4QGXVIZ2ST5UYNOKS2FXHEZQUB","download_json":"https://pith.science/pith/4QGXVIZ2ST5UYNOKS2FXHEZQUB.json","view_paper":"https://pith.science/paper/4QGXVIZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.29196&json=true","fetch_graph":"https://pith.science/api/pith-number/4QGXVIZ2ST5UYNOKS2FXHEZQUB/graph.json","fetch_events":"https://pith.science/api/pith-number/4QGXVIZ2ST5UYNOKS2FXHEZQUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QGXVIZ2ST5UYNOKS2FXHEZQUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QGXVIZ2ST5UYNOKS2FXHEZQUB/action/storage_attestation","attest_author":"https://pith.science/pith/4QGXVIZ2ST5UYNOKS2FXHEZQUB/action/author_attestation","sign_citation":"https://pith.science/pith/4QGXVIZ2ST5UYNOKS2FXHEZQUB/action/citation_signature","submit_replication":"https://pith.science/pith/4QGXVIZ2ST5UYNOKS2FXHEZQUB/action/replication_record"}},"created_at":"2026-08-03T01:20:57.530935+00:00","updated_at":"2026-08-03T01:20:57.530935+00:00"}