{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IQSJEGLVOLEDJONHOKENT3MW7O","short_pith_number":"pith:IQSJEGLV","schema_version":"1.0","canonical_sha256":"442492197572c834b9a77288d9ed96fbb62d2845bb0ed7b761cb8baca1202bf6","source":{"kind":"arxiv","id":"2502.19759","version":2},"attestation_state":"computed","paper":{"title":"Does Your Voice Assistant Remember? Analyzing Conversational Context Recall and Utilization in Voice Interaction Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Che Hyun Lee, Heeseung Kim, Jiheum Yeom, Nohil Park, Sangkwon Park, Sangwon Yu, Sungroh Yoon","submitted_at":"2025-02-27T04:53:55Z","abstract_excerpt":"Recent advancements in multi-turn voice interaction models have improved user-model communication. However, while closed-source models effectively retain and recall past utterances, whether open-source models share this ability remains unexplored. To fill this gap, we systematically evaluate how well open-source interaction models utilize past utterances using ContextDialog, a benchmark we proposed for this purpose. Our findings show that speech-based models have more difficulty than text-based ones, especially when recalling information conveyed in speech, and even with retrieval-augmented ge"},"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":"2502.19759","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-02-27T04:53:55Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"963fd4bd802f85bfea055cf1e79811bc1401783ee1da74bea02c55afd8cf04df","abstract_canon_sha256":"83967a3267d00a99f75d152ac0054231a72c51269d14097165d317492c252988"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:17.329756Z","signature_b64":"y3trDsykXatRsFvEOq3naRzhTTkyqLLzCLuMt87CrXcxTVmMn/bbCqmFZ9rq3CueFaWOMwsqTeVYT4mz+dwpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"442492197572c834b9a77288d9ed96fbb62d2845bb0ed7b761cb8baca1202bf6","last_reissued_at":"2026-07-05T11:08:17.329156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:17.329156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Your Voice Assistant Remember? Analyzing Conversational Context Recall and Utilization in Voice Interaction Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Che Hyun Lee, Heeseung Kim, Jiheum Yeom, Nohil Park, Sangkwon Park, Sangwon Yu, Sungroh Yoon","submitted_at":"2025-02-27T04:53:55Z","abstract_excerpt":"Recent advancements in multi-turn voice interaction models have improved user-model communication. However, while closed-source models effectively retain and recall past utterances, whether open-source models share this ability remains unexplored. To fill this gap, we systematically evaluate how well open-source interaction models utilize past utterances using ContextDialog, a benchmark we proposed for this purpose. Our findings show that speech-based models have more difficulty than text-based ones, especially when recalling information conveyed in speech, and even with retrieval-augmented ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19759","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/2502.19759/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":"2502.19759","created_at":"2026-07-05T11:08:17.329221+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.19759v2","created_at":"2026-07-05T11:08:17.329221+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19759","created_at":"2026-07-05T11:08:17.329221+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQSJEGLVOLED","created_at":"2026-07-05T11:08:17.329221+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQSJEGLVOLEDJONH","created_at":"2026-07-05T11:08:17.329221+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQSJEGLV","created_at":"2026-07-05T11:08:17.329221+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.15957","citing_title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2602.12783","citing_title":"SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IQSJEGLVOLEDJONHOKENT3MW7O","json":"https://pith.science/pith/IQSJEGLVOLEDJONHOKENT3MW7O.json","graph_json":"https://pith.science/api/pith-number/IQSJEGLVOLEDJONHOKENT3MW7O/graph.json","events_json":"https://pith.science/api/pith-number/IQSJEGLVOLEDJONHOKENT3MW7O/events.json","paper":"https://pith.science/paper/IQSJEGLV"},"agent_actions":{"view_html":"https://pith.science/pith/IQSJEGLVOLEDJONHOKENT3MW7O","download_json":"https://pith.science/pith/IQSJEGLVOLEDJONHOKENT3MW7O.json","view_paper":"https://pith.science/paper/IQSJEGLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.19759&json=true","fetch_graph":"https://pith.science/api/pith-number/IQSJEGLVOLEDJONHOKENT3MW7O/graph.json","fetch_events":"https://pith.science/api/pith-number/IQSJEGLVOLEDJONHOKENT3MW7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQSJEGLVOLEDJONHOKENT3MW7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQSJEGLVOLEDJONHOKENT3MW7O/action/storage_attestation","attest_author":"https://pith.science/pith/IQSJEGLVOLEDJONHOKENT3MW7O/action/author_attestation","sign_citation":"https://pith.science/pith/IQSJEGLVOLEDJONHOKENT3MW7O/action/citation_signature","submit_replication":"https://pith.science/pith/IQSJEGLVOLEDJONHOKENT3MW7O/action/replication_record"}},"created_at":"2026-07-05T11:08:17.329221+00:00","updated_at":"2026-07-05T11:08:17.329221+00:00"}