{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RRGYSEOLOGYHXTJDHKQQ5P65ZC","short_pith_number":"pith:RRGYSEOL","schema_version":"1.0","canonical_sha256":"8c4d8911cb71b07bcd233aa10ebfddc8af5037c42c39c536b74dc8ded4054843","source":{"kind":"arxiv","id":"2412.15995","version":1},"attestation_state":"computed","paper":{"title":"Data-Centric Improvements for Enhancing Multi-Modal Understanding in Spoken Conversation Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Maximillian Chen, Ruoxi Sun, Sercan \\\"O. Ar{\\i}k","submitted_at":"2024-12-20T15:43:09Z","abstract_excerpt":"Conversational assistants are increasingly popular across diverse real-world applications, highlighting the need for advanced multimodal speech modeling. Speech, as a natural mode of communication, encodes rich user-specific characteristics such as speaking rate and pitch, making it critical for effective interaction. Our work introduces a data-centric customization approach for efficiently enhancing multimodal understanding in conversational speech modeling. Central to our contributions is a novel multi-task learning paradigm that involves designing auxiliary tasks to utilize a small amount o"},"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":"2412.15995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T15:43:09Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"c476c455dd704e0daf96055e2b79425cd04c30f0ce44fb71db8d9cf77cfdd39e","abstract_canon_sha256":"89c35e7f6b52c34b85d07ce4411302422619817bbc5d285514145976a21e1e70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:33.276266Z","signature_b64":"Hf8V4EW4gxFT1XYQ0jfBfZqLJjHa0oqWDxYSq+TQR+w4NyO9Jexjo4dTAGm21tLOjKnewLyZYFBavU9VfSs5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c4d8911cb71b07bcd233aa10ebfddc8af5037c42c39c536b74dc8ded4054843","last_reissued_at":"2026-07-05T09:52:33.275874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:33.275874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Centric Improvements for Enhancing Multi-Modal Understanding in Spoken Conversation Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Maximillian Chen, Ruoxi Sun, Sercan \\\"O. Ar{\\i}k","submitted_at":"2024-12-20T15:43:09Z","abstract_excerpt":"Conversational assistants are increasingly popular across diverse real-world applications, highlighting the need for advanced multimodal speech modeling. Speech, as a natural mode of communication, encodes rich user-specific characteristics such as speaking rate and pitch, making it critical for effective interaction. Our work introduces a data-centric customization approach for efficiently enhancing multimodal understanding in conversational speech modeling. Central to our contributions is a novel multi-task learning paradigm that involves designing auxiliary tasks to utilize a small amount o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15995","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/2412.15995/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":"2412.15995","created_at":"2026-07-05T09:52:33.275929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15995v1","created_at":"2026-07-05T09:52:33.275929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15995","created_at":"2026-07-05T09:52:33.275929+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRGYSEOLOGYH","created_at":"2026-07-05T09:52:33.275929+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRGYSEOLOGYHXTJD","created_at":"2026-07-05T09:52:33.275929+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRGYSEOL","created_at":"2026-07-05T09:52:33.275929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19163","citing_title":"SpokenNativQA: Multilingual Everyday Spoken Queries for LLMs","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRGYSEOLOGYHXTJDHKQQ5P65ZC","json":"https://pith.science/pith/RRGYSEOLOGYHXTJDHKQQ5P65ZC.json","graph_json":"https://pith.science/api/pith-number/RRGYSEOLOGYHXTJDHKQQ5P65ZC/graph.json","events_json":"https://pith.science/api/pith-number/RRGYSEOLOGYHXTJDHKQQ5P65ZC/events.json","paper":"https://pith.science/paper/RRGYSEOL"},"agent_actions":{"view_html":"https://pith.science/pith/RRGYSEOLOGYHXTJDHKQQ5P65ZC","download_json":"https://pith.science/pith/RRGYSEOLOGYHXTJDHKQQ5P65ZC.json","view_paper":"https://pith.science/paper/RRGYSEOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15995&json=true","fetch_graph":"https://pith.science/api/pith-number/RRGYSEOLOGYHXTJDHKQQ5P65ZC/graph.json","fetch_events":"https://pith.science/api/pith-number/RRGYSEOLOGYHXTJDHKQQ5P65ZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRGYSEOLOGYHXTJDHKQQ5P65ZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRGYSEOLOGYHXTJDHKQQ5P65ZC/action/storage_attestation","attest_author":"https://pith.science/pith/RRGYSEOLOGYHXTJDHKQQ5P65ZC/action/author_attestation","sign_citation":"https://pith.science/pith/RRGYSEOLOGYHXTJDHKQQ5P65ZC/action/citation_signature","submit_replication":"https://pith.science/pith/RRGYSEOLOGYHXTJDHKQQ5P65ZC/action/replication_record"}},"created_at":"2026-07-05T09:52:33.275929+00:00","updated_at":"2026-07-05T09:52:33.275929+00:00"}