{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RRGYSEOLOGYHXTJDHKQQ5P65ZC","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":"89c35e7f6b52c34b85d07ce4411302422619817bbc5d285514145976a21e1e70","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T15:43:09Z","title_canon_sha256":"c476c455dd704e0daf96055e2b79425cd04c30f0ce44fb71db8d9cf77cfdd39e"},"schema_version":"1.0","source":{"id":"2412.15995","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15995","created_at":"2026-07-05T09:52:33Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15995v1","created_at":"2026-07-05T09:52:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15995","created_at":"2026-07-05T09:52:33Z"},{"alias_kind":"pith_short_12","alias_value":"RRGYSEOLOGYH","created_at":"2026-07-05T09:52:33Z"},{"alias_kind":"pith_short_16","alias_value":"RRGYSEOLOGYHXTJD","created_at":"2026-07-05T09:52:33Z"},{"alias_kind":"pith_short_8","alias_value":"RRGYSEOL","created_at":"2026-07-05T09:52:33Z"}],"graph_snapshots":[{"event_id":"sha256:0e7b654e9dc92d5a8e8fb67f2e950ae15521a3924e6bf9609581518159876019","target":"graph","created_at":"2026-07-05T09:52:33Z","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/2412.15995/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Maximillian Chen, Ruoxi Sun, Sercan \\\"O. Ar{\\i}k","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T15:43:09Z","title":"Data-Centric Improvements for Enhancing Multi-Modal Understanding in Spoken Conversation Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15995","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:c8beff9425fc2d90c7de1ea67623e8d31c8192d3d8ababfc58a47a435ff89a22","target":"record","created_at":"2026-07-05T09:52:33Z","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":"89c35e7f6b52c34b85d07ce4411302422619817bbc5d285514145976a21e1e70","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-20T15:43:09Z","title_canon_sha256":"c476c455dd704e0daf96055e2b79425cd04c30f0ce44fb71db8d9cf77cfdd39e"},"schema_version":"1.0","source":{"id":"2412.15995","kind":"arxiv","version":1}},"canonical_sha256":"8c4d8911cb71b07bcd233aa10ebfddc8af5037c42c39c536b74dc8ded4054843","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c4d8911cb71b07bcd233aa10ebfddc8af5037c42c39c536b74dc8ded4054843","first_computed_at":"2026-07-05T09:52:33.275874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:33.275874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hf8V4EW4gxFT1XYQ0jfBfZqLJjHa0oqWDxYSq+TQR+w4NyO9Jexjo4dTAGm21tLOjKnewLyZYFBavU9VfSs5AA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:33.276266Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15995","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8beff9425fc2d90c7de1ea67623e8d31c8192d3d8ababfc58a47a435ff89a22","sha256:0e7b654e9dc92d5a8e8fb67f2e950ae15521a3924e6bf9609581518159876019"],"state_sha256":"3c21228d1083e72d4b4315f69816b684804677a8d14cfd9125430f8b18c92575"}