{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LAQC3IRVGI6WTQILMII4IIVXGS","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":"a7025a163fbeb83fdfaa6f2321a861c90e5bdcc4510d8206130d7bd62e86c76b","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-10T15:19:15Z","title_canon_sha256":"70360d03cad159b71824a303a5f776cbe995cdb1a4d7bc5b67f71a83b06afbaa"},"schema_version":"1.0","source":{"id":"2606.12199","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12199","created_at":"2026-06-11T01:10:53Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12199v1","created_at":"2026-06-11T01:10:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12199","created_at":"2026-06-11T01:10:53Z"},{"alias_kind":"pith_short_12","alias_value":"LAQC3IRVGI6W","created_at":"2026-06-11T01:10:53Z"},{"alias_kind":"pith_short_16","alias_value":"LAQC3IRVGI6WTQIL","created_at":"2026-06-11T01:10:53Z"},{"alias_kind":"pith_short_8","alias_value":"LAQC3IRV","created_at":"2026-06-11T01:10:53Z"}],"graph_snapshots":[{"event_id":"sha256:ab6aba8ad29e78058d0c1faa0e05399af68762d636a9cc6d0b19598f7c401298","target":"graph","created_at":"2026-06-11T01:10:53Z","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/2606.12199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spoken dialogue models typically start from text LLM backbones, yet reasoning often degrades when conditioning on speech instead of text. We attribute part of this modality gap to a temporal-granularity mismatch: speech tokens are temporally redundant and far longer than text under matched semantics, diluting per-token semantic density and weakening text-native reasoning dynamics. We study speech token design as a representation selection problem and sweep frame rates under a frozen LLM backbone with a fixed information rate. To make low frame rates feasible, we introduce factorized FSQ and a ","authors_text":"Chimin Chan, Guangyan Zhang, Haohe Liu, Hongzhan Lin, Peiwen Sun, Qiuqiang Kong, Wei Xue, Xinshen Zhang, Xu Tan, Yiming Li, Zhengxi Liu, Zhen Ye, Zheqi Dai","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-10T15:19:15Z","title":"Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12199","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":"sha256:107d79750c4daaae0f0ee1d01dee293bd88cb0973c0b768d80203001e8605064","target":"record","created_at":"2026-06-11T01:10:53Z","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":"a7025a163fbeb83fdfaa6f2321a861c90e5bdcc4510d8206130d7bd62e86c76b","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-10T15:19:15Z","title_canon_sha256":"70360d03cad159b71824a303a5f776cbe995cdb1a4d7bc5b67f71a83b06afbaa"},"schema_version":"1.0","source":{"id":"2606.12199","kind":"arxiv","version":1}},"canonical_sha256":"58202da235323d69c10b6211c422b73484ea705b0182461ab4ebebce678bef1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58202da235323d69c10b6211c422b73484ea705b0182461ab4ebebce678bef1a","first_computed_at":"2026-06-11T01:10:53.915586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:10:53.915586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uf+sgiyF0wf0m/H9csjS7ggncS+lIfR6sx4VP2s/eplTAnnCxBC3dCuKQlvrOjsYo23ADUosgeI5iq1RcF3jDg==","signature_status":"signed_v1","signed_at":"2026-06-11T01:10:53.916454Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12199","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:107d79750c4daaae0f0ee1d01dee293bd88cb0973c0b768d80203001e8605064","sha256:ab6aba8ad29e78058d0c1faa0e05399af68762d636a9cc6d0b19598f7c401298"],"state_sha256":"afe2a5236da2096f7f1ac43790c0da09a7651e447b0a3e562c5767197d67b5df"}