{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HGGUFKMU3AHM6CVVCL3TMKDDCW","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":"9c3dc0e4c003e59003bc9b349efddbd5495cbf87bc4436f2b4570f6be43d2932","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-28T00:42:45Z","title_canon_sha256":"0246965f7dcf179dea863480482de177b8edc5d6fce929ee45884d55ed336a93"},"schema_version":"1.0","source":{"id":"2605.29209","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29209","created_at":"2026-05-29T01:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29209v1","created_at":"2026-05-29T01:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29209","created_at":"2026-05-29T01:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"HGGUFKMU3AHM","created_at":"2026-05-29T01:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"HGGUFKMU3AHM6CVV","created_at":"2026-05-29T01:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"HGGUFKMU","created_at":"2026-05-29T01:05:24Z"}],"graph_snapshots":[{"event_id":"sha256:f473fd6d8f0ce10bdf6257aaf64fe1d82151bcef22ee6870b7eb54f6e83dec16","target":"graph","created_at":"2026-05-29T01:05:24Z","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/2605.29209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The pursuit of a \"unified\" discrete token for both speech understanding and generation has led the Speech Language Model (SLM) community to heavily rely on Word Error Rate (WER) -- the core metric for Whisper-style tokenizers -- as the definitive proxy for representation quality. This fosters the assumption that low-WER tokens inherently preserve the information necessary for intelligible acoustic synthesis. We argue this is fundamentally deceptive. While high-frequency tokens succeed in generation tasks due to implicit information leakage, isolating pure semantic information at ultra-low fram","authors_text":"Beena Ahmed, Haoyang Zhang, Hexin Liu, Julien Epps, Qiquan Zhang, Shiqi Han, Xiangyu Zhang, Yuxin Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-28T00:42:45Z","title":"The WER Trap: Shattering the Illusion of Unified Tokens in Speech Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29209","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:ead3b355b459d189404c22ade3cb21a50c25905739893367b4d96e93231713d2","target":"record","created_at":"2026-05-29T01:05:24Z","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":"9c3dc0e4c003e59003bc9b349efddbd5495cbf87bc4436f2b4570f6be43d2932","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-05-28T00:42:45Z","title_canon_sha256":"0246965f7dcf179dea863480482de177b8edc5d6fce929ee45884d55ed336a93"},"schema_version":"1.0","source":{"id":"2605.29209","kind":"arxiv","version":1}},"canonical_sha256":"398d42a994d80ecf0ab512f736286315b9fcf5a5f7a428c578a8b83813d67847","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"398d42a994d80ecf0ab512f736286315b9fcf5a5f7a428c578a8b83813d67847","first_computed_at":"2026-05-29T01:05:24.439019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:24.439019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L86SIycFW4dpSp39sUl4qHmDA4bl5QT02qlIqapmSJM73yC9VWGxgRHcCJXKyofPTCH8Q3V8zDwR7A3U532cDg==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:24.439930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29209","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ead3b355b459d189404c22ade3cb21a50c25905739893367b4d96e93231713d2","sha256:f473fd6d8f0ce10bdf6257aaf64fe1d82151bcef22ee6870b7eb54f6e83dec16"],"state_sha256":"c11fc8cab5ed39fd93d0f2bbfe5360dfa5e3d7ccb57817127d3835f12ada01b9"}