{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H3TEP2GWO7BH44GGRADHOHKKCR","short_pith_number":"pith:H3TEP2GW","schema_version":"1.0","canonical_sha256":"3ee647e8d677c27e70c68806771d4a144c05f9e55a19c1b0be68a4681b43aac8","source":{"kind":"arxiv","id":"2606.04474","version":1},"attestation_state":"computed","paper":{"title":"Entity Binding Failures in Speech LLM Reasoning: Diagnosis and Chain-of-Thought Intervention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Jun Zhang, Ming-Hao Hsu, Xiaohai Tian, Zhizheng Wu","submitted_at":"2026-06-03T05:44:09Z","abstract_excerpt":"Speech Large Language Models (SLLMs) underperform their text counterparts on complex reasoning. We reveal that this modality gap is not a uniform cognitive deficit. Evaluating three diverse SLLMs, we show speech-to-text (S2T) matches or exceeds text-to-text (T2T) on spatial, syntactic, and factual tasks. However, on logical tasks requiring entity tracking, S2T accuracy collapses to chance. We diagnose this localized degradation as an entity binding failure: continuous speech features cause models to lose precise entity-property associations during implicit reasoning. To resolve this, we propos"},"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":"2606.04474","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T05:44:09Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"67af7ab48254bfef9d96b8b03137275a2ada2df88c8101eb4a50c5ea887dac93","abstract_canon_sha256":"a0fac677439af50f1027e13895f85bde8ce530307e30789868601de5098bac1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:09.571891Z","signature_b64":"e6LjKSCSYUosnesQSaY/hVxn2S499QRzCadbw+Gg18GqcX4pPDYI9zpdjIQF4ZZ383v+i0HWjFw/w4hLO5w+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ee647e8d677c27e70c68806771d4a144c05f9e55a19c1b0be68a4681b43aac8","last_reissued_at":"2026-06-04T01:09:09.571333Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:09.571333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entity Binding Failures in Speech LLM Reasoning: Diagnosis and Chain-of-Thought Intervention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Jun Zhang, Ming-Hao Hsu, Xiaohai Tian, Zhizheng Wu","submitted_at":"2026-06-03T05:44:09Z","abstract_excerpt":"Speech Large Language Models (SLLMs) underperform their text counterparts on complex reasoning. We reveal that this modality gap is not a uniform cognitive deficit. Evaluating three diverse SLLMs, we show speech-to-text (S2T) matches or exceeds text-to-text (T2T) on spatial, syntactic, and factual tasks. However, on logical tasks requiring entity tracking, S2T accuracy collapses to chance. We diagnose this localized degradation as an entity binding failure: continuous speech features cause models to lose precise entity-property associations during implicit reasoning. To resolve this, we propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04474","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/2606.04474/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":"2606.04474","created_at":"2026-06-04T01:09:09.571423+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04474v1","created_at":"2026-06-04T01:09:09.571423+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04474","created_at":"2026-06-04T01:09:09.571423+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3TEP2GWO7BH","created_at":"2026-06-04T01:09:09.571423+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3TEP2GWO7BH44GG","created_at":"2026-06-04T01:09:09.571423+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3TEP2GW","created_at":"2026-06-04T01:09:09.571423+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H3TEP2GWO7BH44GGRADHOHKKCR","json":"https://pith.science/pith/H3TEP2GWO7BH44GGRADHOHKKCR.json","graph_json":"https://pith.science/api/pith-number/H3TEP2GWO7BH44GGRADHOHKKCR/graph.json","events_json":"https://pith.science/api/pith-number/H3TEP2GWO7BH44GGRADHOHKKCR/events.json","paper":"https://pith.science/paper/H3TEP2GW"},"agent_actions":{"view_html":"https://pith.science/pith/H3TEP2GWO7BH44GGRADHOHKKCR","download_json":"https://pith.science/pith/H3TEP2GWO7BH44GGRADHOHKKCR.json","view_paper":"https://pith.science/paper/H3TEP2GW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04474&json=true","fetch_graph":"https://pith.science/api/pith-number/H3TEP2GWO7BH44GGRADHOHKKCR/graph.json","fetch_events":"https://pith.science/api/pith-number/H3TEP2GWO7BH44GGRADHOHKKCR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3TEP2GWO7BH44GGRADHOHKKCR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3TEP2GWO7BH44GGRADHOHKKCR/action/storage_attestation","attest_author":"https://pith.science/pith/H3TEP2GWO7BH44GGRADHOHKKCR/action/author_attestation","sign_citation":"https://pith.science/pith/H3TEP2GWO7BH44GGRADHOHKKCR/action/citation_signature","submit_replication":"https://pith.science/pith/H3TEP2GWO7BH44GGRADHOHKKCR/action/replication_record"}},"created_at":"2026-06-04T01:09:09.571423+00:00","updated_at":"2026-06-04T01:09:09.571423+00:00"}