{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SIZMHBCAGCSCOFRBNZLC3JQ5MM","short_pith_number":"pith:SIZMHBCA","schema_version":"1.0","canonical_sha256":"9232c3844030a42716216e562da61d63260764861fad9ed3f20d58219fe24ed0","source":{"kind":"arxiv","id":"2606.22473","version":1},"attestation_state":"computed","paper":{"title":"Interleaved Speech Language Models Latently Work In Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Gallil Maimon, Talia Sternberg, Yossi Adi","submitted_at":"2026-06-21T12:33:44Z","abstract_excerpt":"Speech language models (SLMs) have been extensively studied, with the common paradigm incorporating text data and pre-trained text LMs. A leading approach is speech-text interleaving in which models are trained over sequences containing both speech and text tokens, aiming to boost even speech-only capabilities. Yet the way these two modalities interact in the model latent space remains unclear. In this work, we analyze interleaved speech-text LMs from different model families and sizes through the scope of the logit lens to provide such insight. We reveal that these models go through an implic"},"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":"2606.22473","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-21T12:33:44Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"97ddc7c5b197b7b0560fe350bf1a3a391f66dee27d230e057137311a0ac7f04e","abstract_canon_sha256":"d617339884b8b789dc405d2b56cf8ce525371aecdb1250c37da4e5c67aa2a670"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:39.288872Z","signature_b64":"kKu+GytUmH8fmHZRYOUElEOwz2+5fw0i0IJs+HPpDmb5wdIYHR1uv3OoLuIvtqQ3U5TCN03oz5DmmDNnR/c0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9232c3844030a42716216e562da61d63260764861fad9ed3f20d58219fe24ed0","last_reissued_at":"2026-06-23T02:13:39.288469Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:39.288469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interleaved Speech Language Models Latently Work In Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Gallil Maimon, Talia Sternberg, Yossi Adi","submitted_at":"2026-06-21T12:33:44Z","abstract_excerpt":"Speech language models (SLMs) have been extensively studied, with the common paradigm incorporating text data and pre-trained text LMs. A leading approach is speech-text interleaving in which models are trained over sequences containing both speech and text tokens, aiming to boost even speech-only capabilities. Yet the way these two modalities interact in the model latent space remains unclear. In this work, we analyze interleaved speech-text LMs from different model families and sizes through the scope of the logit lens to provide such insight. We reveal that these models go through an implic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22473","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/2606.22473/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":"2606.22473","created_at":"2026-06-23T02:13:39.288535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.22473v1","created_at":"2026-06-23T02:13:39.288535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22473","created_at":"2026-06-23T02:13:39.288535+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIZMHBCAGCSC","created_at":"2026-06-23T02:13:39.288535+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIZMHBCAGCSCOFRB","created_at":"2026-06-23T02:13:39.288535+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIZMHBCA","created_at":"2026-06-23T02:13:39.288535+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/SIZMHBCAGCSCOFRBNZLC3JQ5MM","json":"https://pith.science/pith/SIZMHBCAGCSCOFRBNZLC3JQ5MM.json","graph_json":"https://pith.science/api/pith-number/SIZMHBCAGCSCOFRBNZLC3JQ5MM/graph.json","events_json":"https://pith.science/api/pith-number/SIZMHBCAGCSCOFRBNZLC3JQ5MM/events.json","paper":"https://pith.science/paper/SIZMHBCA"},"agent_actions":{"view_html":"https://pith.science/pith/SIZMHBCAGCSCOFRBNZLC3JQ5MM","download_json":"https://pith.science/pith/SIZMHBCAGCSCOFRBNZLC3JQ5MM.json","view_paper":"https://pith.science/paper/SIZMHBCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.22473&json=true","fetch_graph":"https://pith.science/api/pith-number/SIZMHBCAGCSCOFRBNZLC3JQ5MM/graph.json","fetch_events":"https://pith.science/api/pith-number/SIZMHBCAGCSCOFRBNZLC3JQ5MM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIZMHBCAGCSCOFRBNZLC3JQ5MM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIZMHBCAGCSCOFRBNZLC3JQ5MM/action/storage_attestation","attest_author":"https://pith.science/pith/SIZMHBCAGCSCOFRBNZLC3JQ5MM/action/author_attestation","sign_citation":"https://pith.science/pith/SIZMHBCAGCSCOFRBNZLC3JQ5MM/action/citation_signature","submit_replication":"https://pith.science/pith/SIZMHBCAGCSCOFRBNZLC3JQ5MM/action/replication_record"}},"created_at":"2026-06-23T02:13:39.288535+00:00","updated_at":"2026-06-23T02:13:39.288535+00:00"}