{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IHYGPVJGLY6N5YDSLEPPIJ53Z3","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":"147142321a9959675cc671dce89b94c2d04c2d80a64343dbf2fb63227a305249","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-02T14:22:46Z","title_canon_sha256":"35bb8561fe378424ff732172b2ff2f45026c7ab8a3f082d52a31222b83a862f5"},"schema_version":"1.0","source":{"id":"2607.02214","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02214","created_at":"2026-07-03T01:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02214v1","created_at":"2026-07-03T01:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02214","created_at":"2026-07-03T01:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"IHYGPVJGLY6N","created_at":"2026-07-03T01:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"IHYGPVJGLY6N5YDS","created_at":"2026-07-03T01:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"IHYGPVJG","created_at":"2026-07-03T01:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:2e1ed088fd48e4b590a4f41c1812deac8444a01ded689881a320ae7066bda634","target":"graph","created_at":"2026-07-03T01:17:45Z","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/2607.02214/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning for speech language models (SLMs) is substantially more challenging than for text-based large language models (LLMs), as it requires learning a new modality and a wide range of speech-specific instructions in addition to those supported by text LLMs. Existing SLM training approaches largely replicate the text LLM training paradigm by synthesizing large-scale speech pre-training and instruction-tuning datasets. However, this strategy is difficult to scale, since speech sequences are significantly longer than text sequences. In this paper, we propose SpeechCombine, an instruct","authors_text":"Congrui Du, Kaizhi Qian, Shiyu Chang, Yang Zhang","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-02T14:22:46Z","title":"Unlocking Speech-Text Compositional Powers: Instruction-Following Speech Language Models without Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02214","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:dedf56d2bfdcb60d52e247ce2e7314fc9516b26c64949aa153ce02bd2989b7a7","target":"record","created_at":"2026-07-03T01:17:45Z","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":"147142321a9959675cc671dce89b94c2d04c2d80a64343dbf2fb63227a305249","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-02T14:22:46Z","title_canon_sha256":"35bb8561fe378424ff732172b2ff2f45026c7ab8a3f082d52a31222b83a862f5"},"schema_version":"1.0","source":{"id":"2607.02214","kind":"arxiv","version":1}},"canonical_sha256":"41f067d5265e3cdee072591ef427bbcef61d43bbae4de735b1283ed0d17632c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41f067d5265e3cdee072591ef427bbcef61d43bbae4de735b1283ed0d17632c3","first_computed_at":"2026-07-03T01:17:45.297581Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:45.297581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"afEoSdLYB573AsLGFAjEqkhJE6dQ9lyakUpkPQJAhF5Ite0jlwYpssvnYzSKIUzi97Z+qY4+Bcxq3ww6jQc6Ag==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:45.298020Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02214","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dedf56d2bfdcb60d52e247ce2e7314fc9516b26c64949aa153ce02bd2989b7a7","sha256:2e1ed088fd48e4b590a4f41c1812deac8444a01ded689881a320ae7066bda634"],"state_sha256":"b8a817e290956d9151611f16f7dc0e1cf833a75aa1b380ef7cb5f4c932aa0a3a"}