{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZUOGOBDSLEEGKLN7KE3D43VL5H","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":"61506fa8372a47c5b2685760c608ff81dd3ece4382b3f679da8c5e79a9e753ee","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-07T21:45:04Z","title_canon_sha256":"245f4c687e8e10aba3ac1bd6ff19b01ad8f7caba534bc39f0db6ad7747d2daf3"},"schema_version":"1.0","source":{"id":"2607.06827","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.06827","created_at":"2026-07-09T00:19:29Z"},{"alias_kind":"arxiv_version","alias_value":"2607.06827v1","created_at":"2026-07-09T00:19:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.06827","created_at":"2026-07-09T00:19:29Z"},{"alias_kind":"pith_short_12","alias_value":"ZUOGOBDSLEEG","created_at":"2026-07-09T00:19:29Z"},{"alias_kind":"pith_short_16","alias_value":"ZUOGOBDSLEEGKLN7","created_at":"2026-07-09T00:19:29Z"},{"alias_kind":"pith_short_8","alias_value":"ZUOGOBDS","created_at":"2026-07-09T00:19:29Z"}],"graph_snapshots":[{"event_id":"sha256:c0a15f742742006cb04a1f3c843a57f13b4001369e634b7feeac3ea80de4cd36","target":"graph","created_at":"2026-07-09T00:19:29Z","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/2607.06827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech large language models (Speech LLMs) typically encode speech into sequences far longer than text, creating a major efficiency bottleneck during autoregressive decoding. A common remedy is to compress the speech sequence at the adapter level to remove temporal redundancy before it enters the LLM; however, such early downsampling risks discarding fine-grained information that cannot be recovered. We propose SpeechKV, which applies a learned pooling to the KV cache of speech tokens inside the LLM. This design allows the LLM to fuse speech and text internally while directly accelerating deco","authors_text":"Jinyu Li, Ke-Han Lu, Keqi Deng, Ruchao Fan, Rui Zhao","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-07T21:45:04Z","title":"Compress the Cache, Not the Speech Embedding: KV Compression for Efficient Speech LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.06827","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":"sha256:205ef7301fb7a1fcf7efdf2adbd5ebe5b544e06c0e2b79b9a0a29f9c5439e875","target":"record","created_at":"2026-07-09T00:19:29Z","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":"61506fa8372a47c5b2685760c608ff81dd3ece4382b3f679da8c5e79a9e753ee","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-07T21:45:04Z","title_canon_sha256":"245f4c687e8e10aba3ac1bd6ff19b01ad8f7caba534bc39f0db6ad7747d2daf3"},"schema_version":"1.0","source":{"id":"2607.06827","kind":"arxiv","version":1}},"canonical_sha256":"cd1c6704725908652dbf51363e6eabe9fbd579274d1cd93a5ff437215156c803","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd1c6704725908652dbf51363e6eabe9fbd579274d1cd93a5ff437215156c803","first_computed_at":"2026-07-09T00:19:29.882424Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T00:19:29.882424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/FiX1ax2cC93ovZTG//7yUM6lWNA2wIS+hidZ+jauPvMuAN4gO/UtH0bfSLVciyViBCU5eTbnpzwu+Wy3rgyCQ==","signature_status":"signed_v1","signed_at":"2026-07-09T00:19:29.883221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.06827","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:205ef7301fb7a1fcf7efdf2adbd5ebe5b544e06c0e2b79b9a0a29f9c5439e875","sha256:c0a15f742742006cb04a1f3c843a57f13b4001369e634b7feeac3ea80de4cd36"],"state_sha256":"108e7262b5d5084de93c906a968a4332eda05538de2e315a06b1bb4e3b251725"}