{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:I24L2MWN7N7XIQC4GLU75DY4IV","short_pith_number":"pith:I24L2MWN","canonical_record":{"source":{"id":"2608.08569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T08:17:18Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"b01768795e4b59b26876c197eb0f117ecbf2dff3ddff26590191dae921d2dc8e","abstract_canon_sha256":"05a9a29f7100ecf2bd09d8258c4236c0fbd7d6089d40e0f401402806b72f4ff7"},"schema_version":"1.0"},"canonical_sha256":"46b8bd32cdfb7f74405c32e9fe8f1c457fbb721b4f7ab3f0a2022ac2b7d3464e","source":{"kind":"arxiv","id":"2608.08569","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08569","created_at":"2026-08-11T01:23:00Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08569v1","created_at":"2026-08-11T01:23:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08569","created_at":"2026-08-11T01:23:00Z"},{"alias_kind":"pith_short_12","alias_value":"I24L2MWN7N7X","created_at":"2026-08-11T01:23:00Z"},{"alias_kind":"pith_short_16","alias_value":"I24L2MWN7N7XIQC4","created_at":"2026-08-11T01:23:00Z"},{"alias_kind":"pith_short_8","alias_value":"I24L2MWN","created_at":"2026-08-11T01:23:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:I24L2MWN7N7XIQC4GLU75DY4IV","target":"record","payload":{"canonical_record":{"source":{"id":"2608.08569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T08:17:18Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"b01768795e4b59b26876c197eb0f117ecbf2dff3ddff26590191dae921d2dc8e","abstract_canon_sha256":"05a9a29f7100ecf2bd09d8258c4236c0fbd7d6089d40e0f401402806b72f4ff7"},"schema_version":"1.0"},"canonical_sha256":"46b8bd32cdfb7f74405c32e9fe8f1c457fbb721b4f7ab3f0a2022ac2b7d3464e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:23:00.551809Z","signature_b64":"9Br0wuWQiYs9Cggs/H7/A+ZD4eLSKdUFZmRFUs2FOfv9BrI1cXdH/XpeMx2qtGNpOIyIdWdxGvT82mjL7iIiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46b8bd32cdfb7f74405c32e9fe8f1c457fbb721b4f7ab3f0a2022ac2b7d3464e","last_reissued_at":"2026-08-11T01:23:00.549399Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:23:00.549399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.08569","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-11T01:23:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d2SMzMcIHxedhFVkPsOTW1ZtA9eO3BOOlqg9ZZ+GZ6/4EBn0YLMQYhhYLWL6jNL1MHCIrLcsx1s2kSCwtm6yAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:38:49.153328Z"},"content_sha256":"4188b7111e282ccd0ec9644c37f8bfdb570007ccc3dab2fd561493702c40c133","schema_version":"1.0","event_id":"sha256:4188b7111e282ccd0ec9644c37f8bfdb570007ccc3dab2fd561493702c40c133"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:I24L2MWN7N7XIQC4GLU75DY4IV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.AI","authors_text":"Dongjie Fu, Fangming Feng, Linjun Li, Tao Jin, Wenshi Chen, Wenxu Jia, Xize Cheng, Yingming Li, Zhou Zhao","submitted_at":"2026-08-09T08:17:18Z","abstract_excerpt":"Recent advancements in Speech Large Language Models have demonstrated remarkable capabilities in understanding complex audio tasks. Despite this progress, their long-context inference remains severely bottlenecked by prohibitive KV cache memory demands. Existing text-centric compression methods struggle here, often disrupting speech continuity or discarding crucial semantic cues. To address this, we propose VoxZip, a train-free, two-stage semantic-anchored KV cache compression framework. The first stage uses automatic speech recognition (ASR) transcriptions as explicit semantic anchors to temp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08569","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/2608.08569/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-11T01:23:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UDcJ9DPJLOIY3FeDuoY679rxjwgSaQoTQT1XEe0ATUlfWqfooHrYn4X7qvVlzyT4ZM3LUSTWNfe7/kmxRRkJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:38:49.153849Z"},"content_sha256":"3baed72690d38462c2235936cfce5861527bdbda9d39f7ba40fed0dcdef57a0a","schema_version":"1.0","event_id":"sha256:3baed72690d38462c2235936cfce5861527bdbda9d39f7ba40fed0dcdef57a0a"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:I24L2MWN7N7XIQC4GLU75DY4IV","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2025.acl-long.682) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Wenqian Cui, Dianzhi Yu, Xiaoqi Jiao, Ziqiao Meng, Guangyan Zhang, Qichao Wang, Steven Y. Guo, and Irwin King. 2025. Recent Advances in Speech Language Models: A Survey. InProceedings of the 63rd Annual Meeting of the Association for Comput","arxiv_id":"2608.08569","detector":"doi_compliance","evidence":{"ref_index":6,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v1/","reconstructed_doi":"10.18653/v1/2025.acl-long.682"},"severity":"advisory","ref_index":6,"audited_at":"2026-08-14T05:18:33.496301Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2025.acl-long.682","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"99dc2e5b19fa3d47030eaa6d8523c3a206f1b2af8b6285d30d71c4732d536637","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":19620,"payload_sha256":"41f37800364ad5800e882567864e08d0c5b4967e971ca1e9d7c9141df02a890c","signature_b64":"/B8mvfEG8e13XIadpYvD/b42gu6s8kOaWGTELGtoSvSYJb9L6Ed+z8yF9jG+qsyqD5/DvLdTVYXoa4uGKx0ACA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-14T05:23:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U9es2g11msjiBz+BUZiHf5pthjResKcToo4pcFSCV1KdA9WM6OZZ3thZUpMbcweF/sb3CurhIMbO8pW2RxTdBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:38:49.157576Z"},"content_sha256":"a4a5d099237cd061d4dac1e4496e96bbdd2562ac21a2764ad20db953e1930d54","schema_version":"1.0","event_id":"sha256:a4a5d099237cd061d4dac1e4496e96bbdd2562ac21a2764ad20db953e1930d54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I24L2MWN7N7XIQC4GLU75DY4IV/bundle.json","state_url":"https://pith.science/pith/I24L2MWN7N7XIQC4GLU75DY4IV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I24L2MWN7N7XIQC4GLU75DY4IV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T10:38:49Z","links":{"resolver":"https://pith.science/pith/I24L2MWN7N7XIQC4GLU75DY4IV","bundle":"https://pith.science/pith/I24L2MWN7N7XIQC4GLU75DY4IV/bundle.json","state":"https://pith.science/pith/I24L2MWN7N7XIQC4GLU75DY4IV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I24L2MWN7N7XIQC4GLU75DY4IV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I24L2MWN7N7XIQC4GLU75DY4IV","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"05a9a29f7100ecf2bd09d8258c4236c0fbd7d6089d40e0f401402806b72f4ff7","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T08:17:18Z","title_canon_sha256":"b01768795e4b59b26876c197eb0f117ecbf2dff3ddff26590191dae921d2dc8e"},"schema_version":"1.0","source":{"id":"2608.08569","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08569","created_at":"2026-08-11T01:23:00Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08569v1","created_at":"2026-08-11T01:23:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08569","created_at":"2026-08-11T01:23:00Z"},{"alias_kind":"pith_short_12","alias_value":"I24L2MWN7N7X","created_at":"2026-08-11T01:23:00Z"},{"alias_kind":"pith_short_16","alias_value":"I24L2MWN7N7XIQC4","created_at":"2026-08-11T01:23:00Z"},{"alias_kind":"pith_short_8","alias_value":"I24L2MWN","created_at":"2026-08-11T01:23:00Z"}],"graph_snapshots":[{"event_id":"sha256:3baed72690d38462c2235936cfce5861527bdbda9d39f7ba40fed0dcdef57a0a","target":"graph","created_at":"2026-08-11T01:23:00Z","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/2608.08569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Speech Large Language Models have demonstrated remarkable capabilities in understanding complex audio tasks. Despite this progress, their long-context inference remains severely bottlenecked by prohibitive KV cache memory demands. Existing text-centric compression methods struggle here, often disrupting speech continuity or discarding crucial semantic cues. To address this, we propose VoxZip, a train-free, two-stage semantic-anchored KV cache compression framework. The first stage uses automatic speech recognition (ASR) transcriptions as explicit semantic anchors to temp","authors_text":"Dongjie Fu, Fangming Feng, Linjun Li, Tao Jin, Wenshi Chen, Wenxu Jia, Xize Cheng, Yingming Li, Zhou Zhao","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T08:17:18Z","title":"VoxZip: Semantic-Anchored Temporal KV Cache Compression for Long-Context Audio Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08569","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":"sha256:4188b7111e282ccd0ec9644c37f8bfdb570007ccc3dab2fd561493702c40c133","target":"record","created_at":"2026-08-11T01:23:00Z","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":"05a9a29f7100ecf2bd09d8258c4236c0fbd7d6089d40e0f401402806b72f4ff7","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T08:17:18Z","title_canon_sha256":"b01768795e4b59b26876c197eb0f117ecbf2dff3ddff26590191dae921d2dc8e"},"schema_version":"1.0","source":{"id":"2608.08569","kind":"arxiv","version":1}},"canonical_sha256":"46b8bd32cdfb7f74405c32e9fe8f1c457fbb721b4f7ab3f0a2022ac2b7d3464e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46b8bd32cdfb7f74405c32e9fe8f1c457fbb721b4f7ab3f0a2022ac2b7d3464e","first_computed_at":"2026-08-11T01:23:00.549399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:23:00.549399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Br0wuWQiYs9Cggs/H7/A+ZD4eLSKdUFZmRFUs2FOfv9BrI1cXdH/XpeMx2qtGNpOIyIdWdxGvT82mjL7iIiCw==","signature_status":"signed_v1","signed_at":"2026-08-11T01:23:00.551809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08569","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4188b7111e282ccd0ec9644c37f8bfdb570007ccc3dab2fd561493702c40c133","sha256:3baed72690d38462c2235936cfce5861527bdbda9d39f7ba40fed0dcdef57a0a","sha256:a4a5d099237cd061d4dac1e4496e96bbdd2562ac21a2764ad20db953e1930d54"],"state_sha256":"078aa55ea3aa4248b6d6ee123934101ca8f2f0bfcb973d7c6d2dab5eff60bbfb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EaHaZp4ESEY61Ow8Uw/V4AsJsTKDliZO1Ry2ER9xh6feMrT3BO9cJLCXfOE+2GfJH4j9fn318HB/+xljRdZFDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T10:38:49.159718Z","bundle_sha256":"34fc13550b1f4d26229aac8d1da156ae3ceba04a3e85a2a73a2d02dfbf60bf55"}}