{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JDB7SVHU5WS5B4I2F5FGU2JAZB","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":"52c872f4fb379fa4ab3df4d47e8dea935573e1522197a14118a8497833127a60","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-27T05:15:14Z","title_canon_sha256":"856731d1949c4f9deb62f734e26370d4460ac582fa1ef237de2411d9349ad1f8"},"schema_version":"1.0","source":{"id":"2605.27976","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27976","created_at":"2026-05-28T01:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27976v1","created_at":"2026-05-28T01:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27976","created_at":"2026-05-28T01:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"JDB7SVHU5WS5","created_at":"2026-05-28T01:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"JDB7SVHU5WS5B4I2","created_at":"2026-05-28T01:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"JDB7SVHU","created_at":"2026-05-28T01:04:55Z"}],"graph_snapshots":[{"event_id":"sha256:d96a1ce173b8c0ccbfdf9518997dc0130fb3465bdf19b15024fcd6074bdd42ab","target":"graph","created_at":"2026-05-28T01:04:55Z","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/2605.27976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While large audio language models (LALMs) have achieved remarkable progress in audio processing at the second- or minute-level scale, understanding hour-level audio remains a fundamental bottleneck. Existing benchmarks predominantly rely on short clips or artificially concatenated segments, failing to faithfully assess LALM capacity for long-range information comprehension in real-world scenarios such as podcasts and lengthy speeches. To address this gap, we introduce VoiceGiraffe, a novel benchmark designed to rigorously evaluate LALMs across diverse real-world scenarios, modalities, and lang","authors_text":"Boyu Li, Bo Zheng, Dongxiao Wang, Haoxiang Shi, Jashin Ye, Jingchen Shu, Jun Song, Kunpeng Wang, Mingyang Han, Sashuai Zhou, Weihuang Lin, Yixuan Ye, Zeyu Yuan","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-27T05:15:14Z","title":"VoiceGiraffe: A Benchmark for Extreme Long-Context Audio-Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27976","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:fe3405f54310e1838fc08b2f9de0113ebd65f2a179f7d09209d9f4ed2b15d4a1","target":"record","created_at":"2026-05-28T01:04:55Z","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":"52c872f4fb379fa4ab3df4d47e8dea935573e1522197a14118a8497833127a60","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-27T05:15:14Z","title_canon_sha256":"856731d1949c4f9deb62f734e26370d4460ac582fa1ef237de2411d9349ad1f8"},"schema_version":"1.0","source":{"id":"2605.27976","kind":"arxiv","version":1}},"canonical_sha256":"48c3f954f4eda5d0f11a2f4a6a6920c87b86be67f9a643de47206f0532ac512e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48c3f954f4eda5d0f11a2f4a6a6920c87b86be67f9a643de47206f0532ac512e","first_computed_at":"2026-05-28T01:04:55.057705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:55.057705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WapEq4jKG2yX1TluZktIyPqxh0EG6H4G/4eepUr3mUdqpFVKQNx+yb356c0seS7rtgp5T5k14/moMZJP2rksAg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:55.058124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27976","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe3405f54310e1838fc08b2f9de0113ebd65f2a179f7d09209d9f4ed2b15d4a1","sha256:d96a1ce173b8c0ccbfdf9518997dc0130fb3465bdf19b15024fcd6074bdd42ab"],"state_sha256":"eb009138a2da001aed2126bcf5be864de3b4c621704b9cff29708c7e9eb36646"}