{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JDB7SVHU5WS5B4I2F5FGU2JAZB","short_pith_number":"pith:JDB7SVHU","schema_version":"1.0","canonical_sha256":"48c3f954f4eda5d0f11a2f4a6a6920c87b86be67f9a643de47206f0532ac512e","source":{"kind":"arxiv","id":"2605.27976","version":1},"attestation_state":"computed","paper":{"title":"VoiceGiraffe: A Benchmark for Extreme Long-Context Audio-Language Understanding","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","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","submitted_at":"2026-05-27T05:15:14Z","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"},"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":"2605.27976","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-27T05:15:14Z","cross_cats_sorted":[],"title_canon_sha256":"856731d1949c4f9deb62f734e26370d4460ac582fa1ef237de2411d9349ad1f8","abstract_canon_sha256":"52c872f4fb379fa4ab3df4d47e8dea935573e1522197a14118a8497833127a60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:55.058124Z","signature_b64":"WapEq4jKG2yX1TluZktIyPqxh0EG6H4G/4eepUr3mUdqpFVKQNx+yb356c0seS7rtgp5T5k14/moMZJP2rksAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48c3f954f4eda5d0f11a2f4a6a6920c87b86be67f9a643de47206f0532ac512e","last_reissued_at":"2026-05-28T01:04:55.057705Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:55.057705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoiceGiraffe: A Benchmark for Extreme Long-Context Audio-Language Understanding","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","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","submitted_at":"2026-05-27T05:15:14Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27976","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/2605.27976/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":"2605.27976","created_at":"2026-05-28T01:04:55.057763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27976v1","created_at":"2026-05-28T01:04:55.057763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27976","created_at":"2026-05-28T01:04:55.057763+00:00"},{"alias_kind":"pith_short_12","alias_value":"JDB7SVHU5WS5","created_at":"2026-05-28T01:04:55.057763+00:00"},{"alias_kind":"pith_short_16","alias_value":"JDB7SVHU5WS5B4I2","created_at":"2026-05-28T01:04:55.057763+00:00"},{"alias_kind":"pith_short_8","alias_value":"JDB7SVHU","created_at":"2026-05-28T01:04:55.057763+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/JDB7SVHU5WS5B4I2F5FGU2JAZB","json":"https://pith.science/pith/JDB7SVHU5WS5B4I2F5FGU2JAZB.json","graph_json":"https://pith.science/api/pith-number/JDB7SVHU5WS5B4I2F5FGU2JAZB/graph.json","events_json":"https://pith.science/api/pith-number/JDB7SVHU5WS5B4I2F5FGU2JAZB/events.json","paper":"https://pith.science/paper/JDB7SVHU"},"agent_actions":{"view_html":"https://pith.science/pith/JDB7SVHU5WS5B4I2F5FGU2JAZB","download_json":"https://pith.science/pith/JDB7SVHU5WS5B4I2F5FGU2JAZB.json","view_paper":"https://pith.science/paper/JDB7SVHU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27976&json=true","fetch_graph":"https://pith.science/api/pith-number/JDB7SVHU5WS5B4I2F5FGU2JAZB/graph.json","fetch_events":"https://pith.science/api/pith-number/JDB7SVHU5WS5B4I2F5FGU2JAZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JDB7SVHU5WS5B4I2F5FGU2JAZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JDB7SVHU5WS5B4I2F5FGU2JAZB/action/storage_attestation","attest_author":"https://pith.science/pith/JDB7SVHU5WS5B4I2F5FGU2JAZB/action/author_attestation","sign_citation":"https://pith.science/pith/JDB7SVHU5WS5B4I2F5FGU2JAZB/action/citation_signature","submit_replication":"https://pith.science/pith/JDB7SVHU5WS5B4I2F5FGU2JAZB/action/replication_record"}},"created_at":"2026-05-28T01:04:55.057763+00:00","updated_at":"2026-05-28T01:04:55.057763+00:00"}