{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2YZEW5VFT5K6QCSE2KRRFRYWRC","short_pith_number":"pith:2YZEW5VF","schema_version":"1.0","canonical_sha256":"d6324b76a59f55e80a44d2a312c71688afb1e277d5c2ab9028b4da9c64bca730","source":{"kind":"arxiv","id":"2606.06907","version":1},"attestation_state":"computed","paper":{"title":"SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jimin Hong, Ju Yeon Kang, Nam Soo Kim, Seonuk Kim, Yonghyeon Jun, Yoonhyeong Lee","submitted_at":"2026-06-05T04:50:34Z","abstract_excerpt":"Large audio language models (LALMs) extend large language models with an audio encoder and large-scale audio data. However, the scarcity of high-quality annotated audio data remains a fundamental bottleneck for scaling. Through probing signal detectability analysis, we identify fine-grained spectrotemporal perceptual weaknesses in a foundation LALM. To address these challenges, we propose Spectrotemporal Counting (SpectCount), a data-efficient fine-tuning approach based on fully synthetic audio signals generated on-the-fly, without relying on real-world audio, annotations, or pretrained genera"},"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":"2606.06907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-05T04:50:34Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"d3cb948c8bccec6f0b09af00832a49c6f1cf68eb31b53dc4359e69eecd11eb2e","abstract_canon_sha256":"5e6f036722e894003bb3b45c24999f569f0e4e04f6bf5b6080f70d9b59d89ecb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:35.144154Z","signature_b64":"6ReAsmO3Bq829wrAdWlF0UnUlRVvc848rp9V/gWaPQiXIQ0f4VgjCYiD1dsC2cHwy50jB5+ZeAd7svotgtA1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6324b76a59f55e80a44d2a312c71688afb1e277d5c2ab9028b4da9c64bca730","last_reissued_at":"2026-06-08T01:04:35.143299Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:35.143299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jimin Hong, Ju Yeon Kang, Nam Soo Kim, Seonuk Kim, Yonghyeon Jun, Yoonhyeong Lee","submitted_at":"2026-06-05T04:50:34Z","abstract_excerpt":"Large audio language models (LALMs) extend large language models with an audio encoder and large-scale audio data. However, the scarcity of high-quality annotated audio data remains a fundamental bottleneck for scaling. Through probing signal detectability analysis, we identify fine-grained spectrotemporal perceptual weaknesses in a foundation LALM. To address these challenges, we propose Spectrotemporal Counting (SpectCount), a data-efficient fine-tuning approach based on fully synthetic audio signals generated on-the-fly, without relying on real-world audio, annotations, or pretrained genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06907","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/2606.06907/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":"2606.06907","created_at":"2026-06-08T01:04:35.143460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06907v1","created_at":"2026-06-08T01:04:35.143460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06907","created_at":"2026-06-08T01:04:35.143460+00:00"},{"alias_kind":"pith_short_12","alias_value":"2YZEW5VFT5K6","created_at":"2026-06-08T01:04:35.143460+00:00"},{"alias_kind":"pith_short_16","alias_value":"2YZEW5VFT5K6QCSE","created_at":"2026-06-08T01:04:35.143460+00:00"},{"alias_kind":"pith_short_8","alias_value":"2YZEW5VF","created_at":"2026-06-08T01:04:35.143460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.06907","citing_title":"SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2YZEW5VFT5K6QCSE2KRRFRYWRC","json":"https://pith.science/pith/2YZEW5VFT5K6QCSE2KRRFRYWRC.json","graph_json":"https://pith.science/api/pith-number/2YZEW5VFT5K6QCSE2KRRFRYWRC/graph.json","events_json":"https://pith.science/api/pith-number/2YZEW5VFT5K6QCSE2KRRFRYWRC/events.json","paper":"https://pith.science/paper/2YZEW5VF"},"agent_actions":{"view_html":"https://pith.science/pith/2YZEW5VFT5K6QCSE2KRRFRYWRC","download_json":"https://pith.science/pith/2YZEW5VFT5K6QCSE2KRRFRYWRC.json","view_paper":"https://pith.science/paper/2YZEW5VF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06907&json=true","fetch_graph":"https://pith.science/api/pith-number/2YZEW5VFT5K6QCSE2KRRFRYWRC/graph.json","fetch_events":"https://pith.science/api/pith-number/2YZEW5VFT5K6QCSE2KRRFRYWRC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2YZEW5VFT5K6QCSE2KRRFRYWRC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2YZEW5VFT5K6QCSE2KRRFRYWRC/action/storage_attestation","attest_author":"https://pith.science/pith/2YZEW5VFT5K6QCSE2KRRFRYWRC/action/author_attestation","sign_citation":"https://pith.science/pith/2YZEW5VFT5K6QCSE2KRRFRYWRC/action/citation_signature","submit_replication":"https://pith.science/pith/2YZEW5VFT5K6QCSE2KRRFRYWRC/action/replication_record"}},"created_at":"2026-06-08T01:04:35.143460+00:00","updated_at":"2026-06-08T01:04:35.143460+00:00"}