{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2YZEW5VFT5K6QCSE2KRRFRYWRC","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":"5e6f036722e894003bb3b45c24999f569f0e4e04f6bf5b6080f70d9b59d89ecb","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-05T04:50:34Z","title_canon_sha256":"d3cb948c8bccec6f0b09af00832a49c6f1cf68eb31b53dc4359e69eecd11eb2e"},"schema_version":"1.0","source":{"id":"2606.06907","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06907","created_at":"2026-06-08T01:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06907v1","created_at":"2026-06-08T01:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06907","created_at":"2026-06-08T01:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"2YZEW5VFT5K6","created_at":"2026-06-08T01:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"2YZEW5VFT5K6QCSE","created_at":"2026-06-08T01:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"2YZEW5VF","created_at":"2026-06-08T01:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:8f28ccfdd6cfc80921e9f253ca8d1f01191ac2094604dd951e2d71e2940d517f","target":"graph","created_at":"2026-06-08T01:04:35Z","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/2606.06907/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jimin Hong, Ju Yeon Kang, Nam Soo Kim, Seonuk Kim, Yonghyeon Jun, Yoonhyeong Lee","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-05T04:50:34Z","title":"SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06907","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":"sha256:9656f5f1b0d109fb6b672ac0792301337c139eb3f2f14613a2654291eade35af","target":"record","created_at":"2026-06-08T01:04:35Z","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":"5e6f036722e894003bb3b45c24999f569f0e4e04f6bf5b6080f70d9b59d89ecb","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-05T04:50:34Z","title_canon_sha256":"d3cb948c8bccec6f0b09af00832a49c6f1cf68eb31b53dc4359e69eecd11eb2e"},"schema_version":"1.0","source":{"id":"2606.06907","kind":"arxiv","version":1}},"canonical_sha256":"d6324b76a59f55e80a44d2a312c71688afb1e277d5c2ab9028b4da9c64bca730","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6324b76a59f55e80a44d2a312c71688afb1e277d5c2ab9028b4da9c64bca730","first_computed_at":"2026-06-08T01:04:35.143299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:35.143299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6ReAsmO3Bq829wrAdWlF0UnUlRVvc848rp9V/gWaPQiXIQ0f4VgjCYiD1dsC2cHwy50jB5+ZeAd7svotgtA1DA==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:35.144154Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06907","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9656f5f1b0d109fb6b672ac0792301337c139eb3f2f14613a2654291eade35af","sha256:8f28ccfdd6cfc80921e9f253ca8d1f01191ac2094604dd951e2d71e2940d517f"],"state_sha256":"0f50f250d0c142a5d8ca3134ed8c9c351bf7ed27cc61a35a822909d1adfa8c4a"}